Issue Station
Sign In
Tools hereToolbox

langchain - 💡(How to fix) Fix langchain docs mcp 500 error [2 comments, 2 participants]

Official PRs (…)
ON THIS PAGE

Recommended Tools

×6

Utilities matched from this issue’s tags and category — try them while you read without losing context.

GitHub issue graph ai analysis

Paste a GitHub issue URL. We fetch that issue, discover linked issues from bodies/comments/timeline, collect linked pull requests, and produce a structured English report.

The report is written in English Markdown for sharing and archival.

Helpful · Quick feedback

Loading…
GitHub stats
langchain-ai/langchain#35451•Fetched 2026-04-08 00:26:05
View on GitHub
Comments
2
Participants
2
Timeline
9
Reactions
0
Author
korant96korant96
Participants
keenborder786keenborder786korant96korant96
Timeline (top)
labeled ×3commented ×2closed ×1issue_type_added ×1
  • codex：
⚠ MCP client for `langchain-docs` failed to start: MCP startup failed: handshaking with MCP server failed: Send message error Transport

/mcp

🔌  MCP Tools

  • langchain-docs
    • Status: enabled
    • Auth: Unsupported
    • URL: https://docs.langchain.com/mcp
    • Tools: (none)
    • Resources: (none)
    • Resource templates: (none)
  • claude code：
<img width="765" height="285" alt="Image" src="https://github.com/user-attachments/assets/c05f6ef7-126a-4413-b52d-f71b29e85970" />
  • curl test:
curl -I -L --max-time 10 https://docs.langchain.com/mcp
HTTP/2 500 
cache-control: no-store, no-cache, must-revalidate, proxy-revalidate, max-age=0
cf-cache-status: EXPIRED
cf-ray: 9d3bf37f08a4f8c6-SIN
content-security-policy: worker-src * blob: data: 'unsafe-eval' 'unsafe-inline'; object-src data: ; base-uri 'self'; upgrade-insecure-requests; frame-ancestors 'self' https://dashboard.mintlify.com; form-action 'self' https://codesandbox.io;
date: Thu, 26 Feb 2026 02:18:19 GMT
expires: 0
pragma: no-cache
server: Vercel
strict-transport-security: max-age=63072000
vary: rsc, next-router-state-tree, next-router-prefetch, next-router-segment-prefetch, Accept-Encoding
x-cache-key: langchain-5e9cc07a/547/dpl_7Eu9c4KYPBmvyRPAVrgAbKS4oeja/mcp#html=html
x-frame-options: DENY
x-matched-path: /_mintlify/mcp/[subdomain]/[transport]
x-mint-proxy-version: 1.0.0-prod
x-vercel-cache: MISS
x-vercel-id: sin1:sin1:iad1::iad1::gnxt2-1772072299343-defaddc82bd4
content-length: 0

Error Message

Error Message and Stack Trace (if applicable)

⚠ MCP client for langchain-docs failed to start: MCP startup failed: handshaking with MCP server failed: Send message error Transport

Root Cause

  • codex：
⚠ MCP client for `langchain-docs` failed to start: MCP startup failed: handshaking with MCP server failed: Send message error Transport

