AI Collection MCP

A read-only MCP server that allows agents to search, browse, and compare AI tools from the AI Collection directory. It supports querying tools by category, fetching specific tool details, finding alternatives, viewing curated top picks, and performing side-by-side comparisons of pricing and deployment options.

Visit AI Collection

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.

Community listingStreamable HTTPNo sign-inEndpoint checked 2026-11-01Published by AI Collection

MCP endpoint (Streamable HTTP)

https://thataicollection.com/mcp

Vendor documentation

What you can do with it

Search AI tools by query and category
Fetch details for a specific tool
Find similar tools or alternatives
Compare tools side-by-side

Source and maintenance

Community listingRegistry 0.1.0

mcp-registry: io.github.kerbelp/ai-collection@0.1.0 Project website

Protocol and capabilities

Server: thataicollection-mcp 0.1.0
MCP protocol: 2025-06-18
Tools: 7 advertised
Resources: Not advertised
Resource templates: Not advertised
Prompts: Not advertised

Server-advertised capabilities

{
  "tools": {
    "listChanged": true
  }
}

Tools

7 advertised

search_tools

Advertised by the server during the last successful anonymous check.

Search the AI Collection directory for AI tools matching a query. Returns a ranked list with name, URL, and short description. Use this for 'find me a tool that does X' requests.

search_tools input schema

{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "required": [
    "query"
  ],
  "properties": {
    "limit": {
      "type": "integer",
      "default": 10,
      "maximum": 50,
      "minimum": 1,
      "description": "Maximum number of results to return."
    },
    "query": {
      "type": "string",
      "minLength": 1,
      "description": "Free-text query to match against application names and descriptions."
    },
    "category": {
      "type": "string",
      "description": "Optional category linkName to scope the search (e.g. 'image-generation')."
    }
  },
  "additionalProperties": false
}

get_tool

Advertised by the server during the last successful anonymous check.

Fetch the full detail page for a specific AI tool by its linkName. Returns name, full description, category, screenshot, and additional information if available.

get_tool input schema

{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "required": [
    "linkName"
  ],
  "properties": {
    "linkName": {
      "type": "string",
      "minLength": 1,
      "description": "The canonical linkName of the application (the slug used in /application/<linkName>)."
    }
  },
  "additionalProperties": false
}

list_categories

Advertised by the server during the last successful anonymous check.

List all categories in the directory. Useful when the user wants to browse by topic or narrow a search by category.

list_categories input schema

{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {}
}

browse_category

Advertised by the server during the last successful anonymous check.

List applications inside a specific category, paginated. Use this when the user wants to explore an area rather than search for a specific tool.

browse_category input schema

{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "required": [
    "linkName"
  ],
  "properties": {
    "limit": {
      "type": "integer",
      "default": 20,
      "maximum": 100,
      "minimum": 1,
      "description": "Page size."
    },
    "offset": {
      "type": "integer",
      "default": 0,
      "minimum": 0,
      "description": "Number of results to skip for pagination."
    },
    "linkName": {
      "type": "string",
      "minLength": 1,
      "description": "The category linkName (e.g. 'image-generation')."
    }
  },
  "additionalProperties": false
}

get_alternatives

Advertised by the server during the last successful anonymous check.

Given a specific AI tool, return similar tools (same category, excluding the original). Use for 'what's like X?' or 'cheaper alternative to Y' questions.

get_alternatives input schema

{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "required": [
    "linkName"
  ],
  "properties": {
    "limit": {
      "type": "integer",
      "default": 10,
      "maximum": 50,
      "minimum": 1
    },
    "linkName": {
      "type": "string",
      "minLength": 1,
      "description": "The linkName of the application to find alternatives for."
    }
  },
  "additionalProperties": false
}

get_top_picks

Advertised by the server during the last successful anonymous check.

Return curated editorial picks across the directory, or within a specific category if provided. Use for 'recommend the best AI tools' or 'top X in Y' questions.

get_top_picks input schema

{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "limit": {
      "type": "integer",
      "default": 10,
      "maximum": 50,
      "minimum": 1
    },
    "category": {
      "type": "string",
      "description": "Optional category linkName to scope the picks."
    }
  },
  "additionalProperties": false
}

compare_tools

Advertised by the server during the last successful anonymous check.

Compare two AI tools side-by-side. Returns structured attributes for both (pricing, deployment, modality, content policy) so the client can recommend which fits a user's needs.

compare_tools input schema

{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "required": [
    "linkName_a",
    "linkName_b"
  ],
  "properties": {
    "linkName_a": {
      "type": "string",
      "minLength": 1,
      "description": "The canonical linkName of the first application (slug used in /application/<linkName>)."
    },
    "linkName_b": {
      "type": "string",
      "minLength": 1,
      "description": "The canonical linkName of the second application."
    }
  },
  "additionalProperties": false
}

Prompts

Not advertised

No prompt definitions available.

Resources

Not advertised

No resource definitions available.

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: 369 ms
95th percentile latency: 369 ms

Maintenance history

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

Nov 1, 2026, 8:56 AM UTC · probe · passed · 369 ms · metadata changed · 7 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 ai-collection-mcp https://thataicollection.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 ai-collection-mcp --url https://thataicollection.com/mcp

Cursor

Merge this server into .cursor/mcp.json in your project, then enable ai-collection-mcp in your MCP settings.

Cursor configuration

{
  "mcpServers": {
    "ai-collection-mcp": {
      "url": "https://thataicollection.com/mcp"
    }
  }
}

Cline

Merge this into cline_mcp_settings.json (Cline → MCP Servers → Configure).

Cline configuration

{
  "mcpServers": {
    "ai-collection-mcp": {
      "type": "streamableHttp",
      "url": "https://thataicollection.com/mcp",
      "disabled": false
    }
  }
}

VS Code

Merge this server into .vscode/mcp.json. Use MCP: List Servers to start ai-collection-mcp and inspect its tools.

VS Code configuration

{
  "servers": {
    "ai-collection-mcp": {
      "type": "http",
      "url": "https://thataicollection.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 ai-collection-mcp https://thataicollection.com/mcp

Claude Desktop

Merge this into claude_desktop_config.json (macOS: ~/Library/Application Support/Claude/, Windows: %APPDATA%\Claude\), then restart Claude Desktop.

Claude Desktop configuration

{
  "mcpServers": {
    "ai-collection-mcp": {
      "url": "https://thataicollection.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": {
    "ai-collection-mcp": {
      "serverUrl": "https://thataicollection.com/mcp"
    }
  }
}

Let your agent find its tools

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

Connect Koskamo Explore workflows