RepCheck
Trust & reputation infrastructure for AI agents. Two tools: verify_agent returns trust scores and job history for any agent, report_outcome records completed jobs to build reputation over time. Open source, MIT licensed."
README
RepCheck — Agent Trust Infrastructure
Trust & Reputation Infrastructure for the Agent Economy.
A standalone MCP server. Any agent, any marketplace, one source of truth for trust.
What is RepCheck?
RepCheck is an MCP (Model Context Protocol) server that provides trust and reputation as a service for AI agents. When agents hire other agents — they need to know: is this agent legit?
RepCheck answers that question with two simple tools:
| Tool | Description |
|---|---|
verify_agent |
Look up an agent's trust score, success rate, and job history |
report_outcome |
Record a job result to build reputation over time |
Quick Start
# Clone
git clone https://github.com/realMNohgee/repcheck.git
cd repcheck
# Install
npm install
# Run
npm run dev
The MCP endpoint is at http://localhost:3000/api/mcp.
Test with curl
# List tools
curl -X POST http://localhost:3000/api/mcp \
-H "Content-Type: application/json" \
-d '{"jsonrpc":"2.0","method":"tools/list","id":1}'
# Verify an agent
curl -X POST http://localhost:3000/api/mcp \
-H "Content-Type: application/json" \
-d '{"jsonrpc":"2.0","method":"tools/call","params":{"name":"verify_agent","arguments":{"handle":"@security_bot_42"}},"id":2}'
# Report a job outcome
curl -X POST http://localhost:3000/api/mcp \
-H "Content-Type: application/json" \
-d '{"jsonrpc":"2.0","method":"tools/call","params":{"name":"report_outcome","arguments":{"agent_handle":"@security_bot_42","reporter_handle":"@hiring_agent","outcome":"completed","rating":5}},"id":3}'
How Trust Scores Work
- Agents start at 50 (neutral)
- Scores rise with completed jobs and high ratings
- Scores drop with disputes and failures
- The more jobs completed, the more reliable the score
Architecture
- Next.js 16 — App Router, API routes
- SQLite — Zero-config database via Drizzle ORM + libsql
- MCP JSON-RPC — Standard protocol over HTTP POST at
/api/mcp - Auto-discovery —
.well-known/mcpendpoint for tool discovery - Docker — Ready for Glama listing and self-hosting
Docker
docker build -t repcheck .
docker run -p 3000:3000 repcheck
Tech Stack
- Next.js 16.2 + React 19
- TypeScript 5.9
- Drizzle ORM + SQLite (libsql)
- MCP JSON-RPC 2.0
- MIT License
License
MIT — free, open source, use it anywhere.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.