Skip to main content
Glama

AgentTrust — Pre-Invocation AI Agent Trust & Reliability Checks

Server Details

Check an AI agent endpoint before you call it: read-only, no API key, returns a trustDecision.

Ownership verified
Status
Healthy
Uptime
100.0% over the last 24 hours
Last Tested
Transport
Streamable HTTP · MCP 2025-11-25
URL
Repository
agenttrust-ai/agenttrust
GitHub Stars
0
Server Listing
AgentTrust
ChatGPT
–
Claude
–

TDQS

A3.7/5.0

Scored across 6 tools

Disambiguation2/5

Three tools answer essentially the same question: 'should I invoke this unknown endpoint URL?' — assess_agent, check_agent_trust, and list_agents (with the endpointUrl parameter) all return a reliability score plus a trustDecision for an external URL. An agent must read long descriptions carefully to pick the right one, and the difference between assess_agent's decision/confidence and check_agent_trust's trustDecision is not obvious from the names.

Naming Consistency4/5

All names are snake_case verb_noun (assess_agent, check_agent_trust, get_agent, get_agent_health, list_agents, send_heartbeat). Minor drift in verb choice (assess vs check vs get) for near-identical operations, which reinforces rather than resolves the ambiguity.

Tool Count4/5

Six tools is a reasonable size for a trust-check server, but two of them (assess_agent, check_agent_trust) are redundant entry points to the same lookup, so the surface is slightly padded rather than tight.

Completeness3/5

Read-side coverage is decent (discovery, profile, health, heartbeat, pre-invocation lookup), but there is no enrollment/registration, no score history or trend, and no way to report or submit observations, leaving the lifecycle one-sided.

Publisher details

Operator
AgentTrust · Publisher source
Vendor relationship
First-party · Publisher source
Privacy policy
Not provided
Trust center
Not available
Restrictions
Not applicable

Available Tools

6 tools
assess_agentAssess AgentA
Read-onlyIdempotent
Inspect

Immediate use-or-avoid decision about an AI agent or MCP server endpoint, for an agent deciding whether to call it. Returns decision (allow_with_caution, avoid, or insufficient_evidence), confidence, reasonCodes, reachability (the latest stored observation, with its age), initialRisk, the historical reliability score and trustDecision (unchanged), limitations, and freshness. Built only from AgentTrust's stored observations: it never contacts endpointUrl. Reachability is not safety: allow_with_caution never means the agent's behavior is safe. Requires no API key.

Inputs: endpointUrl (required). Returns: mode, agent, status, matched, +9 more

check_agent_trustCheck Agent TrustA
Read-onlyIdempotent
Inspect

Pre-invocation trust check for an unknown AI agent or MCP server endpoint. Read-only, requires no AgentTrust API key or account. Looks up an agent by its exact invocation URL among AgentTrust's already-observed public agents and returns its status, endpoint-ownership verification, agent reliability score (when available), and a machine-readable trustDecision (recommended, confidence, reasons). Does NOT contact endpointUrl itself during this check — it only reads AgentTrust's own existing monitoring history. An unregistered URL returns { matched: false }, never an error.

Inputs: endpointUrl (required). Returns: name, slug, status, matched, +5 more

get_agentGet AgentA
Read-onlyIdempotent
Inspect

Get one AgentTrust agent's public profile by slug, including its structured Agent Card, current reliability score, and a machine-readable trustDecision (recommended, confidence, reasons) for deciding whether to invoke it.

Inputs: slug (required). Returns: id, name, slug, source, +15 more

get_agent_healthGet Agent HealthA
Read-onlyIdempotent
Inspect

Get one agent's current effective health status and monitoring detail — derived from heartbeat freshness for push-mode agents, or the latest pull check otherwise.

Inputs: slug (required). Returns: slug, status, agentId, latencyMs, +6 more

list_agentsList AgentsA
Read-onlyIdempotent
Inspect

Discover AgentTrust agents. Pass endpointUrl to check the trust status of a specific external agent by its exact invocation URL before deciding whether to invoke it — the response includes a reliability score, endpoint-ownership verification status, and a machine-readable trustDecision (recommended, confidence, reasons). Without endpointUrl, returns the plain paginated listing of public agents, newest first. Requires an API key; for an anonymous pre-invocation check use check_agent_trust.

Inputs: limit, cursor, endpointUrl. Returns: agents, pagination

send_heartbeatSend HeartbeatAInspect

Record a push-style heartbeat for an agent you own, marking it alive right now. The server sets the timestamp; no client-supplied time is accepted.

Inputs: slug (required). Returns: slug, status, lastHeartbeatAt

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      A
      quality
      B
      maintenance
      A free, read-only server that lets users diagnose production AI-agent risks: it flags over-privileged API keys from permission descriptions, scans code snippets for the signals that prevent duplicate execution, and explains guard patterns such as idempotency keys, approval gates, outboxes, and circuit breakers. It makes no network calls or writes, and rejects inputs that look like real secrets.
      3
      46 PyPI
      MIT
    • A
      license
      Not graded
      quality
      C
      maintenance
      Provides AI agents with zero-cost, zero-dependency trust evaluation for domains, URLs, wallets, APIs, and IPs, returning a 0-100 score with SSL, DNS, WHOIS, security header, and content sub-scores, plus batch comparison to rank multiple targets.
      MIT
    • A
      license
      Not graded
      quality
      B
      maintenance
      Enables users to run read-only trust checks on an x402 endpoint and receive a signed report covering endpoint lint, signed offers, ERC-8004 identity, and payer mix before paying.
      MIT
    Try in Browser

    Glama MCP Gateway

    Add one secure layer between your agents and this server.