/mcp

🔌  MCP Tools

  • langchain-docs
    • Status: enabled
    • Auth: Unsupported
    • URL: https://docs.langchain.com/mcp
    • Tools: (none)
    • Resources: (none)
    • Resource templates: (none)
  • claude code：
<img width="765" height="285" alt="Image" src="https://github.com/user-attachments/assets/c05f6ef7-126a-4413-b52d-f71b29e85970" />
  • curl test:
curl -I -L --max-time 10 https://docs.langchain.com/mcp
HTTP/2 500 
cache-control: no-store, no-cache, must-revalidate, proxy-revalidate, max-age=0
cf-cache-status: EXPIRED
cf-ray: 9d3bf37f08a4f8c6-SIN
content-security-policy: worker-src * blob: data: 'unsafe-eval' 'unsafe-inline'; object-src data: ; base-uri 'self'; upgrade-insecure-requests; frame-ancestors 'self' https://dashboard.mintlify.com; form-action 'self' https://codesandbox.io;
date: Thu, 26 Feb 2026 02:18:19 GMT
expires: 0
pragma: no-cache
server: Vercel
strict-transport-security: max-age=63072000
vary: rsc, next-router-state-tree, next-router-prefetch, next-router-segment-prefetch, Accept-Encoding
x-cache-key: langchain-5e9cc07a/547/dpl_7Eu9c4KYPBmvyRPAVrgAbKS4oeja/mcp#html=html
x-frame-options: DENY
x-matched-path: /_mintlify/mcp/[subdomain]/[transport]
x-mint-proxy-version: 1.0.0-prod
x-vercel-cache: MISS
x-vercel-id: sin1:sin1:iad1::iad1::gnxt2-1772072299343-defaddc82bd4
content-length: 0

Fix Action

Fix / Workaround

  • This is a bug, not a usage question.
  • I added a clear and descriptive title that summarizes this issue.
  • I used the GitHub search to find a similar question and didn't find it.
  • I am sure that this is a bug in LangChain rather than my code.
  • The bug is not resolved by updating to the latest stable version of LangChain (or the specific integration package).
  • This is not related to the langchain-community package.
  • I posted a self-contained, minimal, reproducible example. A maintainer can copy it and run it AS IS.

Other Dependencies

aiohttp: 3.13.2 blockbuster: 1.5.26 click: 8.3.1 cloudpickle: 3.1.2 croniter: 6.0.0 cryptography: 46.0.3 dataclasses-json: 0.6.7 grpcio: 1.78.0 grpcio-health-checking: 1.78.0 grpcio-tools: 1.78.0 httpx: 0.28.1 httpx-sse: 0.4.3 jsonpatch: 1.33 jsonschema-rs: 0.29.1 langgraph: 1.0.5 langgraph-checkpoint: 3.0.1 mcp: 1.25.0 numpy: 2.4.0 openai: 2.14.0 opentelemetry-api: 1.39.1 opentelemetry-exporter-otlp-proto-http: 1.39.1 opentelemetry-sdk: 1.39.1 orjson: 3.11.5 packaging: 25.0 protobuf: 6.33.5 pydantic: 2.12.5 pydantic-settings: 2.12.0 pyjwt: 2.10.1 python-dotenv: 1.2.1 PyYAML: 6.0.3 pyyaml: 6.0.3 requests: 2.32.5 requests-toolbelt: 1.0.0 rich: 14.2.0 SQLAlchemy: 2.0.45 sqlalchemy: 2.0.45 sse-starlette: 2.1.3 starlette: 0.50.0 structlog: 25.5.0 tenacity: 9.1.2 tiktoken: 0.12.0 truststore: 0.10.4 typing-extensions: 4.15.0 uuid-utils: 0.12.0 uvicorn: 0.40.0 watchfiles: 1.1.1 xxhash: 3.6.0 zstandard: 0.25.0

Code Example

curl -I -L --max-time 10 https://docs.langchain.com/mcp

---



---

⚠ MCP client for `langchain-docs` failed to start: MCP startup failed: handshaking with MCP server failed: Send message error Transport

/mcp

🔌  MCP Tools

  • langchain-docs
    • Status: enabled
    • Auth: Unsupported
    • URL: https://docs.langchain.com/mcp
    • Tools: (none)
    • Resources: (none)
    • Resource templates: (none)

