Lets an AI client check the reputation of microservices and public APIs using an open trust registry.
Also known as trustscoreagent/trustscoreagent, trustscoreagent, @trustscoreagent/mcp-server
- Stars
- 0
- Tools
- —
- Downloads, 30 days
- —
- Latest version
- 0.2.7
- Last commit
- Nov 16, 2026
- License
- Apache-2.0
What is TrustScoreAgent MCP?
TrustScoreAgent lets an AI client check the reputation of microservices and public APIs using an open trust registry.
Summary generated from the project's README
About TrustScoreAgent MCP server
TrustScoreAgent provides an open reputation registry designed for AI agents and microservices. It allows developers to verify the reliability of public APIs and services by checking trust scores before making calls. The system uses Bayesian scoring and EigenTrust to evaluate dimensions like availability, latency, and conformity, helping agents discover which services are dependable.
This MCP server integrates with clients like Claude and Cursor, enabling agents to perform reputation checks via the check_reputation tool. Users can also submit ratings for services they have interacted with to contribute to the registry. The setup requires no accounts or API keys, as services can be identified simply by their URL, domain, or DID.
Security is maintained through a Merkle audit trail and Ed25519 receipt verification, ensuring that ratings and service interactions are auditable. While the registry is currently in an early phase, it offers a transparent way to manage trust in the agentic economy without requiring upfront registration.
What you can do with it
- 1Verify service reliabilityAn AI agent can check the reputation of a microservice before attempting to call it.
- 2Contribute to service ratingsDevelopers can submit performance metrics to rate a service after an interaction.
- 3Discover dependable APIsUsers can search for the highest rated services within the registry.
Written from the project's README. Every use case is checked against a quote from it.
How to install TrustScoreAgent MCP
Formats verified 10 Nov 2026Add to CursorAdd to GooseInstall TrustScoreAgent MCP in Claude Code
$ claude mcp add trustscoreagent -- npx -y @trustscoreagent/mcp-serverInstall TrustScoreAgent MCP in Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"trustscoreagent": {
"command": "npx",
"args": [
"-y",
"@trustscoreagent/mcp-server"
]
}
}
}Install TrustScoreAgent MCP in VS Code
.vscode/mcp.json
{
"servers": {
"trustscoreagent": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@trustscoreagent/mcp-server"
]
}
}
}Install TrustScoreAgent MCP in VS Code CLI
$ code --add-mcp '{"name":"trustscoreagent","type":"stdio","command":"npx","args":["-y","@trustscoreagent/mcp-server"]}'Install TrustScoreAgent MCP in Claude Desktop
claude_desktop_config.json
{
"mcpServers": {
"trustscoreagent": {
"command": "npx",
"args": [
"-y",
"@trustscoreagent/mcp-server"
]
}
}
}Install TrustScoreAgent MCP in Codex
$ codex mcp add trustscoreagent -- npx -y @trustscoreagent/mcp-serverInstall TrustScoreAgent MCP in Codex config.toml
~/.codex/config.toml
[mcp_servers.trustscoreagent] command = "npx" args = ["-y", "@trustscoreagent/mcp-server"]
Install TrustScoreAgent MCP in Gemini CLI
$ gemini mcp add -s user trustscoreagent npx -- -y @trustscoreagent/mcp-serverInstall TrustScoreAgent MCP in Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"trustscoreagent": {
"command": "npx",
"args": [
"-y",
"@trustscoreagent/mcp-server"
]
}
}
}Configuration
TRUSTSCORE_AGENT_DIDLeave empty (recommended): the server generates an Ed25519 key in ~/.trustscoreagent and signs its ratings with the matching did:key. Setting a DID here overrides that key, so ratings are sent unsigned and count at half weight.
TRUSTSCORE_API_URLBase URL of the TrustScore registry. Defaults to the public production API; override only for a self-hosted or staging instance.
