crewai - 💡(How to fix) Fix [FEATURE] Behavioral trust scoring for crew agent interactions [1 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
crewAIInc/crewAI#5789Fetched 2026-05-14 03:34:14
View on GitHub
Comments
0
Participants
1
Timeline
2
Reactions
0
Author
Participants
Timeline (top)
labeled ×1renamed ×1

Code Example

curl https://dominion-observatory.sgdata.workers.dev/api/agent-query/{agent-id}

---

from crewai import Agent, Task, Crew
from crewai.tools import TrustGateTool

trust_gate = TrustGateTool(
    provider="dominion-observatory",
    threshold=60,  # PASS if score >= 60
    fail_mode="block"  # block task on FAIL
)

agent = Agent(
    role="Payment Processor",
    tools=[trust_gate],
    # trust_gate auto-checks before executing paid actions
)
RAW_BUFFERClick to expand / collapse

Feature Area

Core functionality

Is your feature request related to a an existing bug? Please link it here.

NA

Describe the solution you'd like

Add a behavioral trust scoring layer that evaluates agent/MCP server trustworthiness before crews execute paid actions or sensitive operations.

When crews interact with external MCP servers or paid APIs, there's no standardized way to verify the other party is trustworthy. The x402 Trust-Provider Interface (open spec) solves this with a beforeSettle hook that queries trust providers before settlement.

The Dominion Observatory already tracks 4,500+ MCP servers with behavioral trust scores via a simple REST API:

curl https://dominion-observatory.sgdata.workers.dev/api/agent-query/{agent-id}

This returns a trust score (0-100), behavioral metrics, and attestation data that can gate crew actions.

Describe alternatives you've considered

A TrustGate tool or middleware in CrewAI that runs before task execution:

from crewai import Agent, Task, Crew
from crewai.tools import TrustGateTool

trust_gate = TrustGateTool(
    provider="dominion-observatory",
    threshold=60,  # PASS if score >= 60
    fail_mode="block"  # block task on FAIL
)

agent = Agent(
    role="Payment Processor",
    tools=[trust_gate],
    # trust_gate auto-checks before executing paid actions
)

Reference implementation: https://github.com/vdineshk/daee-engine/tree/main/testnet-demo Integration guide: https://github.com/vdineshk/daee-engine/blob/main/docs/INTEGRATE.md Spec: https://github.com/vdineshk/daee-engine/blob/main/specs/x402-trust-provider-interface/v0.1/SPEC.md

Additional context

Observatory dashboard: https://dominion-observatory.sgdata.workers.dev API stats (4,500+ servers): https://dominion-observatory.sgdata.workers.dev/api/stats The x402 HTTP 402 payment protocol is being adopted for agent-to-agent payments, and needs a trust layer.

Willingness to Contribute

Yes, I'd be happy to submit a pull request

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…

Still need to ship something?

×6

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

Back to top recommendations

TRENDING

crewai - 💡(How to fix) Fix [FEATURE] Behavioral trust scoring for crew agent interactions [1 participants]