Koskamo

Index Agentica MCP

A remote MCP server and REST search API for Index Agentica, an agent-first directory of skills, harnesses, MCP servers, tools, protocols and APIs. It allows agents to search the directory, retrieve entry details, access content like guides and skills, list categories, and request new listings for curator review.

Endpoint and access

No sign-in to connect and list tools. Individual tools may still need a vendor account, credentials, or permissions; check the documented prerequisites.

Index Agentica MCP logo, by Index AgenticaVendor evidenceStreamable HTTPNo sign-inEndpoint checked 2026-11-06Operated by Index Agentica
MCP endpoint (Streamable HTTP)
https://mcp.indexagentica.com/mcp
Vendor documentation

What its tools do

5 tools, grouped by the hints the server advertises. Hints are self-declared, not verified behavior.

Can change data (1)

5 of 5 have a description · 5 of 5 declare behavior hints · 4 of 4 with parameters document them all

Checks and signals

Each line is separate evidence, not a trust score.

  • Passed Endpoint answered the live check ·
  • Passed Official MCP Registry namespace is tied to indexagentica.com ·
  • Passed Endpoint is on the registry namespace domain ·
  • Availability 1 of 1 checks passed in 30 days

What you can do with it

  • Search for MCP servers, tools, and APIs in the directory
  • Retrieve full details of a specific directory entry
  • Access content such as guides, comparisons, and skills
  • Request a new listing to be added to the directory

Source and maintenance

Vendor evidenceRegistry 0.1.0
Maintenance checked

Protocol and capabilities

Server
indexagentica-mcp 0.2.0
MCP protocol negotiated in check
2025-11-25
Tools
5 advertised
Resources
Not advertised
Resource templates
Not advertised
Prompts
Not advertised
Server-advertised capabilities
{
  "tools": {
    "listChanged": false
  }
}

Server-provided instructions

Untrusted server output shown for inspection. It is not Koskamo guidance and is excluded from knowledge search.

Index Agentica (https://indexagentica.com) is an agent-first directory of skills, agent harnesses, MCP servers, tools, protocols, APIs, information sources, finance/payment rails and other directories, plus long-form guides, comparisons, stacks and downloadable Agent Skills. Use `search` to find resources by keywords, type (entry, guide, comparison, stack, skill), category and tags; `get_entry` for the full record of one directory entry; `get_content` (type + id) for a guide, comparison, stack or skill with its markdown; `list_categories` for the category slugs and counts; `request_listing` to ask for something missing to be added (verified by the Curator before listing). Directory data is read-only, refreshed from the published site every ~10 minutes, and licensed CC BY 4.0. To add or correct an entry, see https://indexagentica.com/agents/#contribute.

Tools

5 advertised

search — Search Index Agentica
Advertised by the server during the last successful anonymous check.
Advertised read-only

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.

search input schema
{
  "type": "object",
  "properties": {
    "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\"])."
    },
    "type": {
      "enum": [
        "entry",
        "guide",
        "comparison",
        "stack",
        "skill",
        "all"
      ],
      "type": "string",
      "default": "all",
      "description": "Optional result type: entry (directory entries), guide, comparison, stack, skill, or all (default)."
    },
    "limit": {
      "type": "integer",
      "default": 10,
      "maximum": 50,
      "minimum": 1,
      "description": "Maximum number of results (1-50, default 10)."
    },
    "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."
    },
    "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."
    }
  },
  "additionalProperties": false
}
search output schema
{
  "type": "object",
  "required": [
    "query",
    "total",
    "results"
  ],
  "properties": {
    "tags": {
      "type": "array",
      "items": {
        "type": "string"
      }
    },
    "type": {
      "type": "string",
      "description": "Type filter applied (all when none)."
    },
    "limit": {
      "type": "integer"
    },
    "query": {
      "type": "string"
    },
    "total": {
      "type": "integer",
      "description": "Number of matches before the limit was applied."
    },
    "results": {
      "type": "array",
      "items": {
        "type": "object",
        "required": [
          "type",
          "id",
          "name",
          "summary",
          "url"
        ],
        "properties": {
          "id": {
            "type": "string"
          },
          "url": {
            "type": "string"
          },
          "name": {
            "type": "string"
          },
          "tags": {
            "type": "array",
            "items": {
              "type": "string"
            }
          },
          "type": {
            "enum": [
              "entry",
              "guide",
              "comparison",
              "stack",
              "skill"
            ],
            "type": "string",
            "description": "entry (directory entry) or a long-form type: guide, comparison, stack, skill."
          },
          "links": {
            "type": "object"
          },
          "score": {
            "type": "number"
          },
          "author": {
            "type": "string",
            "description": "Long-form only."
          },
          "status": {
            "type": "string"
          },
          "entries": {
            "type": "array",
            "items": {
              "type": "string"
            },
            "description": "Long-form only: directory entry ids it references."
          },
          "pricing": {
            "type": "string"
          },
          "summary": {
            "type": "string"
          },
          "category": {
            "type": "string",
            "description": "Entries only."
          },
          "mcp_endpoint": {
            "type": "string"
          },
          "last_verified": {
            "type": "string",
            "description": "Long-form only."
          }
        }
      }
    },
    "category": {
      "type": "string",
      "description": "Category filter applied (omitted when none)."
    }
  }
}
search annotations
{
  "title": "Search Index Agentica",
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}
get_entry — Get directory entry
Advertised by the server during the last successful anonymous check.
Advertised read-only

