AgentTrust MCP server
Commit Oct 31, 2026Verify the reliability and ownership of AI agent endpoints before making calls using pre-invocation trust checks.
Also known as agenttrust-ai/agenttrust, agenttrust
- Stars
- 0
- Tools
- —
- Downloads, 30 days
- —
- Latest version
- 1.0.4
- Last commit
- Oct 31, 2026
- License
- MIT
What is AgentTrust MCP?
AgentTrust verifies the reliability and ownership of AI agent endpoints before making calls using pre-invocation trust checks.
Summary generated from the project's README
About AgentTrust MCP server
AgentTrust provides infrastructure for verifying the reliability and ownership of AI agent endpoints before an interaction occurs. It allows developers to perform pre-invocation trust checks on MCP and A2A agents by looking up an invocation URL to receive a machine-readable trust decision. This process is entirely read-only and does not contact the target endpoint during the check, ensuring privacy and speed.
Users can access these capabilities through a TypeScript SDK or by connecting to a public MCP server via a streamable HTTP transport. No account or API key is required for public trust checks, which include tools like check_agent_trust and assess_agent. For those managing their own agents, an account and API key are necessary to register identities, perform daily health checks, and accumulate reliability scores based on observed history.
What you can do with it
- 1Verify endpoint reliability before callingAn AI client can check if a specific agent URL is healthy and reachable before attempting to make a request.
Written from the project's README. Every use case is checked against a quote from it.
How to install AgentTrust MCP
Formats verified 10 Nov 2026Add to CursorAdd to GooseInstall AgentTrust MCP in Claude Code
$ claude mcp add --transport http agenttrust https://getagenttrust.com/api/mcp/publicInstall AgentTrust MCP in Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"agenttrust": {
"url": "https://getagenttrust.com/api/mcp/public"
}
}
}Install AgentTrust MCP in VS Code
.vscode/mcp.json
{
"servers": {
"agenttrust": {
"type": "http",
"url": "https://getagenttrust.com/api/mcp/public"
}
}
}Install AgentTrust MCP in VS Code CLI
$ code --add-mcp '{"name":"agenttrust","type":"http","url":"https://getagenttrust.com/api/mcp/public"}'Install AgentTrust MCP in Codex
$ codex mcp add agenttrust --url https://getagenttrust.com/api/mcp/publicInstall AgentTrust MCP in Codex config.toml
~/.codex/config.toml
[mcp_servers.agenttrust] url = "https://getagenttrust.com/api/mcp/public"
Install AgentTrust MCP in Gemini CLI
$ gemini mcp add -s user --transport http agenttrust https://getagenttrust.com/api/mcp/publicInstall AgentTrust MCP in Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"agenttrust": {
"url": "https://getagenttrust.com/api/mcp/public",
"type": "http"
}
}
}Automated checks
Ran Nov 15, 2026Full report →Not verified yet. A server needs a score of 80, no serious finding, and enough data for us to check. How checks work · What to fix for more points
- Source repository linked and reachableagenttrust-ai/agenttrust is public and reachablegithub.com/agenttrust-ai/agenttrust ↗Pass
- Package names this repository as its sourceNot checked
- Build provenance (Sigstore attestation)Not checked
- Open source license (OSI)MITspdx.org/licenses/MIT.html ↗Pass
- Commit or release in the last yearLast commit or release 2026-10-31github.com/agenttrust-ai/agenttrust ↗Pass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNot checked
- No critical advisory in the package or its dependenciesNot checked
- No hidden instructions to the model0 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledNot checked
- Remote endpoint answers the MCP handshakeinitialize answered with protocol 2025-06-18 in 270 msPass
README
View on GitHubAgentTrust — Pre-invocation Trust Check for AI Agent Endpoints
Check an AI agent or MCP server endpoint before you call it. Given the exact
endpoint URL, AgentTrust returns the reliability evidence it has already
collected, endpoint-ownership verification, and a machine-readable
trustDecision — without contacting the endpoint.
