litellm - 💡(How to fix) Fix [Bug]: Semantic MCP Tool Filtering emits invalid OpenAI tool schema

2026-05-25 15:01:07 - LiteLLM - INFO - mcp_server_manager.py:3060 - reload_servers_from_database() - Found 4 MCP servers in database
15:01:07 - LiteLLM Proxy:INFO: proxy_server.py:6372 - Loading 0 search tool(s) from database into router
2026-05-25 15:01:07 - LiteLLM Proxy - INFO - proxy_server.py:6372 - _init_search_tools_in_db() - Loading 0 search tool(s) from database into router
15:01:07 - LiteLLM Proxy:INFO: tool_registry_writer.py:329 - ToolPolicyRegistry: synced 41 tool policies and 0 object permissions from DB
2026-05-25 15:01:07 - LiteLLM Proxy - INFO - tool_registry_writer.py:329 - sync_tool_policy_from_db() - ToolPolicyRegistry: synced 41 tool policies and 0 object permissions from DB
15:01:16 - LiteLLM Proxy:INFO: route_llm_request.py:176 - SESSION REUSE: Attached shared aiohttp session to request (ID: 125568310588960)
2026-05-25 15:01:16 - LiteLLM Proxy - INFO - route_llm_request.py:176 - add_shared_session_to_data() - SESSION REUSE: Attached shared aiohttp session to request (ID: 125568310588960)
15:01:16 - LiteLLM:INFO: mcp_server_manager.py:1425 - _get_tools_from_server for github...
2026-05-25 15:01:16 - LiteLLM - INFO - mcp_server_manager.py:1425 - _get_tools_from_server() - _get_tools_from_server for github...
15:01:16 - LiteLLM:INFO: mcp_server_manager.py:1425 - _get_tools_from_server for searxng...
2026-05-25 15:01:16 - LiteLLM - INFO - mcp_server_manager.py:1425 - _get_tools_from_server() - _get_tools_from_server for searxng...
15:01:16 - LiteLLM:INFO: mcp_server_manager.py:1425 - _get_tools_from_server for GPT_Reseacher...
2026-05-25 15:01:16 - LiteLLM - INFO - mcp_server_manager.py:1425 - _get_tools_from_server() - _get_tools_from_server for GPT_Reseacher...
15:01:16 - LiteLLM:INFO: mcp_server_manager.py:1425 - _get_tools_from_server for tavily...
2026-05-25 15:01:16 - LiteLLM - INFO - mcp_server_manager.py:1425 - _get_tools_from_server() - _get_tools_from_server for tavily...
2026-05-25 15:01:16 - mcp.client.streamable_http - INFO - streamable_http.py:181 - _maybe_extract_session_id_from_response() - Received session ID: 39797865769f4e98b9591cb26acd2b56
2026-05-25 15:01:16 - mcp.client.streamable_http - INFO - streamable_http.py:193 - _maybe_extract_protocol_version_from_message() - Negotiated protocol version: 2025-11-25
2026-05-25 15:01:16 - mcp.client.streamable_http - INFO - streamable_http.py:181 - _maybe_extract_session_id_from_response() - Received session ID: 44fd256bfc8c420993dfe039c966b86a
2026-05-25 15:01:16 - mcp.client.streamable_http - INFO - streamable_http.py:193 - _maybe_extract_protocol_version_from_message() - Negotiated protocol version: 2025-11-25
2026-05-25 15:01:16 - mcp.client.streamable_http - INFO - streamable_http.py:298 - handle_get_stream() - GET stream disconnected, reconnecting in 1000ms...
15:01:16 - LiteLLM:INFO: client.py:437 - MCP client listed 5 tools from http://gptr-mcp:8000/mcp: ['deep_research', 'quick_search', 'write_report', 'get_research_sources', 'get_research_context']
2026-05-25 15:01:16 - LiteLLM - INFO - client.py:437 - list_tools() - MCP client listed 5 tools from http://gptr-mcp:8000/mcp: ['deep_research', 'quick_search', 'write_report', 'get_research_sources', 'get_research_context']
15:01:16 - LiteLLM:INFO: mcp_server_manager.py:2218 - Successfully fetched 5 tools from server GPT_Reseacher
2026-05-25 15:01:16 - LiteLLM - INFO - mcp_server_manager.py:2218 - _create_prefixed_tools() - Successfully fetched 5 tools from server GPT_Reseacher
2026-05-25 15:01:16 - mcp.client.streamable_http - INFO - streamable_http.py:298 - handle_get_stream() - GET stream disconnected, reconnecting in 1000ms...
15:01:16 - LiteLLM:WARNING: user_api_key_auth_mcp.py:826 - Failed to get allowed tools for server: 404: {'error': "Team doesn't exist in db. Team=litellm-dashboard. Create team via `/team/new` call."}
2026-05-25 15:01:16 - LiteLLM - WARNING - user_api_key_auth_mcp.py:826 - get_allowed_tools_for_server() - Failed to get allowed tools for server: 404: {'error': "Team doesn't exist in db. Team=litellm-dashboard. Create team via `/team/new` call."}
15:01:16 - LiteLLM:INFO: client.py:437 - MCP client listed 3 tools from http://searx-crawl-mcp:9555/mcp: ['crawl', 'crawl_site', 'search']
2026-05-25 15:01:16 - LiteLLM - INFO - client.py:437 - list_tools() - MCP client listed 3 tools from http://searx-crawl-mcp:9555/mcp: ['crawl', 'crawl_site', 'search']
15:01:16 - LiteLLM:INFO: mcp_server_manager.py:2218 - Successfully fetched 3 tools from server searxng
2026-05-25 15:01:16 - LiteLLM - INFO - mcp_server_manager.py:2218 - _create_prefixed_tools() - Successfully fetched 3 tools from server searxng
15:01:16 - LiteLLM:WARNING: user_api_key_auth_mcp.py:826 - Failed to get allowed tools for server: 404: {'error': "Team doesn't exist in db. Team=litellm-dashboard. Create team via `/team/new` call."}
2026-05-25 15:01:16 - LiteLLM - WARNING - user_api_key_auth_mcp.py:826 - get_allowed_tools_for_server() - Failed to get allowed tools for server: 404: {'error': "Team doesn't exist in db. Team=litellm-dashboard. Create team via `/team/new` call."}
2026-05-25 15:01:16 - mcp.client.streamable_http - INFO - streamable_http.py:181 - _maybe_extract_session_id_from_response() - Received session ID: O7YGX44SQUEAWNG5J6KRFHBC4J
2026-05-25 15:01:16 - mcp.client.streamable_http - INFO - streamable_http.py:193 - _maybe_extract_protocol_version_from_message() - Negotiated protocol version: 2025-11-25
2026-05-25 15:01:16 - mcp.client.streamable_http - INFO - streamable_http.py:298 - handle_get_stream() - GET stream disconnected, reconnecting in 1000ms...
