Skip to main content
Glama

AgentScore MCP Server

Official MCP server for the AgentScore Registry (Base Sepolia).

Quick Start

npm install
npm run build
npm run dev          # stdio (Claude Desktop, Cursor, etc.)
# or
HTTP_PORT=3000 npm start   # HTTP/SSE

Related MCP server: Crest Counterparty Intelligence

npm run docker:build
npm run docker:run
# Server available at http://localhost:3000/mcp

Configure in MCP Clients

Claude Desktop / Cursor / Windsurf Add to your MCP config (usually ~/Library/Application Support/Claude/mcp.json or equivalent):

{
  "mcpServers": {
    "agent-score": {
      "command": "node",
      "args": ["/absolute/path/to/agent-score-mcp/dist/index.js"]
    }
  }
}

For Docker version:

{
  "mcpServers": {
    "agent-score": {
      "command": "docker",
      "args": ["run", "-i", "--rm", "agent-score-mcp"]
    }
  }
}

HTTP clients (e.g. custom agents)

POST to http://localhost:3000/mcp with standard MCP JSON-RPC.

Available Tools

  • getAgentScore(identifier) β†’ {score, historyCount, metadataURI}

  • getAgentHistory(tokenId, limit) β†’ [{score, timestamp}, ...]

  • listRegisteredAgents(owner?) β†’ array of enriched agents

All read-only. Zero private keys. Fully trustless.

Enjoy building with AgentScore reputation! πŸš€

Available Tools

3 tools
getAgentHistoryGet Agent HistoryC

Returns array of past scores with timestamps (recent first)

Inputs: tokenId (required), limit.

getAgentScoreGet Agent ScoreB

Returns current reputation score, history count and metadata URI. Accepts tokenId (number) OR agent address (0x...)

Inputs: identifier (required). Returns: score, metadataURI, historyCount

listRegisteredAgentsList Registered AgentsB

List all agents (or single agent by owner address). Returns enriched data.

Inputs: owner.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    B3.1/5.0

    Scored across 3 tools

    Disambiguation5/5

    Each tool has a clearly distinct purpose: getAgentHistory retrieves historical data, getAgentScore provides current reputation metrics, and listRegisteredAgents enumerates agents with optional filtering. There is no overlap in functionality, and the descriptions clearly differentiate their roles.

    Naming Consistency3/5

    The naming is mixed: getAgentHistory and getAgentScore follow a consistent verb_noun pattern, but listRegisteredAgents uses a different verb style ('list' vs. 'get'). While all names are readable, the inconsistency in verb choice reduces predictability.

    Tool Count3/5

    With only 3 tools, the set feels thin for a server named 'AgentScore MCP Server', which suggests a broader scope for managing agent scores and data. While the tools cover basic retrieval and listing, the count may be insufficient for comprehensive operations like updating scores or managing registrations.

    Completeness2/5

    The tool surface is significantly incomplete for an agent scoring system. It only includes read operations (get and list), with no ability to create, update, or delete scores or agents. This leaves obvious gaps in CRUD coverage, likely causing agent failures in scenarios requiring data modification.

    Maintenance

    ActivityInactive
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • F
      license
      Not graded
      quality
      B
      maintenance
      Provides protocol-neutral market intelligence for the AI agent economy, with read-only tools to search agents, retrieve details and histories, compare agents, list categories, view category rankings, and access methodology.
      -
    • A
      license
      A
      quality
      C
      maintenance
      Enables MCP clients to search and inspect AI agents registered in ERC-8004 registries, retrieving profiles, owners, feedback, validations, and USDC-weighted trust scores without requiring a wallet or API key.
      6
      72 npm
      MIT