MCP.Market

Agent Trust MCP server

by Nikoble1926·io.github.Nikoble1926/agent-trust-mcp·v1.0.0
No reviews yet

ERC-8004 agent trust scores via x402: free preview + paid USDC-on-Base signed scores (5 chains)

B80/100grade B
Write a reviewInstall
What users say
No reviews yet
Be the first
Safety scan
B80/100

full report

Adoption
New

0 stars

Reviews

Write one

Nobody has reviewed Agent Trust yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Agent Trust tools (2)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

  • get_agent_trust

    Paid ($0.005 USDC): signed ERC-8004 trust score (0-100) + component breakdown (client breadth, recency, value, volume) for one agent on a chosen chain. Reads on-chain Identity + Reputation registries.

  • get_trust_preview

    FREE demo: an example ERC-8004 agent trust score (0-100) with component breakdown, no payment, no wallet key required.

Public scan report

scanner v0.1.9 · 2026-09-26 · same rubric, same numbers if you re-run it

no findings
  • Code scan2 source files scanned25/25
  • –Live reliabilityno gateway calls yet and no remote to proben/a
  • –Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitystatic API keys via environment variables6/15
  • Maintenancelast push 8 days ago15/15
  • Maintainer identityregistry namespace matches repository owner6/10
Overall 80/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How Agent Trust compares

Against every graded AI and agents MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
80/100
higher than 60% of 4,460 AI and agents servers
Tools
2
the typical AI and agents server has 6
Tools that change things
0%
typical: 0%. Fewer write tools means less an agent can break

What its tools let an agent do: 2 read

Install Agent Trust in Claude Code, Cursor or VS Code

Runs npx -y @nikosble1926/agent-trust-mcp on your machine. Read the scan report first; the gateway never runs local packages.

claude mcp add agent-trust-mcp -- npx -y @nikosble1926/agent-trust-mcp
Add to Cursor

What the publisher says

From the Agent Trust repository's README, as published. We do not edit it. Read it on GitHub

agent-trust-oracle

Read only, pay per call trust scores for ERC-8004 agents, served over the x402 protocol. Every response is a signed, verifiable verdict.

What this is (for AI agents): a pay per call HTTP 402 endpoint that returns a signed, machine readable trust score for an ERC-8004 agent. No accounts, no API keys. Pay USDC on Base, get a verdict you can verify yourself.

What it does

  • Returns a signed trust score for an agent, on demand, per call over HTTP 402
  • Read only on chain analytics across multiple EVM chains (Ethereum, Base, BSC, Mantle, Polygon)
  • Built for the ERC-8004 agent identity and reputation ecosystem
  • Free preview endpoint so you can see the shape before you pay

How it works

  • Signed with EIP-191; every verdict is canonicalized and independently verifiable
  • Settled per call in USDC on Base
  • You pay only for a successful 2xx response
  • Open source, MIT

Live: trust.nsgoods.org Manifest: /.well-known/x402 · Methodology: /methodology

Part of nsgoods, a suite of signed x402 data oracles. Hub: x402.nsgoods.org

Nothing above is checked by us. What we check is on the safety report.

Agent Trust: common questions

Is Agent Trust MCP server safe?
Mostly: it is graded B (80/100). Read the Agent Trust safety report
How do I install Agent Trust?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does Agent Trust need an API key?
Yes. The registry entry asks for EVM_PRIVATE_KEY.
Is Agent Trust maintained?
The last commit was 47 days ago (2026-09-18). The latest release is v1.0.0.
What can I use instead of Agent Trust?
Servers from other publishers that do the same job: Agoragentic Agent OS MCP server, three.ws Provenance MCP server and IWE (iwe.md) MCP server.
How does Agent Trust compare with other AI and agents MCP servers?
safety score 80/100 (higher than 60% of 4,460 AI and agents servers); tools 2 (the typical AI and agents server has 6); tools that change things 0% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.

Alternatives to Agent Trust

Same job from other publishers: the closest match first, then the best rated.

  • Agoragentic Agent OS MCP
    Triptych OS (Agent OS) MCP for governed routing, receipts, and USDC settlement on Base.
    B
  • three.ws Provenance
    Append-only, signed, on-chain-verifiable agent action log — record and audit what agents did.
    More from nirholas →
    B
  • IWE (iwe.md)
    Markdown knowledge base as agent memory. Runs against the notes directory it is started in.
    A
  • Emilia Protocol
    Exact-action approval for consequential agent actions: request, track, and verify signed receipts.
    B
  • Attestix
    AI agent identity, signed credentials, delegated authority and governance evidence.
    A