Tavily MCP server running on stdio
15:01:17 - LiteLLM:INFO: client.py:437 - MCP client listed 5 tools from stdio: ['tavily_search', 'tavily_extract', 'tavily_crawl', 'tavily_map', 'tavily_research']
2026-05-25 15:01:17 - LiteLLM - INFO - client.py:437 - list_tools() - MCP client listed 5 tools from stdio: ['tavily_search', 'tavily_extract', 'tavily_crawl', 'tavily_map', 'tavily_research']
15:01:17 - LiteLLM:INFO: mcp_server_manager.py:2218 - Successfully fetched 5 tools from server tavily
2026-05-25 15:01:17 - LiteLLM - INFO - mcp_server_manager.py:2218 - _create_prefixed_tools() - Successfully fetched 5 tools from server tavily
15:01:17 - LiteLLM:WARNING: user_api_key_auth_mcp.py:826 - Failed to get allowed tools for server: 404: {'error': "Team doesn't exist in db. Team=litellm-dashboard. Create team via `/team/new` call."}
2026-05-25 15:01:17 - LiteLLM - WARNING - user_api_key_auth_mcp.py:826 - get_allowed_tools_for_server() - Failed to get allowed tools for server: 404: {'error': "Team doesn't exist in db. Team=litellm-dashboard. Create team via `/team/new` call."}
15:01:17 - LiteLLM:INFO: client.py:437 - MCP client listed 20 tools from http://github-mcp-server:8082/mcp/: ['get_commit', 'get_file_contents', 'get_label', 'get_latest_release', 'get_me', 'get_release_by_tag', 'get_tag', 'issue_read', 'list_branches', 'list_commits', 'list_issues', 'list_pull_requests', 'list_releases', 'list_tags', 'pull_request_read', 'search_code', 'search_issues', 'search_pull_requests', 'search_repositories', 'search_users']
2026-05-25 15:01:17 - LiteLLM - INFO - client.py:437 - list_tools() - MCP client listed 20 tools from http://github-mcp-server:8082/mcp/: ['get_commit', 'get_file_contents', 'get_label', 'get_latest_release', 'get_me', 'get_release_by_tag', 'get_tag', 'issue_read', 'list_branches', 'list_commits', 'list_issues', 'list_pull_requests', 'list_releases', 'list_tags', 'pull_request_read', 'search_code', 'search_issues', 'search_pull_requests', 'search_repositories', 'search_users']
15:01:17 - LiteLLM:INFO: mcp_server_manager.py:2218 - Successfully fetched 20 tools from server github
2026-05-25 15:01:17 - LiteLLM - INFO - mcp_server_manager.py:2218 - _create_prefixed_tools() - Successfully fetched 20 tools from server github
15:01:17 - LiteLLM:WARNING: user_api_key_auth_mcp.py:826 - Failed to get allowed tools for server: 404: {'error': "Team doesn't exist in db. Team=litellm-dashboard. Create team via `/team/new` call."}
2026-05-25 15:01:17 - LiteLLM - WARNING - user_api_key_auth_mcp.py:826 - get_allowed_tools_for_server() - Failed to get allowed tools for server: 404: {'error': "Team doesn't exist in db. Team=litellm-dashboard. Create team via `/team/new` call."}
15:01:17 - LiteLLM:INFO: server.py:1442 - Successfully fetched 33 tools total from all MCP servers
2026-05-25 15:01:17 - LiteLLM - INFO - server.py:1442 - _get_tools_from_mcp_servers() - Successfully fetched 33 tools total from all MCP servers
15:01:17 - LiteLLM:INFO: utils.py:4054 - 
LiteLLM completion() model= byteshape/Qwen3.6-35B-A3B-MTP-GGUF:19BPW; provider = custom_openai
2026-05-25 15:01:17 - LiteLLM - INFO - utils.py:4054 - _check_valid_arg() - 
LiteLLM completion() model= byteshape/Qwen3.6-35B-A3B-MTP-GGUF:19BPW; provider = custom_openai
15:01:18 - LiteLLM Proxy:INFO: spend_update_queue.py:35 - Spend tracking - flushed 4 spend update items from in-memory queue
2026-05-25 15:01:18 - LiteLLM Proxy - INFO - spend_update_queue.py:35 - flush_and_get_aggregated_db_spend_update_transactions() - Spend tracking - flushed 4 spend update items from in-memory queue
15:01:18 - LiteLLM Proxy:INFO: daily_spend_update_queue.py:90 - Spend tracking - flushed 1 daily spend update items from in-memory queue
2026-05-25 15:01:18 - LiteLLM Proxy - INFO - daily_spend_update_queue.py:90 - flush_and_get_aggregated_daily_spend_update_transactions() - Spend tracking - flushed 1 daily spend update items from in-memory queue
15:01:18 - LiteLLM Proxy:INFO: daily_spend_update_queue.py:90 - Spend tracking - flushed 1 daily spend update items from in-memory queue
2026-05-25 15:01:18 - LiteLLM Proxy - INFO - daily_spend_update_queue.py:90 - flush_and_get_aggregated_daily_spend_update_transactions() - Spend tracking - flushed 1 daily spend update items from in-memory queue
15:01:18 - LiteLLM Proxy:INFO: utils.py:5215 - Spend tracking - processing 1 spend logs for DB write
2026-05-25 15:01:18 - LiteLLM Proxy - INFO - utils.py:5215 - update_spend_logs() - Spend tracking - processing 1 spend logs for DB write
15:01:24 - LiteLLM Router:INFO: router.py:2503 - litellm.acompletion(model=byteshape/Qwen3.6-35B-A3B-MTP-GGUF:19BPW) 200 OK
2026-05-25 15:01:24 - LiteLLM Router - INFO - router.py:2503 - _acompletion() - litellm.acompletion(model=byteshape/Qwen3.6-35B-A3B-MTP-GGUF:19BPW) 200 OK
INFO:     192.168.12.198:55407 - "POST /chat/completions HTTP/1.1" 200 OK
INFO:     192.168.12.198:59360 - "GET /v1/mcp/server HTTP/1.1" 200 OK
INFO:     192.168.12.198:58132 - "GET /v1/mcp/toolset HTTP/1.1" 200 OK
INFO:     192.168.12.198:54225 - "GET /config/list?config_type=general_settings HTTP/1.1" 200 OK
INFO:     192.168.12.198:55878 - "GET /model_group/info HTTP/1.1" 200 OK
INFO:     192.168.12.198:62515 - "GET /v1/mcp/network/client-ip HTTP/1.1" 200 OK
INFO:     192.168.12.198:55878 - "HEAD / HTTP/1.1" 200 OK
INFO:     192.168.12.198:55878 - "GET /__next._tree.txt?_rsc=1r34m HTTP/1.1" 404 Not Found
INFO:     192.168.12.198:59360 - "GET /v1/mcp/server/submissions HTTP/1.1" 200 OK
2026-05-25 15:01:29 - mcp.client.streamable_http - INFO - streamable_http.py:181 - _maybe_extract_session_id_from_response() - Received session ID: cee2591247324aa0a2766abe6a9e9289
2026-05-25 15:01:29 - mcp.client.streamable_http - INFO - streamable_http.py:181 - _maybe_extract_session_id_from_response() - Received session ID: a5490b2d69e2446094cb7b4307182e66
2026-05-25 15:01:29 - mcp.client.streamable_http - INFO - streamable_http.py:193 - _maybe_extract_protocol_version_from_message() - Negotiated protocol version: 2025-11-25
2026-05-25 15:01:29 - mcp.client.streamable_http - INFO - streamable_http.py:193 - _maybe_extract_protocol_version_from_message() - Negotiated protocol version: 2025-11-25
INFO:     192.168.12.198:54225 - "GET /model_group/info HTTP/1.1" 200 OK
INFO:     192.168.12.198:62515 - "GET /config/list?config_type=general_settings HTTP/1.1" 200 OK
2026-05-25 15:01:29 - mcp.client.streamable_http - INFO - streamable_http.py:298 - handle_get_stream() - GET stream disconnected, reconnecting in 1000ms...