Automated checks
Ran Nov 14, 2026Full report →Passed our automated checks. That is not a security audit: read the code and give the server the narrowest access it needs. How checks work
- Source repository linked and reachabletrustscoreagent/trustscoreagent is public and reachablegithub.com/trustscoreagent/trustscoreagent ↗Pass
- Package names this repository as its source@trustscoreagent/mcp-server names trustscoreagent/trustscoreagent as sourcenpmjs.com/package/@trustscoreagent/mcp-server ↗Pass
- Build provenance (Sigstore attestation)No build attestation published for this releaseNot checked
- Open source license (OSI)Apache-2.0spdx.org/licenses/Apache-2.0.html ↗Pass
- Commit or release in the last yearLast commit or release 2026-11-12github.com/trustscoreagent/trustscoreagent ↗Pass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNo popular package one edit away from @trustscoreagent/mcp-serverPass
- No critical advisory in the package or its dependencies99 resolved dependencies checked; no critical advisoryosv.dev ↗Pass
- 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 handshakeNot checked
README
View on GitHubTrustScoreAgent
Free, open reputation registry for AI microservices. Agents check trust scores before calling any service.
Status: Phase 1 (early). The API, scoring (Beta + EigenTrust), receipt verification, Merkle audit trail and MCP server are implemented and tested, but the public dataset is still small (seeded by a transparent probe of public APIs and x402 endpoints), and parts of the design (x402 payments, mandatory agent signatures) are Phase 2. We publish early and openly on purpose: the trust layer for the agentic economy should exist, be auditable, and be adoptable before it becomes critical. See the trust model in SECURITY.md.
What is this?
AI agents increasingly rely on paid microservices. TrustScoreAgent lets any agent:
- Check the reputation of a service before calling it
- Rate a service after calling it
- Discover which services are reliable
No account needed. No API key. Identify services by URL, domain, or DID.
Quick start
# Check a service's trust score (any format works)
curl "https://api.trustscoreagent.com/v1/score?service=api.example.com"
curl "https://api.trustscoreagent.com/v1/score?service=https://api.example.com/v1/translate"
# Unknown services return a neutral score (0.5), no errors
curl "https://api.trustscoreagent.com/v1/score?service=never-seen-before.com"
# Rate a service after calling it
curl -X POST "https://api.trustscoreagent.com/v1/rate" \
-H "Content-Type: application/json" \
-H "X-Agent-DID: my-agent.example.com" \
-d '{
"service": "api.example.com",
"metrics": {
"status_code": 200,
"latency_ms": 143,
"schema_valid": true
}
}'
# List top-rated services
curl "https://api.trustscoreagent.com/v1/services?sort_by=score&min_ratings=10"
Local development
# Start PostgreSQL and Redis
docker compose up -d
# Run the API
dotnet run --project src/TrustScore.Api
# Run tests
dotnet test
# Swagger UI
open http://localhost:5000/swagger
Architecture
- C# / .NET 8: ASP.NET Core Minimal API
- PostgreSQL: Ratings and service scores
- Redis: Score caching, rate limiting, nonce tracking
- Beta Reputation System: Bayesian scoring (per-dimension: availability, latency, conformity)
- EigenTrust: Anti-Sybil agent trust scoring
- Merkle Tree: Audit log with inclusion and consistency proofs (RFC 6962 tree; each leaf commits to what the rating reported)
- Ed25519 Receipt Verification: Cryptographic proof of service interaction
- MCP Server: Integration with Claude, Cursor, and MCP-compatible agents
API Reference
Core (free, always)
| Endpoint | Description |
|---|---|
GET /v1/score?service= |
Trust score for a service (0.5 neutral for unknown) |
POST /v1/rate |
Submit a rating after calling a service |
GET /v1/services |
List rated services (pagination, sorting, filtering) |
GET /v1/agent/trust?did= |
Check your agent's trust score |
GET /v1/audit/root |
Latest Merkle tree root |
GET /v1/audit/proof/{id} |
Inclusion proof for a rating, with the fields it commits to |
GET /v1/audit/anchors |
History of anchored roots |
GET /v1/audit/consistency?from=&to= |
Proof that a later root extends an earlier one |
GET /v1/audit/anchors/{id}/ots |
OpenTimestamps proof that the root is committed in Bitcoin |
GET /v1/stats?days= |
How much the registry is used (aggregate counts) |
Premium (free for now, x402 micropayments later)
| Endpoint | Description |
|---|---|
GET /v1/score/history?service= |
Daily aggregated score history |
GET /v1/score/detailed?service= |
Latency percentiles, quality distribution |
POST /v1/scores/bulk |
Up to 100 scores in one request |
Service identification
All endpoints accept services in any format (they are normalized internally):
api.example.com(domain)https://api.example.com/v1/translate(URL)did:web:api.example.com(DID)
All three resolve to the same service.
