Index Agentica

Search a curated directory of agent tools, MCP servers, APIs, protocols and skills. No auth.

我該用這個嗎

品質與安全性

A
說明品質
100%
結構描述完整度
80%
命名品質
100%
汙染風險
100%
權限相符程度
100%
協定合規性
100%

根據工具定義與協定合規性的自動化分析。

上下文成本

~1,578Token(工具定義)
~3.1 KB典型回應大小
中等的注意力影響(128k 上下文的 1.23%)

這是每次將伺服器的工具載入模型上下文時所消耗的約略 token 數量。數量越高,可用於其他工作的注意力就越少。

安裝

一鍵安裝

將以下內容加入你的 `claude_desktop_config.json` 檔案:

{
  "mcpServers": {
    "mcp": {
      "url": "https://mcp.indexagentica.com/mcp"
    }
  }
}

遠端端點

https://mcp.indexagentica.com/mcpstreamable-http

它能做什麼

工具清單

工具(4)

🟢 唯讀🟡 寫入🔴 刪除⚪ 未知
🟢search(query, type, category, tags, limit)

Search Index Agentica: the directory of agent-usable resources (skills, harnesses, MCP servers, tools, protocols, APIs, information sources, finance/payments, directories) plus its long-form content (guides, comparisons, stacks and downloadable Agent Skills). Matches the query words against name/title, id, tags, summary and description and returns the best matches first, each with its type, a relevance score and links (HTML, markdown, JSON). Optionally filter by type (entry, guide, comparison, stack, skill; default all), category (entries only) and/or tags (ALL given tags must match). An empty query with a filter lists everything in that filter. For full details use get_entry for type entry, or get_content with the type and id for long-form items.

輸入結構描述

{
  "type": "object",
  "properties": {
    "query": {
      "type": "string",
      "maxLength": 200,
      "description": "Free-text search words, e.g. \"browser automation\" or \"payments x402\". May be empty when category or tags are given."
    },
    "type": {
      "type": "string",
      "enum": [
        "entry",
        "guide",
        "comparison",
        "stack",
        "skill",
        "all"
      ],
      "default": "all",
      "description": "Optional result type: entry (directory entries), guide, comparison, stack, skill, or all (default)."
    },
    "category": {
      "type": "string",
      "description": "Optional entry category slug to restrict results to (implies type entry). Current categories: skills, harnesses, mcp-servers, tools, protocols, apis, information, finance-payments, directories, infrastructure, evals-observability."
    },
    "tags": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "maxItems": 10,
      "description": "Optional list of tag slugs; results must have all of them (e.g. [\"open-source\", \"python\"])."
    },
    "limit": {
      "type": "integer",
      "minimum": 1,
      "maximum": 50,
      "default": 10,
      "description": "Maximum number of results (1-50, default 10)."
    }
  },
  "additionalProperties": false
}

輸出結構描述

{
  "type": "object",
  "properties": {
    "query": {
      "type": "string"
    },
    "type": {
      "type": "string",
      "description": "Type filter applied (all when none)."
    },
    "category": {
      "type": "string",
      "description": "Category filter applied (omitted when none)."
    },
    "tags": {
      "type": "array",
      "items": {
        "type": "string"
      }
    },
    "limit": {
      "type": "integer"
    },
    "total": {
      "type": "integer",
      "description": "Number of matches before the limit was applied."
    },
    "results": {
      "type": "array",
      "items": {
        "type": "object",
        "properties": {
          "type": {
            "type": "string",
            "enum": [
              "entry",
              "guide",
              "comparison",
              "stack",
              "skill"
            ],
            "description": "entry (directory entry) or a long-form type: guide, comparison, stack, skill."
          },
          "id": {
            "type": "string"
          },
          "name": {
            "type": "string"
          },
          "category": {
            "type": "string",
            "description": "Entries only."
          },
          "summary": {
            "type": "string"
          },
          "url": {
            "type": "string"
          },
          "tags": {
            "type": "array",
            "items": {
              "type": "string"
            }
          },
          "author": {
            "type": "string",
            "description": "Long-form only."
          },
          "last_verified": {
            "type": "string",
            "description": "Long-form only."
          },
          "entries": {
            "type": "array",
            "items": {
              "type": "string"
            },
            "description": "Long-form only: directory entry ids it references."
          },
          "status": {
            "type": "string"
          },
          "pricing": {
            "type": "string"
          },
          "mcp_endpoint": {
            "type": "string"
          },
          "score": {
            "type": "number"
          },
          "links": {
            "type": "object"
          }
        },
        "required": [
          "type",
          "id",
          "name",
          "summary",
          "url"
        ]
      }
    }
  },
  "required": [
    "query",
    "total",
    "results"
  ]
}
🟢get_entry(id)