2026-05-25 15:01:29 - mcp.client.streamable_http - INFO - streamable_http.py:298 - handle_get_stream() - GET stream disconnected, reconnecting in 1000ms...
2026-05-25 15:01:30 - mcp.client.streamable_http - INFO - streamable_http.py:181 - _maybe_extract_session_id_from_response() - Received session ID: 2HVTBMV22QDJ33DZOYMB7LE7NW
2026-05-25 15:01:30 - mcp.client.streamable_http - INFO - streamable_http.py:193 - _maybe_extract_protocol_version_from_message() - Negotiated protocol version: 2025-11-25
2026-05-25 15:01:30 - mcp.client.streamable_http - INFO - streamable_http.py:298 - handle_get_stream() - GET stream disconnected, reconnecting in 1000ms...
Tavily MCP server running on stdio
15:01:33 - LiteLLM Proxy:INFO: utils.py:3696 - Data Inserted into Config Table
2026-05-25 15:01:33 - LiteLLM Proxy - INFO - utils.py:3696 - insert_data() - Data Inserted into Config Table
15:01:33 - LiteLLM:INFO: mcp_server_manager.py:1425 - _get_tools_from_server for github...
2026-05-25 15:01:33 - LiteLLM - INFO - mcp_server_manager.py:1425 - _get_tools_from_server() - _get_tools_from_server for github...
2026-05-25 15:01:33 - mcp.client.streamable_http - INFO - streamable_http.py:181 - _maybe_extract_session_id_from_response() - Received session ID: FOZY6TQFCREXOWZO2AB6KLE2BV
2026-05-25 15:01:33 - mcp.client.streamable_http - INFO - streamable_http.py:193 - _maybe_extract_protocol_version_from_message() - Negotiated protocol version: 2025-11-25
2026-05-25 15:01:33 - mcp.client.streamable_http - INFO - streamable_http.py:298 - handle_get_stream() - GET stream disconnected, reconnecting in 1000ms...
15:01:34 - LiteLLM:INFO: client.py:437 - MCP client listed 20 tools from http://github-mcp-server:8082/mcp/: ['get_commit', 'get_file_contents', 'get_label', 'get_latest_release', 'get_me', 'get_release_by_tag', 'get_tag', 'issue_read', 'list_branches', 'list_commits', 'list_issues', 'list_pull_requests', 'list_releases', 'list_tags', 'pull_request_read', 'search_code', 'search_issues', 'search_pull_requests', 'search_repositories', 'search_users']
2026-05-25 15:01:34 - LiteLLM - INFO - client.py:437 - list_tools() - MCP client listed 20 tools from http://github-mcp-server:8082/mcp/: ['get_commit', 'get_file_contents', 'get_label', 'get_latest_release', 'get_me', 'get_release_by_tag', 'get_tag', 'issue_read', 'list_branches', 'list_commits', 'list_issues', 'list_pull_requests', 'list_releases', 'list_tags', 'pull_request_read', 'search_code', 'search_issues', 'search_pull_requests', 'search_repositories', 'search_users']
15:01:34 - LiteLLM:INFO: mcp_server_manager.py:2218 - Successfully fetched 20 tools from server github
2026-05-25 15:01:34 - LiteLLM - INFO - mcp_server_manager.py:2218 - _create_prefixed_tools() - Successfully fetched 20 tools from server github
15:01:34 - LiteLLM:INFO: mcp_server_manager.py:1425 - _get_tools_from_server for searxng...
2026-05-25 15:01:34 - LiteLLM - INFO - mcp_server_manager.py:1425 - _get_tools_from_server() - _get_tools_from_server for searxng...
2026-05-25 15:01:34 - mcp.client.streamable_http - INFO - streamable_http.py:181 - _maybe_extract_session_id_from_response() - Received session ID: aafbc65a262f47e9b4923a7784f60235
2026-05-25 15:01:34 - mcp.client.streamable_http - INFO - streamable_http.py:193 - _maybe_extract_protocol_version_from_message() - Negotiated protocol version: 2025-11-25
2026-05-25 15:01:34 - mcp.client.streamable_http - INFO - streamable_http.py:298 - handle_get_stream() - GET stream disconnected, reconnecting in 1000ms...
15:01:34 - LiteLLM:INFO: client.py:437 - MCP client listed 3 tools from http://searx-crawl-mcp:9555/mcp: ['crawl', 'crawl_site', 'search']
2026-05-25 15:01:34 - LiteLLM - INFO - client.py:437 - list_tools() - MCP client listed 3 tools from http://searx-crawl-mcp:9555/mcp: ['crawl', 'crawl_site', 'search']
15:01:34 - LiteLLM:INFO: mcp_server_manager.py:2218 - Successfully fetched 3 tools from server searxng
2026-05-25 15:01:34 - LiteLLM - INFO - mcp_server_manager.py:2218 - _create_prefixed_tools() - Successfully fetched 3 tools from server searxng
15:01:34 - LiteLLM:INFO: mcp_server_manager.py:1425 - _get_tools_from_server for GPT_Reseacher...