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.

get_entry input schema
{
  "type": "object",
  "required": [
    "id"
  ],
  "properties": {
    "id": {
      "type": "string",
      "pattern": "^[a-z0-9]+(?:-[a-z0-9]+)*$",
      "maxLength": 80,
      "description": "Entry id (kebab-case slug) as returned by search."
    }
  },
  "additionalProperties": false
}
get_entry output schema
{
  "type": "object",
  "required": [
    "entry"
  ],
  "properties": {
    "entry": {
      "type": "object",
      "description": "The full entry, following https://indexagentica.com/schema/entry.schema.json plus a links object."
    }
  }
}
get_entry annotations
{
  "title": "Get directory entry",
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}
get_content — Get guide, comparison, stack or skill
Advertised by the server during the last successful anonymous check.
Advertised read-only

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.

get_content input schema
{
  "type": "object",
  "required": [
    "type",
    "id"
  ],
  "properties": {
    "id": {
      "type": "string",
      "pattern": "^[a-z0-9]+(?:-[a-z0-9]+)*$",
      "maxLength": 80,
      "description": "Item id (kebab-case slug) as returned by search."
    },
    "type": {
      "enum": [
        "guide",
        "comparison",
        "stack",
        "skill"
      ],
      "type": "string",
      "description": "guide, comparison, stack or skill."
    },
    "include_html": {
      "type": "boolean",
      "default": false,
      "description": "Also return the rendered HTML body."
    }
  },
  "additionalProperties": false
}
get_content output schema
{
  "type": "object",
  "required": [
    "content"
  ],
  "properties": {
    "content": {
      "type": "object",
      "required": [
        "type",
        "id",
        "title",
        "markdown"
      ],
      "properties": {
        "id": {
          "type": "string"
        },
        "type": {
          "type": "string"
        },
        "links": {
          "type": "object"
        },
        "title": {
          "type": "string"
        },
        "markdown": {
          "type": "string"
        }
      },
      "description": "The item: front_matter, markdown, links and type-specific fields (comparison, stack, skill_md). See https://indexagentica.com/openapi.json (LongformItem)."
    }
  }
}
get_content annotations
{
  "title": "Get guide, comparison, stack or skill",
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}
list_categories — List categories
Advertised by the server during the last successful anonymous check.
Advertised read-only

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.

list_categories input schema
{
  "type": "object",
  "properties": {},
  "additionalProperties": false
}
list_categories output schema
{
  "type": "object",
  "required": [
    "total",
    "categories"
  ],
  "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",
        "required": [
          "slug",
          "name",
          "count"
        ],
        "properties": {
          "html": {
            "type": "string"
          },
          "json": {
            "type": "string"
          },
          "name": {
            "type": "string"
          },
          "slug": {
            "type": "string"
          },
          "count": {
            "type": "integer"
          },
          "description": {
            "type": "string"
          }
        }
      }
    }
  }
}
list_categories annotations
{
  "title": "List categories",
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}
request_listing — Request a listing
Advertised by the server during the last successful anonymous check.

Ask Index Agentica to add something that is missing (a skill, agent harness, MCP server, tool, protocol, API, ...). Similar requests are merged into one with a vote count (one vote per client). Nothing is listed automatically: the Curator verifies each request first. The public queue is at https://mcp.indexagentica.com/v1/requests and https://indexagentica.com/requested/. Limits: 5 requests per hour and 20 per day per client. Search first to check it is not already listed.

