Agentresources MCP server
io.github.sznt2010/agentresources-mcp·v0.1.2MCP server for Agent Resources: Trust Cards, signed telemetry, ERC-8004 identity, x402.
0 stars
Reviews
Write oneNobody has reviewed Agentresources yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
Agentresources tools (4, 1 write)
write = sends, deletes, buys or postsRead from the package source without running it. The installed server may list more.
memoryMemory verbs (remember, recall, forget, improve). Reads and writes go through the unified telemetry-as-memory store; recall is a multi-stage retrieval (cosine + cross-encoder + MMR + tail prune) handled server-side.
signing_keysManage an agent's signed-telemetry keys (list / register / revoke). Wraps /api/v1/agents/{id}/signing-keys.
telemetry_ingestwrite actionSubmit a batch of telemetry spans (optionally signed envelope) to the AR gateway. Requires an authenticated session token.
trust_card_lookupFetch the public Trust Card (signed JSON-LD VC) for a wallet from /.well-known/trust-card/{wallet}. Optionally include the latest Merkle anchor proof.
Public scan report
scanner v0.1.9 · 2026-09-27 · same rubric, same numbers if you re-run it
- Code scan14 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 146 days ago8/15
- Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
How Agentresources compares
Against every graded AI and agents MCP server, from our own scans and uptime checks. Updated after each scan run.
- Safety score
- 72/100
- higher than 40% of 4,460 AI and agents servers
- Tools
- 4
- the typical AI and agents server has 6
- Tools that change things
- 25%
- typical: 0%. Fewer write tools means less an agent can break
What its tools let an agent do: 3 read · 1 change
Install Agentresources in Claude Code, Cursor or VS Code
Runs npx -y @agentresources/mcp on your machine. Read the scan report first; the gateway never runs local packages.
claude mcp add agentresources-mcp -- npx -y @agentresources/mcp
What the publisher says
From the Agentresources repository's README, as published. We do not edit it. Read it on GitHub
@agentresources/mcp
Operational MCP server for Agent Resources —
Trust Card lookup, signed telemetry, memory verbs, signing-key management,
and the ar CLI in one package.
This repo is the public mirror of @agentresources/mcp. The package is published to npm from the AR monorepo; this mirror exists so the MCP Registry, punkpeye/awesome-mcp-servers, and any agent that wants to fork the source can read it without authenticating.
Install
# Run as a one-shot MCP server (recommended for Claude Desktop / Cursor / Copilot CLI)
npx -y @agentresources/mcp
# Or install globally to get the `ar` CLI
npm i -g @agentresources/mcp
ar doctor # 6-check self-diagnostic
ar skills get agent-resourcesWiring
// .mcp.json (Claude Desktop / Cursor / Copilot CLI)
{
"mcpServers": {
"agentresources": {
"command": "npx",
"args": ["-y", "@agentresources/mcp"],
"env": {
"AR_API_BASE": "https://api.agentresources.xyz",
"AR_AGENT_PRIVATE_KEY": "0x...", // optional; needed for write-side tools
},
},
},
}Tools
A second public package, @agentresources/docs-mcp, is a read-only doc explorer that runs without any AR credentials. Use it for agents that only need to read AR specs.
Skills are free
@agentresources/mcp is free. Paid AR products — Trust Card issuance, Scan, KYA, Retraining, on-chain attestation — are billable API services. This MCP server doesn't expose paid endpoints behind a free fly-by; it delegates to the gateway, which enforces the x402 payment challenge. See PHILOSOPHY.
Crypto-scam notice
AR has no token, no presale, no airdrop, no points, no staking. We will never DM you to ask for seed phrases, private keys, or funds. The only on-chain artefacts are ERC-8004 Identity NFTs, daily Merkle anchors, and the AR Treasury Agent (Base mainnet tokenId 45880). Report impersonation to contact@agentresources.xyz.
How this repo stays in sync
This repo is a downstream mirror of the canonical source at packages/mcp/ in the AR monorepo. CI on every push:
- Re-runs npm pack against the published @agentresources/mcp@ and diffs the tarball contents against src/ here.
- Validates server.json against the live MCP Registry schema.
To open a PR, edit the canonical source in the AR monorepo — the change will land here via the next sync.
License
MIT © Agent Resources
Trust Card
Verify the publisher of this repo: https://api.agentresources.xyz/.well-known/trust-card/agent/32f4ec0b-452e-467d-997b-ebd49730bb0a
Nothing above is checked by us. What we check is on the safety report.
Agentresources: common questions
- Is Agentresources MCP server safe?
- Mostly: it is graded B (72/100). Read the Agentresources safety report
- How do I install Agentresources?
- It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
- Does Agentresources need an API key?
- Yes. The registry entry asks for
AR_AGENT_PRIVATE_KEY. - Is Agentresources maintained?
- The last commit was 184 days ago (2026-05-04). The latest release is v0.1.2.
- What can I use instead of Agentresources?
- Servers from other publishers that do the same job: Attestix MCP server, Emilia Protocol MCP server and three.ws Provenance MCP server.
- How does Agentresources compare with other AI and agents MCP servers?
- safety score 72/100 (higher than 40% of 4,460 AI and agents servers); tools 4 (the typical AI and agents server has 6); tools that change things 25% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.
Alternatives to Agentresources
Same job from other publishers: the closest match first, then the best rated.
- AttestixAI agent identity, signed credentials, delegated authority and governance evidence.not reviewedEstablishedA
- Emilia ProtocolExact-action approval for consequential agent actions: request, track, and verify signed receipts.not reviewedEstablishedB
- three.ws ProvenanceAppend-only, signed, on-chain-verifiable agent action log — record and audit what agents did.not reviewedEstablishedB