2026-05-25 15:01:34 - LiteLLM - INFO - mcp_server_manager.py:1425 - _get_tools_from_server() - _get_tools_from_server for GPT_Reseacher...
2026-05-25 15:01:34 - mcp.client.streamable_http - INFO - streamable_http.py:181 - _maybe_extract_session_id_from_response() - Received session ID: 6730f2ddcc664dafbbe3f622c1c5ea54
2026-05-25 15:01:34 - mcp.client.streamable_http - INFO - streamable_http.py:193 - _maybe_extract_protocol_version_from_message() - Negotiated protocol version: 2025-11-25
2026-05-25 15:01:34 - mcp.client.streamable_http - INFO - streamable_http.py:298 - handle_get_stream() - GET stream disconnected, reconnecting in 1000ms...
15:01:34 - LiteLLM:INFO: client.py:437 - MCP client listed 5 tools from http://gptr-mcp:8000/mcp: ['deep_research', 'quick_search', 'write_report', 'get_research_sources', 'get_research_context']
2026-05-25 15:01:34 - LiteLLM - INFO - client.py:437 - list_tools() - MCP client listed 5 tools from http://gptr-mcp:8000/mcp: ['deep_research', 'quick_search', 'write_report', 'get_research_sources', 'get_research_context']
15:01:34 - LiteLLM:INFO: mcp_server_manager.py:2218 - Successfully fetched 5 tools from server GPT_Reseacher
2026-05-25 15:01:34 - LiteLLM - INFO - mcp_server_manager.py:2218 - _create_prefixed_tools() - Successfully fetched 5 tools from server GPT_Reseacher
15:01:34 - LiteLLM:INFO: mcp_server_manager.py:1425 - _get_tools_from_server for tavily...
2026-05-25 15:01:34 - LiteLLM - INFO - mcp_server_manager.py:1425 - _get_tools_from_server() - _get_tools_from_server for tavily...
Tavily MCP server running on stdio
15:01:35 - LiteLLM:INFO: client.py:437 - MCP client listed 5 tools from stdio: ['tavily_search', 'tavily_extract', 'tavily_crawl', 'tavily_map', 'tavily_research']
2026-05-25 15:01:35 - LiteLLM - INFO - client.py:437 - list_tools() - MCP client listed 5 tools from stdio: ['tavily_search', 'tavily_extract', 'tavily_crawl', 'tavily_map', 'tavily_research']
15:01:35 - LiteLLM:INFO: mcp_server_manager.py:2218 - Successfully fetched 5 tools from server tavily
2026-05-25 15:01:35 - LiteLLM - INFO - mcp_server_manager.py:2218 - _create_prefixed_tools() - Successfully fetched 5 tools from server tavily
15:01:35 - LiteLLM:INFO: semantic_tool_filter.py:80 - Fetched 33 tools from 4 MCP servers
2026-05-25 15:01:35 - LiteLLM - INFO - semantic_tool_filter.py:80 - build_router_from_mcp_registry() - Fetched 33 tools from 4 MCP servers
2026-05-25 15:01:35 WARNING semantic_router No index provided. Using default LocalIndex.
15:01:35 - LiteLLM:INFO: utils.py:1656 - Wrapper: Completed Call, calling success_handler
2026-05-25 15:01:35 - LiteLLM - INFO - utils.py:1656 - wrapper() - Wrapper: Completed Call, calling success_handler
15:01:35 - LiteLLM Router:INFO: router.py:4399 - litellm.embedding(model=ibm-granite/granite-embedding-english-r2) 200 OK
2026-05-25 15:01:35 - LiteLLM Router - INFO - router.py:4399 - _embedding() - litellm.embedding(model=ibm-granite/granite-embedding-english-r2) 200 OK
15:01:36 - LiteLLM:INFO: utils.py:1656 - Wrapper: Completed Call, calling success_handler
2026-05-25 15:01:36 - LiteLLM - INFO - utils.py:1656 - wrapper() - Wrapper: Completed Call, calling success_handler
15:01:36 - LiteLLM Router:INFO: router.py:4399 - litellm.embedding(model=ibm-granite/granite-embedding-english-r2) 200 OK
2026-05-25 15:01:36 - LiteLLM Router - INFO - router.py:4399 - _embedding() - litellm.embedding(model=ibm-granite/granite-embedding-english-r2) 200 OK
2026-05-25 15:01:36 WARNING semantic_router No config is written for LocalIndex.
15:01:36 - LiteLLM:INFO: semantic_tool_filter.py:147 - Built semantic router with 33 tools
2026-05-25 15:01:36 - LiteLLM - INFO - semantic_tool_filter.py:147 - _build_router() - Built semantic router with 33 tools
15:01:36 - LiteLLM Proxy:INFO: hook.py:358 -  MCP Semantic Tool Filter enabled: embedding_model=ibm-granite/granite-embedding-english-r2, top_k=5, similarity_threshold=0.2
2026-05-25 15:01:36 - LiteLLM Proxy - INFO - hook.py:358 - initialize_from_config() -  MCP Semantic Tool Filter enabled: embedding_model=ibm-granite/granite-embedding-english-r2, top_k=5, similarity_threshold=0.2
15:01:36 - LiteLLM Proxy:INFO: proxy_server.py:5814 - MCP Semantic Filter reinitialized from DB
2026-05-25 15:01:36 - LiteLLM Proxy - INFO - proxy_server.py:5814 - _init_semantic_filter_settings_in_db() - MCP Semantic Filter reinitialized from DB
INFO:     192.168.12.198:58132 - "PATCH /update/mcp_semantic_filter_settings HTTP/1.1" 200 OK
INFO:     192.168.12.198:58132 - "GET /get/mcp_semantic_filter_settings HTTP/1.1" 200 OK
15:01:36 - LiteLLM Proxy:INFO: guardrail_registry.py:749 - Guardrail 'protected-class-information' (ID: de75f2f4-fb9e-4b27-96c7-d2822364b9bc) params changed, re-initializing...
2026-05-25 15:01:36 - LiteLLM Proxy - INFO - guardrail_registry.py:749 - sync_guardrail_from_db() - Guardrail 'protected-class-information' (ID: de75f2f4-fb9e-4b27-96c7-d2822364b9bc) params changed, re-initializing...
15:01:36 - LiteLLM Proxy:INFO: guardrail_registry.py:749 - Guardrail 'network-infrastructure-pii' (ID: 99831f41-def9-4861-a2e9-5fe1e49d1b15) params changed, re-initializing...
2026-05-25 15:01:36 - LiteLLM Proxy - INFO - guardrail_registry.py:749 - sync_guardrail_from_db() - Guardrail 'network-infrastructure-pii' (ID: 99831f41-def9-4861-a2e9-5fe1e49d1b15) params changed, re-initializing...