No AgentTrust account or API key required · Read-only · MCP and TypeScript SDK
AgentTrust is trust infrastructure for AI agents. It provides
reliability monitoring, endpoint verification, and pre-invocation trust
checks for MCP and A2A agents. An agent registers an identity, gets
health-checked once a day, optionally proves ownership of its
endpoint, and accumulates a deterministic reliability score from that
observed history. Any external AI agent or system can look up another
agent by its invocation URL and get back a machine-readable
trustDecision — a signal derived from AgentTrust's own observed and
verified data, for the caller to weigh, never a certification or
guarantee of safety — before deciding whether to interact with it.
Official MCP Registry identity: io.github.agenttrust-ai/agenttrust.
Quick start — no account needed
Every example below checks AgentTrust's own monitored test agent,
https://agenttrust-umber.vercel.app/api/test-agent; swap in the URL you're
about to call.
MCP
Add the public connector https://getagenttrust.com/api/mcp/public
(Streamable HTTP, no authentication; two read-only tools, check_agent_trust
and assess_agent).
In Claude Code:
claude mcp add --transport http agenttrust https://getagenttrust.com/api/mcp/public
Claude Desktop, Cursor and a plain curl call:
Connect an MCP client.
TypeScript SDK
npm install @getagenttrust/sdk
import { checkAgentTrust } from "@getagenttrust/sdk";
// AgentTrust's own test agent: a real, monitored endpoint you can check.
const result = await checkAgentTrust("https://agenttrust-umber.vercel.app/api/test-agent");
if (result.matched) {
console.log(result.status, result.reliabilityScore, result.trustDecision);
// e.g. "healthy" 100 { recommended: true, confidence: "high", reasons: [] }
} else {
// AgentTrust has no data for this endpoint (yet). An unmatched result never
// carries a score; result.observation may say it was queued for a lookup.
console.log("Unknown endpoint", result.observation?.status);
}
Policies (assertTrusted), errors and options: SDK README
· npm. New to AgentTrust?
Start with First 5 minutes.
In the browser
Check the test agent on getagenttrust.com.
First 5 minutes
No account or API key. Node.js 18 or later.
1. Install. assessAgent needs SDK 0.2.0 or later.
npm install @getagenttrust/sdk@^0.2.0
2. Check an endpoint. This checks AgentTrust's own monitored test agent, so it returns a real result. The check is read-only, and AgentTrust never contacts the endpoint you ask about.
import { assessAgent } from "@getagenttrust/sdk";
// AgentTrust's own monitored test agent. Swap in the URL your agent is about to call.
const assessment = await assessAgent("https://agenttrust-umber.vercel.app/api/test-agent");
console.log(assessment.decision, assessment.confidence, assessment.reasonCodes);
// e.g. allow_with_caution high ["OWNERSHIP_VERIFIED", "REACHABLE_AT_LAST_CHECK", …]
if (assessment.decision === "allow_with_caution") {
// Reachable and not failing in AgentTrust's observations. Not proof that the
// agent behaves safely: keep your own safeguards when you call it.
} else {
// "avoid", or "insufficient_evidence" — also the answer for a URL AgentTrust
// doesn't monitor (matched: false, reasonCodes includes "UNKNOWN_ENDPOINT").
console.log("Not calling it:", assessment.limitations);
}
3. Read the answer. confidence, reasonCodes and limitations say why.
decision |
What it means | What to do |
|---|---|---|
allow_with_caution |
AgentTrust's observations show the endpoint reachable and not failing: a current historical reliability score, or at least two successful observations at least 10 minutes apart. | Call it, with your own safeguards. It isn't proof that the agent behaves safely. |
avoid |
AgentTrust's observations show it failing — for example two or more consecutive failures, or a current reliability score below 50. | Don't call it. |
insufficient_evidence |
Not enough evidence either way: an endpoint AgentTrust doesn't monitor, too few or too old observations, or a single failure that may be temporary. | Don't treat it as approval — handle it as an unknown endpoint. |
Which call should I use?
| Call | Use it when | You get |
|---|---|---|
assessAgent(url) |
Your agent needs one decision to act on before it calls an endpoint. | decision, confidence, reasonCodes and limitations, with the evidence behind them. |
checkAgentTrust(url) |
You want the evidence itself — status, reliabilityScore, verified and trustDecision — to apply your own rules. |
{ matched: true, … }, or { matched: false } for an endpoint AgentTrust doesn't monitor. |
assertTrusted(url, policy) |
You want a gate: go ahead only if the endpoint meets your policy. | The checkAgentTrust result, or a thrown NotTrustedError. |
All three are anonymous and read-only, and never contact the endpoint (over MCP: assess_agent and check_agent_trust). They report what AgentTrust has observed; they don't certify an endpoint's security.