---

curl -I -L --max-time 10 https://docs.langchain.com/mcp
HTTP/2 500 
cache-control: no-store, no-cache, must-revalidate, proxy-revalidate, max-age=0
cf-cache-status: EXPIRED
cf-ray: 9d3bf37f08a4f8c6-SIN
content-security-policy: worker-src * blob: data: 'unsafe-eval' 'unsafe-inline'; object-src data: ; base-uri 'self'; upgrade-insecure-requests; frame-ancestors 'self' https://dashboard.mintlify.com; form-action 'self' https://codesandbox.io;
date: Thu, 26 Feb 2026 02:18:19 GMT
expires: 0
pragma: no-cache
server: Vercel
strict-transport-security: max-age=63072000
vary: rsc, next-router-state-tree, next-router-prefetch, next-router-segment-prefetch, Accept-Encoding
x-cache-key: langchain-5e9cc07a/547/dpl_7Eu9c4KYPBmvyRPAVrgAbKS4oeja/mcp#html=html
x-frame-options: DENY
x-matched-path: /_mintlify/mcp/[subdomain]/[transport]
x-mint-proxy-version: 1.0.0-prod
x-vercel-cache: MISS
x-vercel-id: sin1:sin1:iad1::iad1::gnxt2-1772072299343-defaddc82bd4
content-length: 0

---

$ python -m langchain_core.sys_info

System Information
------------------
> OS:  Linux
> OS Version:  #1 SMP Fri Sep 26 15:08:55 CST 2025
> Python Version:  3.12.11 (main, Sep  2 2025, 11:18:24) [GCC 8.5.0 20210514 (Tencent 8.5.0-26)]

Package Information
-------------------
> langchain_core: 1.2.5
> langchain: 1.1.3
> langchain_community: 0.4.1
> langsmith: 0.7.1
> langchain_classic: 1.0.1
> langchain_mcp_adapters: 0.2.1
> langchain_openai: 1.1.6
> langchain_text_splitters: 1.1.0
> langgraph_api: 0.7.29
> langgraph_cli: 0.4.12
> langgraph_runtime_inmem: 0.24.1
> langgraph_sdk: 0.3.1

Optional packages not installed
-------------------------------
> langserve

Other Dependencies
------------------
> aiohttp: 3.13.2
> blockbuster: 1.5.26
> click: 8.3.1
> cloudpickle: 3.1.2
> croniter: 6.0.0
> cryptography: 46.0.3
> dataclasses-json: 0.6.7
> grpcio: 1.78.0
> grpcio-health-checking: 1.78.0
> grpcio-tools: 1.78.0
> httpx: 0.28.1
> httpx-sse: 0.4.3
> jsonpatch: 1.33
> jsonschema-rs: 0.29.1
> langgraph: 1.0.5
> langgraph-checkpoint: 3.0.1
> mcp: 1.25.0
> numpy: 2.4.0
> openai: 2.14.0
> opentelemetry-api: 1.39.1
> opentelemetry-exporter-otlp-proto-http: 1.39.1
> opentelemetry-sdk: 1.39.1
> orjson: 3.11.5
> packaging: 25.0
> protobuf: 6.33.5
> pydantic: 2.12.5
> pydantic-settings: 2.12.0
> pyjwt: 2.10.1
> python-dotenv: 1.2.1
> PyYAML: 6.0.3
> pyyaml: 6.0.3
> requests: 2.32.5
> requests-toolbelt: 1.0.0
> rich: 14.2.0
> SQLAlchemy: 2.0.45
> sqlalchemy: 2.0.45
> sse-starlette: 2.1.3
> starlette: 0.50.0
> structlog: 25.5.0
> tenacity: 9.1.2
> tiktoken: 0.12.0
> truststore: 0.10.4
> typing-extensions: 4.15.0
> uuid-utils: 0.12.0
> uvicorn: 0.40.0
> watchfiles: 1.1.1
> xxhash: 3.6.0
> zstandard: 0.25.0
RAW_BUFFERClick to expand / collapse

Checked other resources

  • This is a bug, not a usage question.
  • I added a clear and descriptive title that summarizes this issue.
  • I used the GitHub search to find a similar question and didn't find it.
  • I am sure that this is a bug in LangChain rather than my code.
  • The bug is not resolved by updating to the latest stable version of LangChain (or the specific integration package).
  • This is not related to the langchain-community package.
  • I posted a self-contained, minimal, reproducible example. A maintainer can copy it and run it AS IS.

