MCP.so
登录

Agentforge Trust

@KOVY

代码仓库

关于 Agentforge Trust

One MCP connection → 100+ MCP servers, with trust audit, discovery, and execution│Trust Scores (0-100) across 5 dimensions: code health, security, behavioral audit│community trust, EU compliance.

基本信息

分类

开发工具

传输方式

stdio

发布者

KOVY

提交者

Dušan Kovář

配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

{
  "mcpServers": {
    "agentforge": {
      "command": "npx",
      "args": [
        "-y",
        "agentforge-trust-mcp@latest"
      ],
      "env": {
        "AGENTFORGE_API_URL": "https://agentforge.community",
        "AGENTFORGE_API_KEY": "af_agent_REPLACE_AFTER_REGISTRATION"
      }
    }
  }
}

工具

8

Fetch the AgentForge Trust Score for an MCP server. Returns the overall score (0-100), per-dimension breakdown (code_health, security_scan, behavioral_audit, community_trust, eu_compliance), and badges. Use before connecting to any MCP server.

Check whether a server passes a trust policy. Returns allowed:true/false plus individual check results. Example policy: {min_overall: 70, required_badges: ['actively_maintained']}. Use this to gate agent decisions like 'should I use this server for financial data?'.

Search AgentForge catalog for servers matching a category and minimum trust threshold. Returns up to 25 results sorted by trust score.

Given a natural-language use case, recommend MCP servers filtered by trust. Example: 'I need to validate Czech VAT IDs and convert ISDOC invoices'. Uses AgentForge semantic search + trust filter.

Browse the AgentForge catalog of MCP servers. Supports full-text search, semantic search, and category filtering. No authentication required. Use this when you need to find servers offering a specific capability (e.g. 'GitHub PR automation', 'EU VAT validation'). Returns server metadata, tool counts, pricing tier, and trust scores. Each result carries TWO trust fields: `audit_score` (0-100, dynamic from the AgentForge audit pipeline — AUTHORITATIVE for policy gating, may be null if not yet audited) and `trust_score` (0-10, legacy community rating — for display fallback only). Always prefer audit_score when present; treat null audit_score as 'audit pending'.

Search ACROSS multiple MCP servers in a single call. Returns relevant tools per server, sorted by relevance. Replaces N sequential discover+capabilities calls. Requires AGENTFORGE_API_KEY (set in env or call register_agent first). Use this when an agent needs to fan out a query like 'find me anything that can parse DICOM medical images' across the catalog.

Invoke any tool on any MCP server in the AgentForge catalog. AgentForge proxies the call, applies rate limits, billing (per-call or wallet credits), and returns the result. Requires AGENTFORGE_API_KEY. Use this to actually USE a server's capability after discovery, e.g. call_tool(server='github-pro', tool='create_pr', input={...}).

Self-register this agent with AgentForge. Returns an af_agent_* API key that unlocks broadcast_search and call_tool. Run once at agent startup, store the key in env as AGENTFORGE_API_KEY. No auth required for registration. Idempotent on slug — running twice produces a uniqued slug.

概览

What is Agentforge Trust?

Agentforge Trust is an MCP server that provides a single connection to over 100 MCP servers, with integrated trust audit, discovery, and execution. It assigns trust scores (0-100) across five dimensions: code health, security, behavioral audit, community trust, and EU compliance.

How to use Agentforge Trust?

—

Key features of Agentforge Trust

  • Access to 100+ MCP servers via one connection
  • Trust audit across five dimensions
  • Discovery of available MCP servers
  • Execution of MCP server operations
  • Trust scores (0-100) for each dimension

Use cases of Agentforge Trust

—

FAQ from Agentforge Trust

—

评论

开发工具 分类下的更多 MCP 服务器

Deepwiki MCP Server

regenrek

📖 MCP server for fetch deepwiki.com and get latest knowledge in Cursor and other Code Editors

1.4K

Serena

oraios

A powerful MCP toolkit for coding, providing semantic retrieval and editing capabilities - the IDE for your agent

26.2K

sentry-mcp

getsentry

An MCP server for interacting with Sentry via LLMs.

754

TalkToFigma

sonnylazuardi

TalkToFigma: MCP integration between AI Agent (Cursor, Claude Code, Codex) and Figma, allowing Agentic AI to communicate with Figma for reading designs and modifying them programmatically.

6.9K

Grafana MCP server

grafana

MCP server for Grafana

3.2K