MCP Server
TrustScoreAgent is available as an MCP server for Claude, Cursor, and other agents.
# Add to Claude Code
claude mcp add trustscoreagent -- npx -y @trustscoreagent/mcp-server
Before paying an x402 endpoint, check_reputation with the pay_to of the 402 you received
says whether that payee is the one the registry has seen there. See docs/mcp.md
for full setup instructions. Also listed on the
official MCP Registry
(io.github.trustscoreagent/mcp-server), npm,
Smithery and
Glama; each GitHub release attaches an
.mcpb bundle for Claude Desktop.
x402 plugin
@trustscoreagent/x402 plugs into the x402 client SDK (@x402/core, used by
@x402/fetch and @x402/axios). Before each payment it checks the payee against the one the
registry saw on that endpoint and stops the payment on a mismatch, before anything is signed.
const guard = trustScoreGuard();
guard.attach(client, http);
const fetchWithPayment = wrapFetchWithPayment(guard.wrapFetch(fetch), http);
The score alone never blocks unless you set minScore, an unreachable registry never blocks
unless you set failClosed, and rating after payment is opt-in (rate: true). It runs in your
agent: requests never go through TrustScoreAgent. See x402-plugin/README.md.
Framework integrations
Drop-in tools for agent frameworks (no account or API key needed):
- LangChain:
from trustscoreagent_langchain import get_trustscoreagent_tools - CrewAI:
from trustscoreagent_crewai import get_trustscoreagent_tools
Each exposes trustscore_check_reputation, trustscore_submit_rating, and
trustscore_list_services. See integrations/.
Documentation
- API Reference
- Examples & Recipes
- Receipt Standard
- MCP Server Setup: Claude, Cursor, Windsurf
- x402 plugin: check the payee before paying
- Why Trust Matters for Agents
- Privacy & Data Handling
- Audit Log Specification, with an independent verifier in
tools/verify-proof
Contributing
Contributions are welcome: see CONTRIBUTING.md and our Code of Conduct. To report a vulnerability, follow SECURITY.md.
Project status & trust model
TrustScoreAgent is Phase 1 (early). What that means in practice:
- Baseline data is real and auditable. Initial scores come from a transparent operated
probe (
did:web:trustscoreagent.com:probe) that measures the availability, latency and conformity of a curated list of public, free APIs, and of the x402 endpoints agents pay the most (picked daily from the public Bazaar catalog and probed without paying, see docs/x402-probe.md): real, Merkle-audited measurements, not fabricated numbers. For those x402 endpoints the score also says which payee address and price they ask for, and when either last changed. Community and receipt-verified ratings accumulate on top. (The earlier fictitious*.example.comseeds have been removed.) - Single operator. Neutrality currently rests on open-source scoring code and a verifiable Merkle audit trail, not on decentralization. Federation is a later phase.
- Agent identity can be proven, but is not yet mandatory. Agents identified by a
did:keysign each rating with their Ed25519 key (X-Agent-Signature), which binds the rating to the holder of that key. Unsigned ratings still count at half weight so existing clients keep working, which means a rating is only as attributable as its signature. Verified service receipts remain the strongest signal.
See SECURITY.md for the full trust model and how to report vulnerabilities.
License
Apache-2.0. See LICENSE.
TrustScoreAgent MCP questions
How do I add TrustScoreAgent MCP to Claude Code?
Run claude mcp add trustscoreagent -- npx -y @trustscoreagent/mcp-server in your terminal. Add --scope user to make it available in every project.
How do I add TrustScoreAgent 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 use TrustScoreAgent?
No, you do not need an account or an API key to use the service.
How can I identify a service in the registry?
You can identify services using a URL, a domain, or a Decentralized Identifier (DID).
What happens if I check a service that is not in the registry?
Unknown services will return a neutral score of 0.5 without causing errors.