15:01:36 - LiteLLM Proxy:INFO: guardrail_registry.py:749 - Guardrail 'credentials-api-keys' (ID: dbb2f7d4-d763-4b87-9bd6-9467faca440a) params changed, re-initializing...
2026-05-25 15:01:36 - LiteLLM Proxy - INFO - guardrail_registry.py:749 - sync_guardrail_from_db() - Guardrail 'credentials-api-keys' (ID: dbb2f7d4-d763-4b87-9bd6-9467faca440a) params changed, re-initializing...
15:01:36 - LiteLLM Proxy:INFO: guardrail_registry.py:749 - Guardrail 'financial-pii' (ID: f5fe12a7-3bee-4838-a6c6-72fb3f1acff2) params changed, re-initializing...
2026-05-25 15:01:36 - LiteLLM Proxy - INFO - guardrail_registry.py:749 - sync_guardrail_from_db() - Guardrail 'financial-pii' (ID: f5fe12a7-3bee-4838-a6c6-72fb3f1acff2) params changed, re-initializing...
15:01:36 - LiteLLM Proxy:INFO: guardrail_registry.py:749 - Guardrail 'contact-information-pii' (ID: 59ebdd59-b345-41e9-8dd6-19d3a8ac66c0) params changed, re-initializing...
2026-05-25 15:01:36 - LiteLLM Proxy - INFO - guardrail_registry.py:749 - sync_guardrail_from_db() - Guardrail 'contact-information-pii' (ID: 59ebdd59-b345-41e9-8dd6-19d3a8ac66c0) params changed, re-initializing...
15:01:36 - LiteLLM Proxy:INFO: guardrail_registry.py:749 - Guardrail 'international-pii-identifiers' (ID: de1a481c-b828-456b-afff-21fcfab3e831) params changed, re-initializing...
2026-05-25 15:01:36 - LiteLLM Proxy - INFO - guardrail_registry.py:749 - sync_guardrail_from_db() - Guardrail 'international-pii-identifiers' (ID: de1a481c-b828-456b-afff-21fcfab3e831) params changed, re-initializing...
15:01:36 - LiteLLM Proxy:INFO: guardrail_registry.py:749 - Guardrail 'au-pii-passports' (ID: da882914-e6e8-4319-8a01-7d47f620f9f8) params changed, re-initializing...
2026-05-25 15:01:36 - LiteLLM Proxy - INFO - guardrail_registry.py:749 - sync_guardrail_from_db() - Guardrail 'au-pii-passports' (ID: da882914-e6e8-4319-8a01-7d47f620f9f8) params changed, re-initializing...
15:01:36 - LiteLLM Proxy:INFO: guardrail_registry.py:749 - Guardrail 'au-pii-tax-identifiers' (ID: 5cd0bb10-a0ef-42bc-98a3-a3e92e553319) params changed, re-initializing...
2026-05-25 15:01:36 - LiteLLM Proxy - INFO - guardrail_registry.py:749 - sync_guardrail_from_db() - Guardrail 'au-pii-tax-identifiers' (ID: 5cd0bb10-a0ef-42bc-98a3-a3e92e553319) params changed, re-initializing...
15:01:36 - LiteLLM Proxy:INFO: policy_registry.py:578 - Synced 1 production policies and 0 draft/published (by ID) from DB to in-memory registry
2026-05-25 15:01:36 - LiteLLM Proxy - INFO - policy_registry.py:578 - sync_policies_from_db() - Synced 1 production policies and 0 draft/published (by ID) from DB to in-memory registry
15:01:36 - LiteLLM Proxy:INFO: attachment_registry.py:482 - Synced 0 attachments from DB to in-memory registry
2026-05-25 15:01:36 - LiteLLM Proxy - INFO - attachment_registry.py:482 - sync_attachments_from_db() - Synced 0 attachments from DB to in-memory registry
15:01:36 - LiteLLM:INFO: mcp_server_manager.py:3060 - Found 4 MCP servers in database
2026-05-25 15:01:36 - LiteLLM - INFO - mcp_server_manager.py:3060 - reload_servers_from_database() - Found 4 MCP servers in database
15:01:37 - LiteLLM Proxy:INFO: proxy_server.py:6372 - Loading 0 search tool(s) from database into router
2026-05-25 15:01:37 - LiteLLM Proxy - INFO - proxy_server.py:6372 - _init_search_tools_in_db() - Loading 0 search tool(s) from database into router
15:01:37 - LiteLLM Proxy:INFO: tool_registry_writer.py:329 - ToolPolicyRegistry: synced 41 tool policies and 0 object permissions from DB
2026-05-25 15:01:37 - LiteLLM Proxy - INFO - tool_registry_writer.py:329 - sync_tool_policy_from_db() - ToolPolicyRegistry: synced 41 tool policies and 0 object permissions from DB
INFO:     192.168.12.198:59883 - "GET /v2/guardrails/list HTTP/1.1" 200 OK
INFO:     192.168.12.198:58132 - "GET /tag/list HTTP/1.1" 200 OK
INFO:     192.168.12.198:52778 - "GET /model_group/info HTTP/1.1" 200 OK
INFO:     192.168.12.198:57977 - "GET /policies/list HTTP/1.1" 200 OK
INFO:     192.168.12.198:57244 - "GET /vector_store/list HTTP/1.1" 200 OK
INFO:     192.168.12.198:59883 - "GET /v1/mcp/server HTTP/1.1" 200 OK
INFO:     192.168.12.198:58132 - "GET /v1/mcp/toolset HTTP/1.1" 200 OK
INFO:     192.168.12.198:57977 - "GET /sso/get/ui_settings HTTP/1.1" 200 OK
INFO:     192.168.12.198:57244 - "GET /v2/guardrails/list HTTP/1.1" 200 OK
INFO:     192.168.12.198:52778 - "GET /v2/model/info?include_team_models=true&page=1&size=200 HTTP/1.1" 200 OK
INFO:     192.168.12.198:59883 - "GET /model_group/info HTTP/1.1" 200 OK
INFO:     192.168.12.198:57977 - "GET /v1/mcp/server HTTP/1.1" 200 OK
INFO:     192.168.12.198:58132 - "GET /policies/list HTTP/1.1" 200 OK
INFO:     192.168.12.198:52778 - "GET /model_group/info HTTP/1.1" 200 OK
15:01:52 - LiteLLM:INFO: mcp_server_manager.py:1425 - _get_tools_from_server for github...
2026-05-25 15:01:52 - LiteLLM - INFO - mcp_server_manager.py:1425 - _get_tools_from_server() - _get_tools_from_server for github...
