@agentkarma/mcp
Exposes AgentKarma's read-only trust and reputation tools (karma, agents, succession, bonds, check_trust) to any MCP client for checking on-chain agent reputation.
README
@agentkarma/mcp
Turnkey MCP server for AgentKarma — the reputation layer for autonomous on-chain agents.
Expose AgentKarma's read surface (two-faced karma, ERC-8004 agents, succession/bond signals, and a local check_trust gate) to any MCP client — Claude Desktop, Cursor, Continue, …
Run it
npx @agentkarma/mcp # stdio (default) — for Claude Desktop / Cursor
npx @agentkarma/mcp --http --port 8787 # HTTP streamable endpoint at /mcp
That's the whole story — this package bundles @agentkarma/sdk and @modelcontextprotocol/sdk as regular dependencies, so there are no peer flags to remember.
Options
--http Serve over HTTP instead of stdio (default: stdio)
--port <n> HTTP port (default 8787)
--host <host> HTTP host (default 127.0.0.1)
--base-url <url> AgentKarma API base (default https://agentkarma.io;
also reads AGENTKARMA_BASE_URL)
-v, --version Print version
-h, --help Show help
The HTTP server binds loopback (127.0.0.1) by default and enables DNS-rebinding
protection there. The endpoint is read-only and unauthenticated — binding a
non-loopback host (e.g. --host 0.0.0.0) exposes it to the network; put it behind
your own auth/proxy if you do.
Programmatic use
import { startStdioServer, startHttpServer, createAgentKarmaMcpServer } from '@agentkarma/mcp';
await startStdioServer(); // connect over stdio
const http = await startHttpServer({ port: 8787 }); // returns the http.Server
Claude Desktop / Cursor config
{
"mcpServers": {
"agentkarma": {
"command": "npx",
"args": ["-y", "@agentkarma/mcp"]
}
}
}
Tools (read-only)
get_karma · get_celo_agent · search_agents · get_agent_history · get_feedback_summary · get_succession · get_bond · get_surety · check_trust
Every tool is read-only and needs no keys. AgentKarma is non-routing — it answers the trust question; it never signs, executes, or proxies a call.
Under the hood
This is a thin launcher over @agentkarma/sdk/mcp. To embed the server in your own process, or to mount the framework-agnostic tool catalog (@agentkarma/sdk/tools) on an existing MCP server, use the SDK directly.
License
MIT
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
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.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.