Fetch one Index Agentica entry by its id (kebab-case slug, e.g. "model-context-protocol"). Returns every field: name, category, summary, description, url, repo, docs, tags, license, pricing, status, agent_access (llms_txt, openapi, mcp_endpoint, auth), related ids, sources, dates and links. If the id is unknown the result is an error with suggested ids.

輸入結構描述

{
  "type": "object",
  "properties": {
    "id": {
      "type": "string",
      "pattern": "^[a-z0-9]+(?:-[a-z0-9]+)*$",
      "maxLength": 80,
      "description": "Entry id (kebab-case slug) as returned by search."
    }
  },
  "required": [
    "id"
  ],
  "additionalProperties": false
}

輸出結構描述

{
  "type": "object",
  "properties": {
    "entry": {
      "type": "object",
      "description": "The full entry, following https://indexagentica.com/schema/entry.schema.json plus a links object."
    }
  },
  "required": [
    "entry"
  ]
}
🟢get_content(type, id, include_html)

Fetch one Index Agentica long-form item by type and id (as returned by search). Returns its metadata (title, summary, author, tags, dates, referenced entries with links, related items, sources, links) and its markdown (scheme links resolved to absolute URLs). Comparisons include the structured table (criteria, one row per entry, verdict); stacks include the use case and components; skills include the full SKILL.md (skill_md) plus download links (links.zip, links.skill_md). Unknown ids return an error with suggestions.

輸入結構描述

{
  "type": "object",
  "properties": {
    "type": {
      "type": "string",
      "enum": [
        "guide",
        "comparison",
        "stack",
        "skill"
      ],
      "description": "guide, comparison, stack or skill."
    },
    "id": {
      "type": "string",
      "pattern": "^[a-z0-9]+(?:-[a-z0-9]+)*$",
      "maxLength": 80,
      "description": "Item id (kebab-case slug) as returned by search."
    },
    "include_html": {
      "type": "boolean",
      "default": false,
      "description": "Also return the rendered HTML body."
    }
  },
  "required": [
    "type",
    "id"
  ],
  "additionalProperties": false
}

輸出結構描述

{
  "type": "object",
  "properties": {
    "content": {
      "type": "object",
      "description": "The item: front_matter, markdown, links and type-specific fields (comparison, stack, skill_md). See https://indexagentica.com/openapi.json (LongformItem).",
      "properties": {
        "type": {
          "type": "string"
        },
        "id": {
          "type": "string"
        },
        "title": {
          "type": "string"
        },
        "markdown": {
          "type": "string"
        },
        "links": {
          "type": "object"
        }
      },
      "required": [
        "type",
        "id",
        "title",
        "markdown"
      ]
    }
  },
  "required": [
    "content"
  ]
}
🟢list_categories

List all Index Agentica categories with their slug, name, description, entry count and links (HTML page and JSON). Use a slug as the category filter for search.

輸入結構描述

{
  "type": "object",
  "properties": {},
  "additionalProperties": false
}

輸出結構描述

{
  "type": "object",
  "properties": {
    "total": {
      "type": "integer",
      "description": "Total number of entries in the directory."
    },
    "generated": {
      "type": "string",
      "description": "When the published index was built."
    },
    "categories": {
      "type": "array",
      "items": {
        "type": "object",
        "properties": {
          "slug": {
            "type": "string"
          },
          "name": {
            "type": "string"
          },
          "description": {
            "type": "string"
          },
          "count": {
            "type": "integer"
          },
          "html": {
            "type": "string"
          },
          "json": {
            "type": "string"
          }
        },
        "required": [
          "slug",
          "name",
          "count"
        ]
      }
    }
  },
  "required": [
    "total",
    "categories"
  ]
}

社群

為此伺服器評分

證據

近期觀測

已驗證未記錄版本4 個工具