Package (Required)

  • langchain
  • langchain-openai
  • langchain-anthropic
  • langchain-classic
  • langchain-core
  • langchain-model-profiles
  • langchain-tests
  • langchain-text-splitters
  • langchain-chroma
  • langchain-deepseek
  • langchain-exa
  • langchain-fireworks
  • langchain-groq
  • langchain-huggingface
  • langchain-mistralai
  • langchain-nomic
  • langchain-ollama
  • langchain-openrouter
  • langchain-perplexity
  • langchain-qdrant
  • langchain-xai
  • Other / not sure / general

Related Issues / PRs

#33636

Reproduction Steps / Example Code (Python)

curl -I -L --max-time 10 https://docs.langchain.com/mcp

Error Message and Stack Trace (if applicable)

Description

  • codex：
⚠ MCP client for `langchain-docs` failed to start: MCP startup failed: handshaking with MCP server failed: Send message error Transport

/mcp

🔌  MCP Tools

  • langchain-docs
    • Status: enabled
    • Auth: Unsupported
    • URL: https://docs.langchain.com/mcp
    • Tools: (none)
    • Resources: (none)
    • Resource templates: (none)
  • claude code：
<img width="765" height="285" alt="Image" src="https://github.com/user-attachments/assets/c05f6ef7-126a-4413-b52d-f71b29e85970" />
  • curl test:
curl -I -L --max-time 10 https://docs.langchain.com/mcp
HTTP/2 500 
cache-control: no-store, no-cache, must-revalidate, proxy-revalidate, max-age=0
cf-cache-status: EXPIRED
cf-ray: 9d3bf37f08a4f8c6-SIN
content-security-policy: worker-src * blob: data: 'unsafe-eval' 'unsafe-inline'; object-src data: ; base-uri 'self'; upgrade-insecure-requests; frame-ancestors 'self' https://dashboard.mintlify.com; form-action 'self' https://codesandbox.io;
date: Thu, 26 Feb 2026 02:18:19 GMT
expires: 0
pragma: no-cache
server: Vercel
strict-transport-security: max-age=63072000
vary: rsc, next-router-state-tree, next-router-prefetch, next-router-segment-prefetch, Accept-Encoding
x-cache-key: langchain-5e9cc07a/547/dpl_7Eu9c4KYPBmvyRPAVrgAbKS4oeja/mcp#html=html
x-frame-options: DENY
x-matched-path: /_mintlify/mcp/[subdomain]/[transport]
x-mint-proxy-version: 1.0.0-prod
x-vercel-cache: MISS
x-vercel-id: sin1:sin1:iad1::iad1::gnxt2-1772072299343-defaddc82bd4
content-length: 0

System Info

$ python -m langchain_core.sys_info

System Information
------------------
> OS:  Linux
> OS Version:  #1 SMP Fri Sep 26 15:08:55 CST 2025
> Python Version:  3.12.11 (main, Sep  2 2025, 11:18:24) [GCC 8.5.0 20210514 (Tencent 8.5.0-26)]

Package Information
-------------------
> langchain_core: 1.2.5
> langchain: 1.1.3
> langchain_community: 0.4.1
> langsmith: 0.7.1
> langchain_classic: 1.0.1
> langchain_mcp_adapters: 0.2.1
> langchain_openai: 1.1.6
> langchain_text_splitters: 1.1.0
> langgraph_api: 0.7.29
> langgraph_cli: 0.4.12
> langgraph_runtime_inmem: 0.24.1
> langgraph_sdk: 0.3.1