15:01:52 - LiteLLM:INFO: mcp_server_manager.py:1425 - _get_tools_from_server for searxng...
2026-05-25 15:01:52 - LiteLLM - INFO - mcp_server_manager.py:1425 - _get_tools_from_server() - _get_tools_from_server for searxng...
15:01:52 - LiteLLM:INFO: mcp_server_manager.py:1425 - _get_tools_from_server for GPT_Reseacher...
2026-05-25 15:01:52 - LiteLLM - INFO - mcp_server_manager.py:1425 - _get_tools_from_server() - _get_tools_from_server for GPT_Reseacher...
15:01:52 - LiteLLM:INFO: mcp_server_manager.py:1425 - _get_tools_from_server for tavily...
2026-05-25 15:01:52 - LiteLLM - INFO - mcp_server_manager.py:1425 - _get_tools_from_server() - _get_tools_from_server for tavily...
2026-05-25 15:01:52 - mcp.client.streamable_http - INFO - streamable_http.py:181 - _maybe_extract_session_id_from_response() - Received session ID: 09380f66124f461eafde466da143040d
2026-05-25 15:01:52 - mcp.client.streamable_http - INFO - streamable_http.py:193 - _maybe_extract_protocol_version_from_message() - Negotiated protocol version: 2025-11-25
2026-05-25 15:01:52 - mcp.client.streamable_http - INFO - streamable_http.py:181 - _maybe_extract_session_id_from_response() - Received session ID: bde2ec88375a474bb6d79d6e57b2f9e8
2026-05-25 15:01:52 - mcp.client.streamable_http - INFO - streamable_http.py:193 - _maybe_extract_protocol_version_from_message() - Negotiated protocol version: 2025-11-25
2026-05-25 15:01:52 - mcp.client.streamable_http - INFO - streamable_http.py:298 - handle_get_stream() - GET stream disconnected, reconnecting in 1000ms...
2026-05-25 15:01:52 - mcp.client.streamable_http - INFO - streamable_http.py:298 - handle_get_stream() - GET stream disconnected, reconnecting in 1000ms...
15:01:52 - LiteLLM:INFO: client.py:437 - MCP client listed 5 tools from http://gptr-mcp:8000/mcp: ['deep_research', 'quick_search', 'write_report', 'get_research_sources', 'get_research_context']
2026-05-25 15:01:52 - LiteLLM - INFO - client.py:437 - list_tools() - MCP client listed 5 tools from http://gptr-mcp:8000/mcp: ['deep_research', 'quick_search', 'write_report', 'get_research_sources', 'get_research_context']
15:01:52 - LiteLLM:INFO: mcp_server_manager.py:2218 - Successfully fetched 5 tools from server GPT_Reseacher
2026-05-25 15:01:52 - LiteLLM - INFO - mcp_server_manager.py:2218 - _create_prefixed_tools() - Successfully fetched 5 tools from server GPT_Reseacher
15:01:52 - LiteLLM:INFO: client.py:437 - MCP client listed 3 tools from http://searx-crawl-mcp:9555/mcp: ['crawl', 'crawl_site', 'search']
2026-05-25 15:01:52 - LiteLLM - INFO - client.py:437 - list_tools() - MCP client listed 3 tools from http://searx-crawl-mcp:9555/mcp: ['crawl', 'crawl_site', 'search']
15:01:52 - LiteLLM:INFO: mcp_server_manager.py:2218 - Successfully fetched 3 tools from server searxng
2026-05-25 15:01:52 - LiteLLM - INFO - mcp_server_manager.py:2218 - _create_prefixed_tools() - Successfully fetched 3 tools from server searxng
15:01:52 - LiteLLM:WARNING: user_api_key_auth_mcp.py:826 - Failed to get allowed tools for server: 404: {'error': "Team doesn't exist in db. Team=litellm-dashboard. Create team via `/team/new` call."}
2026-05-25 15:01:52 - LiteLLM - WARNING - user_api_key_auth_mcp.py:826 - get_allowed_tools_for_server() - Failed to get allowed tools for server: 404: {'error': "Team doesn't exist in db. Team=litellm-dashboard. Create team via `/team/new` call."}
15:01:52 - LiteLLM:WARNING: user_api_key_auth_mcp.py:826 - Failed to get allowed tools for server: 404: {'error': "Team doesn't exist in db. Team=litellm-dashboard. Create team via `/team/new` call."}
2026-05-25 15:01:52 - LiteLLM - WARNING - user_api_key_auth_mcp.py:826 - get_allowed_tools_for_server() - Failed to get allowed tools for server: 404: {'error': "Team doesn't exist in db. Team=litellm-dashboard. Create team via `/team/new` call."}
2026-05-25 15:01:52 - mcp.client.streamable_http - INFO - streamable_http.py:181 - _maybe_extract_session_id_from_response() - Received session ID: GBPA2EVUPP27VDP3WKHQXSH2GW
2026-05-25 15:01:52 - mcp.client.streamable_http - INFO - streamable_http.py:193 - _maybe_extract_protocol_version_from_message() - Negotiated protocol version: 2025-11-25
2026-05-25 15:01:53 - mcp.client.streamable_http - INFO - streamable_http.py:298 - handle_get_stream() - GET stream disconnected, reconnecting in 1000ms...