Unknown endpoints are an answer, not an error
AgentTrust only has evidence for endpoints it monitors, so your first check of a real URL may come back unknown. That is an answer, not an API failure — the call succeeds:
assessAgentreturnsmatched: false,decision: "insufficient_evidence",confidence: "none", andreasonCodesincluding"UNKNOWN_ENDPOINT".checkAgentTrustreturns{ matched: false }, sometimes with anobservationstatus when AgentTrust has queued the URL for a lookup in the official MCP Registry.assertTrustedthrowsNotTrustedError("AgentTrust has no data for this endpoint") unless you passallowUnknown: true.
Real failures — RATE_LIMITED, TIMEOUT, NETWORK_ERROR and the rest — throw an AgentTrustError instead.
Handle an unknown endpoint as not trusted: don't map insufficient_evidence to "allow", keep allowUnknown: false (the default) unless you have chosen otherwise on purpose, and ask a human or run your own checks before calling an endpoint nobody has observed.
Next steps
- Gate a real connection:
examples/check-before-connect.tsputsassertTrustedin front of an MCP client connection. - Tune the gate:
minConfidence,requireVerifiedandminReliabilityScorein theassertTrustedpolicy — see the SDK README. - Running an agent yourself? Register it so other agents can check it — that needs an account and an API key: Getting started.
Public checks vs. agent management
| Public trust checks | Agent management | |
|---|---|---|
| For | Checking any endpoint before you call it | Registering and monitoring your own agents; full agent records |
| Account / API key | Not needed | Account and API key (Authorization: Bearer <API_KEY>) |
| Interfaces | MCP check_agent_trust and assess_agent at /api/mcp/public; @getagenttrust/sdk (checkAgentTrust, assertTrusted, assessAgent) |
REST /api/v1/*; MCP server /api/mcp (list_agents, get_agent, get_agent_health, send_heartbeat) |
To register an agent: sign up, create a key under Dashboard → API keys, then follow Getting started (REST).
Documentation
You don't need this repository to use AgentTrust:
- /docs — full REST, MCP and SDK reference.
- /llms.txt — the same reference as one plain-text file, for an LLM's context.
Developing this project
This is a Next.js (App Router) + Drizzle + Supabase app, deployed on Vercel.
npm install
npm run dev
Open http://localhost:3000. You'll need a
.env.local — see .env.example for the required variables (Supabase
credentials, database connection strings, and the server-only secrets
described inline).
Useful scripts:
npm run test # vitest — full suite runs against an embedded pglite DB, no live database needed
npm run typecheck # tsc --noEmit
npm run lint # eslint
npm run db:generate # generate a new Drizzle migration from schema changes (offline)
npm run db:migrate # apply pending migrations to the database in DIRECT_URL
AgentTrust MCP questions
How do I add AgentTrust MCP to Claude Code?
Run claude mcp add --transport http agenttrust https://getagenttrust.com/api/mcp/public in your terminal. Add --scope user to make it available in every project.
How do I add AgentTrust MCP to Cursor?
Open ~/.cursor/mcp.json and add the server under mcpServers, using the Cursor config shown in the install section above.
Do I need an account or API key to check an agent?
No, public trust checks are anonymous and read-only, requiring no account or API key.
Does AgentTrust contact the endpoint I am checking?
No, AgentTrust provides reliability evidence and trust decisions without contacting the target endpoint directly.
What does an 'allow_with_caution' decision mean?
It means observations show the endpoint is reachable and not failing, but it is not a guarantee of safety.
What should I do if the endpoint is unknown?
You should treat unknown endpoints as not trusted and handle them as unknown rather than approving them.