Optional packages not installed
-------------------------------
> langserve

Other Dependencies
------------------
> aiohttp: 3.13.2
> blockbuster: 1.5.26
> click: 8.3.1
> cloudpickle: 3.1.2
> croniter: 6.0.0
> cryptography: 46.0.3
> dataclasses-json: 0.6.7
> grpcio: 1.78.0
> grpcio-health-checking: 1.78.0
> grpcio-tools: 1.78.0
> httpx: 0.28.1
> httpx-sse: 0.4.3
> jsonpatch: 1.33
> jsonschema-rs: 0.29.1
> langgraph: 1.0.5
> langgraph-checkpoint: 3.0.1
> mcp: 1.25.0
> numpy: 2.4.0
> openai: 2.14.0
> opentelemetry-api: 1.39.1
> opentelemetry-exporter-otlp-proto-http: 1.39.1
> opentelemetry-sdk: 1.39.1
> orjson: 3.11.5
> packaging: 25.0
> protobuf: 6.33.5
> pydantic: 2.12.5
> pydantic-settings: 2.12.0
> pyjwt: 2.10.1
> python-dotenv: 1.2.1
> PyYAML: 6.0.3
> pyyaml: 6.0.3
> requests: 2.32.5
> requests-toolbelt: 1.0.0
> rich: 14.2.0
> SQLAlchemy: 2.0.45
> sqlalchemy: 2.0.45
> sse-starlette: 2.1.3
> starlette: 0.50.0
> structlog: 25.5.0
> tenacity: 9.1.2
> tiktoken: 0.12.0
> truststore: 0.10.4
> typing-extensions: 4.15.0
> uuid-utils: 0.12.0
> uvicorn: 0.40.0
> watchfiles: 1.1.1
> xxhash: 3.6.0
> zstandard: 0.25.0

extent analysis

Fix Plan

Problem Summary

The issue is related to the MCP client for langchain-docs failing to start, resulting in a 500 error when trying to access the MCP server.

Root Cause Analysis

The root cause of the issue is likely related to the MCP server configuration or the MCP client setup.

Fix Plan

Step 1: Check MCP Server Configuration

  • Verify that the MCP server is running and configured correctly.
  • Check the MCP server logs for any errors or issues.

Step 2: Update MCP Client

  • Update the MCP client to the latest version.
  • Check the MCP client documentation for any changes or updates that may affect the MCP server configuration.

Step 3: Configure MCP Client

  • Verify that the MCP client is properly configured to connect to the MCP server.
  • Check the MCP client configuration files for any errors or issues.

Step 4: Test MCP Client

  • Test the MCP client to ensure it can connect to the MCP server and retrieve data correctly.

Step 5: Update langchain Package

  • Update the langchain package to the latest version.
  • Check the langchain documentation for any changes or updates that may affect the MCP client configuration.

Step 6: Test MCP Client Again

  • Test the MCP client again to ensure it can connect to the MCP server and retrieve data correctly after updating the langchain package.

Example Code

import os
import requests

# MCP client configuration
mcp_server_url = "https://docs.langchain.com/mcp"
mcp_client_id = "your_mcp_client_id"
mcp_client_secret = "your_mcp_client_secret"

# Set up MCP client
mcp_client = requests.Session()
mcp_client.auth = (mcp_client_id, mcp_client_secret)

# Test MCP client
response = mcp_client.get(mcp_server_url)
if response.status_code == 200:
    print("MCP client

Vote matrix · Quick signals

Works
Did the solution work? Tap to confirm.
Easy Fix
Was it a quick fix?
Time Saver
Did it save you time?
Blocking
Was it severely blocking?
Common Issue
Are others likely hitting this too?
Flaky / Intermittent
Is it intermittent?
Verified / Reproducible
Can you reproduce it reliably?
Loading…
#api#ssr#installation#tensor shape#autograd error#conversation history#tool integration#LLM response

Still need to ship something?

×6

Another batch ranked right after the header list — different links, same matching logic.

Back to top recommendations

TRENDING