request_listing input schema
{
  "type": "object",
  "required": [
    "wanted",
    "category"
  ],
  "properties": {
    "url": {
      "type": "string",
      "format": "uri",
      "maxLength": 300,
      "description": "Optional http(s) link (repo, docs or homepage). Not shown publicly until verified."
    },
    "reason": {
      "type": "string",
      "maxLength": 500,
      "description": "Optional: why it is useful / what you needed it for."
    },
    "wanted": {
      "type": "string",
      "maxLength": 120,
      "minLength": 1,
      "description": "Short name of what is wanted, e.g. \"Linear MCP server\" or \"a skill for Terraform plans\"."
    },
    "category": {
      "enum": [
        "skills",
        "harnesses",
        "mcp-servers",
        "tools",
        "protocols",
        "apis",
        "information",
        "finance-payments",
        "directories",
        "infrastructure",
        "evals-observability",
        "other"
      ],
      "type": "string",
      "description": "Directory category slug, or \"other\". Current categories: skills, harnesses, mcp-servers, tools, protocols, apis, information, finance-payments, directories, infrastructure, evals-observability."
    },
    "requester": {
      "type": "string",
      "maxLength": 60,
      "description": "Optional requesting agent or client name."
    }
  },
  "additionalProperties": false
}
request_listing output schema
{
  "type": "object",
  "required": [
    "ok",
    "id",
    "merged",
    "request"
  ],
  "properties": {
    "id": {
      "type": "integer"
    },
    "ok": {
      "type": "boolean"
    },
    "list": {
      "type": "string"
    },
    "note": {
      "type": "string"
    },
    "merged": {
      "type": "boolean"
    },
    "request": {
      "type": "object",
      "properties": {
        "id": {
          "type": "integer"
        },
        "votes": {
          "type": "integer"
        },
        "status": {
          "enum": [
            "pending",
            "verified",
            "listed",
            "rejected"
          ],
          "type": "string"
        },
        "wanted": {
          "type": "string"
        },
        "category": {
          "type": "string"
        },
        "last_seen": {
          "type": "string"
        },
        "first_seen": {
          "type": "string"
        }
      }
    },
    "vote_counted": {
      "type": "boolean"
    }
  }
}
request_listing annotations
{
  "title": "Request a listing",
  "readOnlyHint": false,
  "openWorldHint": false,
  "idempotentHint": false,
  "destructiveHint": false
}

Prompts

Not advertised

No prompt definitions available.

Resources

Not advertised

No resource definitions available.

90-day uptime

A lightweight connection check about every six hours, sampled on hosts with many listings. It shows the server answered, not that its tools work.

Too few checks for a percentage yet (1 of 1 answered).

  1. 2026-11-07: 1 of 1 checks answered

30-day availability

Aggregated from read-only remote checks; this is not a tool-execution or security guarantee.

Successful checks
1 of 1 (100%)
Average latency
524 ms
95th percentile latency
524 ms

Maintenance history

Public check and source-refresh events. Editorial and ownership records remain private.

  • · probe · passed · 524 ms · metadata changed · 5 tool(s)

Connect from your client

Each snippet registers the same endpoint; pick the client you use.

This server is operated by the named third party. Listing and endpoint checks are not an endorsement or a security audit. Review the operator's permissions, terms, and data handling before connecting. How listings are checked and corrected.

Claude Code

Run this once in a terminal. It registers the remote server. Use --scope project to write .mcp.json for the repo.
Claude Code configuration
claude mcp add --transport http index-agentica-mcp https://mcp.indexagentica.com/mcp

Codex

Run this once. Codex stores MCP servers in ~/.codex/config.toml (or .codex/config.toml in a trusted project).
Codex configuration
codex mcp add index-agentica-mcp --url https://mcp.indexagentica.com/mcp

Cursor

Merge this server into .cursor/mcp.json in your project, then enable index-agentica-mcp in your MCP settings.
Cursor configuration
{
  "mcpServers": {
    "index-agentica-mcp": {
      "url": "https://mcp.indexagentica.com/mcp"
    }
  }
}

Cline

Merge this into cline_mcp_settings.json (Cline → MCP Servers → Configure).
Cline configuration
{
  "mcpServers": {
    "index-agentica-mcp": {
      "type": "streamableHttp",
      "url": "https://mcp.indexagentica.com/mcp",
      "disabled": false
    }
  }
}

VS Code

Merge this server into .vscode/mcp.json. Use MCP: List Servers to start index-agentica-mcp and inspect its tools.
VS Code configuration
{
  "servers": {
    "index-agentica-mcp": {
      "type": "http",
      "url": "https://mcp.indexagentica.com/mcp"
    }
  }
}

Gemini CLI

Run this once. It writes .gemini/settings.json in the current project; pass --scope user for ~/.gemini/settings.json.
Gemini CLI configuration
gemini mcp add --transport http index-agentica-mcp https://mcp.indexagentica.com/mcp

Claude Desktop

Open Claude Settings > Connectors > Add custom connector, enter this server URL and enable it for the conversation. This is a manual remote-connector handoff, not a desktop JSON configuration.
Claude Desktop configuration
https://mcp.indexagentica.com/mcp

Windsurf

Merge this into ~/.codeium/windsurf/mcp_config.json, then refresh MCP in Cascade. Windsurf remote servers use serverUrl, not url.
Windsurf configuration
{
  "mcpServers": {
    "index-agentica-mcp": {
      "serverUrl": "https://mcp.indexagentica.com/mcp"
    }
  }
}

Let your agent find its tools

Find servers like Index Agentica MCP from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.

Do you run Index Agentica MCP?

Prove ownership with a DNS record, a well-known file, or your Official MCP Registry entry, and your edits publish immediately. Proofs are re-checked weekly; admins can still hide or remove a listing.

Claim this listing