Agent Index

Free open dataset of compliance, security and risk AI agents and audit firms. Read-only search.

我该使用它吗

质量与安全性

A
描述质量
92%
模式完整度
94%
命名质量
96%
投毒风险
100%
权限匹配度
100%
协议合规性
100%

基于对工具定义和协议合规性的自动分析。

上下文开销

~644token 数(工具定义)
~997 B典型响应大小
对注意力有中等影响(占 128k 上下文窗口的 0.50%)

这是每次将服务器的工具加载到模型上下文窗口时所消耗的大致 token 数。数值越高,可用于其他任务的注意力就越少。

安装

一键安装

将以下内容添加到你的 `claude_desktop_config.json` 文件中:

{
  "mcpServers": {
    "agent-index": {
      "url": "https://theagentindex.io/api/mcp"
    }
  }
}

远程端点

https://theagentindex.io/api/mcpstreamable-http

它能做什么

工具清单

工具(5)

🟢 只读🟡 写入🔴 删除⚪ 未知
🟢search_agents(query, category, framework, pricing_model, limit)

Search the Agent Index open dataset of GRC, security, and operations AI agents. Returns canonical theagentindex.io URLs. Not a ranking.

输入模式

{
  "type": "object",
  "properties": {
    "query": {
      "type": "string",
      "description": "Free-text query over name, vendor, summary, description, categories and frameworks"
    },
    "category": {
      "type": "string",
      "description": "Agent category slug (compliance, security, risk, privacy, business-ops, code-security)"
    },
    "framework": {
      "type": "string",
      "description": "Compliance framework filter, e.g. SOC 2, ISO 27001, HIPAA"
    },
    "pricing_model": {
      "type": "string",
      "description": "Pricing model filter, e.g. annual-contract, usage, quote"
    },
    "limit": {
      "type": "integer",
      "minimum": 1,
      "maximum": 100,
      "default": 20
    }
  },
  "additionalProperties": false
}
🟢get_agent(slug)

Get one Agent Index listing by slug, with the canonical page URL and source citations.

输入模式

{
  "type": "object",
  "properties": {
    "slug": {
      "type": "string",
      "description": "Agent slug, e.g. vanta"
    }
  },
  "required": [
    "slug"
  ],
  "additionalProperties": false
}
🟢search_auditors(query, framework, accreditation_body, country, limit)

Search compliance audit firms in Agent Index (Verified and registry-listed), labelled by listing tier. Cross-checked against official accreditation registries (ANAB, UKAS, NABCB, PCI SSC, HITRUST, FedRAMP, GovRAMP, Cyber AB, CERT-In, ISMAP, CPAverify). Not a ranking or endorsement.

输入模式

{
  "type": "object",
  "properties": {
    "query": {
      "type": "string",
      "description": "Free-text query over firm name, headquarters, frameworks and accreditation bodies"
    },
    "framework": {
      "type": "string",
      "description": "Framework tag, e.g. SOC 2, ISO 27001, PCI DSS, CERT-In"
    },
    "accreditation_body": {
      "type": "string",
      "description": "Accreditation body, e.g. ANAB, UKAS, PCI SSC QSA, CERT-In"
    },
    "country": {
      "type": "string",
      "description": "Headquarters or office country (US, United Kingdom, India, …)"
    },
    "limit": {
      "type": "integer",
      "minimum": 1,
      "maximum": 100,
      "default": 20
    }
  },
  "additionalProperties": false
}
🟢get_auditor(slug)

Get one audit firm by slug, including listing_tier, the Verified flag, and accreditation registry URLs for official cross-checks.

输入模式

{
  "type": "object",
  "properties": {
    "slug": {
      "type": "string",
      "description": "Auditor slug, e.g. schellman"
    }
  },
  "required": [
    "slug"
  ],
  "additionalProperties": false
}
⚪compare_agents(slugs)

Compare 2–4 Agent Index listings side by side. Facts only — not a ranking or recommendation.

输入模式

{
  "type": "object",
  "properties": {
    "slugs": {
      "type": "array",
      "minItems": 2,
      "maxItems": 4,
      "items": {
        "type": "string"
      },
      "description": "Array of 2–4 agent slugs"
    }
  },
  "required": [
    "slugs"
  ],
  "additionalProperties": false
}

社区

评价此服务器

证据

最近观测

已验证未记录版本5 个工具