Tavily MCP server running on stdio
15:01:53 - LiteLLM:INFO: client.py:437 - MCP client listed 5 tools from stdio: ['tavily_search', 'tavily_extract', 'tavily_crawl', 'tavily_map', 'tavily_research']
2026-05-25 15:01:53 - LiteLLM - INFO - client.py:437 - list_tools() - MCP client listed 5 tools from stdio: ['tavily_search', 'tavily_extract', 'tavily_crawl', 'tavily_map', 'tavily_research']
15:01:53 - LiteLLM:INFO: mcp_server_manager.py:2218 - Successfully fetched 5 tools from server tavily
2026-05-25 15:01:53 - LiteLLM - INFO - mcp_server_manager.py:2218 - _create_prefixed_tools() - Successfully fetched 5 tools from server tavily
15:01:53 - LiteLLM:WARNING: user_api_key_auth_mcp.py:826 - Failed to get allowed tools for server: 404: {'error': "Team doesn't exist in db. Team=litellm-dashboard. Create team via `/team/new` call."}
2026-05-25 15:01:53 - LiteLLM - WARNING - user_api_key_auth_mcp.py:826 - get_allowed_tools_for_server() - Failed to get allowed tools for server: 404: {'error': "Team doesn't exist in db. Team=litellm-dashboard. Create team via `/team/new` call."}
15:01:53 - LiteLLM:INFO: client.py:437 - MCP client listed 20 tools from http://github-mcp-server:8082/mcp/: ['get_commit', 'get_file_contents', 'get_label', 'get_latest_release', 'get_me', 'get_release_by_tag', 'get_tag', 'issue_read', 'list_branches', 'list_commits', 'list_issues', 'list_pull_requests', 'list_releases', 'list_tags', 'pull_request_read', 'search_code', 'search_issues', 'search_pull_requests', 'search_repositories', 'search_users']
2026-05-25 15:01:53 - LiteLLM - INFO - client.py:437 - list_tools() - MCP client listed 20 tools from http://github-mcp-server:8082/mcp/: ['get_commit', 'get_file_contents', 'get_label', 'get_latest_release', 'get_me', 'get_release_by_tag', 'get_tag', 'issue_read', 'list_branches', 'list_commits', 'list_issues', 'list_pull_requests', 'list_releases', 'list_tags', 'pull_request_read', 'search_code', 'search_issues', 'search_pull_requests', 'search_repositories', 'search_users']
15:01:53 - LiteLLM:INFO: mcp_server_manager.py:2218 - Successfully fetched 20 tools from server github
2026-05-25 15:01:53 - LiteLLM - INFO - mcp_server_manager.py:2218 - _create_prefixed_tools() - Successfully fetched 20 tools from server github
15:01:53 - LiteLLM:WARNING: user_api_key_auth_mcp.py:826 - Failed to get allowed tools for server: 404: {'error': "Team doesn't exist in db. Team=litellm-dashboard. Create team via `/team/new` call."}
2026-05-25 15:01:53 - LiteLLM - WARNING - user_api_key_auth_mcp.py:826 - get_allowed_tools_for_server() - Failed to get allowed tools for server: 404: {'error': "Team doesn't exist in db. Team=litellm-dashboard. Create team via `/team/new` call."}
15:01:53 - LiteLLM:INFO: server.py:1442 - Successfully fetched 33 tools total from all MCP servers
2026-05-25 15:01:53 - LiteLLM - INFO - server.py:1442 - _get_tools_from_mcp_servers() - Successfully fetched 33 tools total from all MCP servers
15:01:53 - LiteLLM Proxy:INFO: hook.py:183 - Expanded 1 MCP reference(s) to 33 tools
2026-05-25 15:01:53 - LiteLLM Proxy - INFO - hook.py:183 - async_pre_call_hook() - Expanded 1 MCP reference(s) to 33 tools
15:01:53 - LiteLLM:INFO: utils.py:1656 - Wrapper: Completed Call, calling success_handler
2026-05-25 15:01:53 - LiteLLM - INFO - utils.py:1656 - wrapper() - Wrapper: Completed Call, calling success_handler
15:01:53 - LiteLLM Router:INFO: router.py:4399 - litellm.embedding(model=ibm-granite/granite-embedding-english-r2) 200 OK
2026-05-25 15:01:53 - LiteLLM Router - INFO - router.py:4399 - _embedding() - litellm.embedding(model=ibm-granite/granite-embedding-english-r2) 200 OK
15:01:53 - LiteLLM Proxy:INFO: hook.py:247 - Semantic tool filter: 33->5 tools
2026-05-25 15:01:53 - LiteLLM Proxy - INFO - hook.py:247 - async_pre_call_hook() - Semantic tool filter: 33->5 tools
15:01:53 - LiteLLM Proxy:INFO: route_llm_request.py:176 - SESSION REUSE: Attached shared aiohttp session to request (ID: 125568310588960)
2026-05-25 15:01:53 - LiteLLM Proxy - INFO - route_llm_request.py:176 - add_shared_session_to_data() - SESSION REUSE: Attached shared aiohttp session to request (ID: 125568310588960)
15:01:53 - LiteLLM:INFO: utils.py:4054 - 
LiteLLM completion() model= byteshape/Qwen3.6-35B-A3B-MTP-GGUF:19BPW; provider = custom_openai
2026-05-25 15:01:53 - LiteLLM - INFO - utils.py:4054 - _check_valid_arg() - 
LiteLLM completion() model= byteshape/Qwen3.6-35B-A3B-MTP-GGUF:19BPW; provider = custom_openai
15:01:53 - LiteLLM Router:INFO: router.py:2535 - litellm.acompletion(model=byteshape/Qwen3.6-35B-A3B-MTP-GGUF:19BPW) Exception litellm.InternalServerError: InternalServerError: Custom_openaiException - Failed to parse tools: Missing tool function: {"name":"searxng-search","parameters":{"additionalProperties":false,"properties":{"query":{"type":"string","description":"Search query string (required)"},"language":{"default":"en","type":"string","description":"Language code for results (e.g., 'en', 'de', 'fr'). Default: 'en'"},"time_range":{"anyOf":[{"type":"string"},{"type":"null"}],"default":null,"description":"Time range filter - 'day', 'week', 'month', or 'year'. Default: None (no filter)"},"categories":{"anyOf":[{"items":{"type":"string"},"type":"array"},{"type":"null"}],"default":null,"description":"Categories to search (e.g., ['general', 'images', 'news']). Default: None (all)"},"engines":{"anyOf":[{"items":{"type":"string"},"type":"array"},{"type":"null"}],"default":null,"description":"Specific search engines to use. Default: None (all available)"},"safesearch":{"default":1,"type":"integer","description":"Safe search level - 0 (off), 1 (moderate), 2 (strict). Default: 1"},"pageno":{"default":1,"type":"integer","description":"Page number for results (minimum 1). Default: 1"},"max_results":{"default":10,"type":"integer","description":"Maximum results to return (1-50). Default: 10"},"max_retries":{"default":3,"type":"integer","description":"Maximum attempts for transient RequestError failures (default: 3)"}},"required":["query"],"type":"object"},"strict":false,"type":"function","description":"Search the web using SearXNG metasearch engine."}; tools = [
  {
    "name": "searxng-search",
    "parameters": {
      "additionalProperties": false,
      "properties": {
        "query": {
          "type": "string",
          "description": "Search query string (required)"
        },
        "language": {
          "default": "en",
          "type": "string",
          "description": "Language code for results (e.g., 'en', 'de', 'fr'). Default: 'en'"
        },
        "time_range": {
          "anyOf": [
            {
              "type": "string"
            },
            {
              "type": "null"
            }
          ],
          "default": null,
          "description": "Time range filter - 'day', 'week', 'month', or 'year'. Default: None (no filter)"
        },
        "categories": {
          "anyOf": [
            {
              "items": {
                "type": "string"
              },
              "type": "array"
            },
            {
              "type": "null"
            }
          ],
          "default": null,
          "description": "Categories to search (e.g., ['general', 'images', 'news']). Default: None (all)"
        },
        "engines": {
          "anyOf": [
            {
              "items": {
                "type": "string"
              },
              "type": "array"
            },
            {
              "type": "null"
            }
          ],
          "default": null,
          "description": "Specific search engines to use. Default: None (all available)"
        },
        "safesearch": {
          "default": 1,
          "type": "integer",
          "description": "Safe search level - 0 (off), 1 (moderate), 2 (strict). Default: 1"
        },
        "pageno": {
          "default": 1,
          "type": "integer",
          "description": "Page number for results (minimum 1). Default: 1"
        },
        "max_results": {
          "default": 10,
          "type": "integer",
          "description": "Maximum results to return (1-50). Default: 10"
        },
        "max_retries": {
          "default": 3,
          "type": "integer",
          "description": "Maximum attempts for transient RequestError failures (default: 3)"
        }
      },
      "required": [
        "query"
      ],
      "type": "object"
    },
    "strict": false,
    "type": "function",
    "description": "Search the web using SearXNG metasearch engine."
  },
  {
    "name": "tavily-tavily_search",
    "parameters": {
      "type": "object",
      "properties": {
        "query": {
          "type": "string",
          "description": "Search query"
        },
        "search_depth": {
          "type": "string",
          "enum": [
            "basic",
            "advanced",
            "fast",
            "ultra-fast"
          ],
          "description": "The depth of the search. 'basic' for generic results, 'advanced' for more thorough search, 'fast' for optimized low latency with high relevance, 'ultra-fast' for prioritizing latency above all else",
          "default": "basic"
        },
        "topic": {
          "type": "string",
          "enum": [
            "general"
          ],
          "description": "The category of the search. This will determine which of our agents will be used for the search",
          "default": "general"
        },
        "time_range": {
          "type": "string",
          "description": "The time range back from the current date to include in the search results",
          "enum": [
            "day",
            "week",
            "month",
            "year"
          ]
        },
        "start_date": {
          "type": "string",
          "description": "Will return all results after the specified start date. Required to be written in the format YYYY-MM-DD.",
          "default": ""
        },
        "end_date": {
          "type": "string",
          "description": "Will return all results before the specified end date. Required to be written in the format YYYY-MM-DD",
          "default": ""
        },
        "max_results": {
          "type": "number",
          "description": "The maximum number of search results to return",
          "default": 5,
          "minimum": 5,
          "maximum": 20
        },
        "include_images": {
          "type": "boolean",
          "description": "Include a list of query-related images in the response",
          "default": false
        },
        "include_image_descriptions": {
          "type": "boolean",
          "description": "Include a list of query-related images and their descriptions in the response",
          "default": false
        },
        "include_raw_content": {
          "type": "boolean",
          "description": "Include the cleaned and parsed HTML content of each search result",
          "default": false
        },
        "include_domains": {
          "type": "array",
          "items": {
            "type": "string"
          },
          "description": "A list of domains to specifically include in the search results, if the user asks to search on specific sites set this to the domain of the site",
          "default": []
        },
        "exclude_domains": {
          "type": "array",
          "items": {
            "type": "string"
          },
          "description": "List of domains to specifically exclude, if the user asks to exclude a domain set this to the domain of the site",
          "default": []
        },
        "country": {
          "type": "string",
          "description": "Boost search results from a specific country. Must be a full country name (e.g., 'United States', 'Japan', 'Germany'). ISO country codes (e.g., 'us', 'jp') are not supported. Available only if topic is general. See https://docs.tavily.com/documentation/api-reference/search for the full list of supported countries.",
          "default": ""
        },
        "include_favicon": {
          "type": "boolean",
          "description": "Whether to include the favicon URL for each result",
          "default": false
        },
        "exact_match": {
          "type": "boolean",
          "description": "Only return results containing the exact phrase(s) in quotes in your query"
        }
      },
      "required": [
        "query"
      ],
      "additionalProperties": false
    },
    "strict": false,
    "type": "function",
    "description": "Search the web for current information on any topic. Use for news, facts, or data beyond your knowledge cutoff. Returns snippets and source URLs."
  },
  {
    "name": "GPT_Reseacher-quick_search",
    "parameters": {
      "additionalProperties": false,
      "properties": {
        "query": {
          "type": "string",
          "description": "The search query"
        }
      },
      "required": [
        "query"
      ],
      "type": "object"
    },
    "strict": false,
    "type": "function",
    "description": "Perform a quick web search on a given query and return search results with snippets.\nThis optimizes for speed over quality and is useful when an LLM doesn't need in-depth\ninformation on a topic."
  },
  {
    "name": "tavily-tavily_crawl",
    "parameters": {
      "type": "object",
      "properties": {
        "url": {
          "type": "string",
          "description": "The root URL to begin the crawl"
        },
        "max_depth": {
          "type": "integer",
          "description": "Max depth of the crawl. Defines how far from the base URL the crawler can explore.",
          "default": 1,
          "minimum": 1
        },
        "max_breadth": {
          "type": "integer",
          "description": "Max number of links to follow per level of the tree (i.e., per page)",
          "default": 20,
          "minimum": 1
        },
        "limit": {
          "type": "integer",
          "description": "Total number of links the crawler will process before stopping",
          "default": 50,
          "minimum": 1
        },
        "instructions": {
          "type": "string",
          "description": "Natural language instructions for the crawler. Instructions specify which types of pages the crawler should return."
        },
        "select_paths": {
          "type": "array",
          "items": {
            "type": "string"
          },
          "description": "Regex patterns to select only URLs with specific path patterns (e.g., /docs/.*, /api/v1.*)",
          "default": []
        },
        "select_domains": {
          "type": "array",
          "items": {
            "type": "string"
          },
          "description": "Regex patterns to restrict crawling to specific domains or subdomains (e.g., ^docs\\.example\\.com$)",
          "default": []
        },
        "allow_external": {
          "type": "boolean",
          "description": "Whether to return external links in the final response",
          "default": true
        },
        "extract_depth": {
          "type": "string",
          "enum": [
            "basic",
            "advanced"
          ],
          "description": "Advanced extraction retrieves more data, including tables and embedded content, with higher success but may increase latency",
          "default": "basic"
        },
        "format": {
          "type": "string",
          "enum": [
            "markdown",
            "text"
          ],
          "description": "The format of the extracted web page content. markdown returns content in markdown format. text returns plain text and may increase latency.",
          "default": "markdown"
        },
        "include_favicon": {
          "type": "boolean",
          "description": "Whether to include the favicon URL for each result",
          "default": false
        }
      },
      "required": [
        "url"
      ],
      "additionalProperties": false
    },
    "strict": false,
    "type": "function",
    "description": "Crawl a website starting from a URL. Extracts content from pages with configurable depth and breadth."
  },