AI Collection

io.github.kerbelpPublished by GitHub account kerbelpv0.1.0Updated Oct 29, 2026

Discover and compare AI tools: search, browse categories, find alternatives and curated picks.

VerifiedStreamable HTTPWeb executableWeb Search & ScrapingAI & ML

Overview

AI-generated overview

Remote MCP server for the AI Collection directory: lets an assistant search, browse, compare and get recommendations for AI tools.

What you can do
  • Search the AI tool directory by query and get ranked results with name, link and short description
  • Fetch a tool's full detail page by its linkName, including category, screenshot and extra information
  • List directory categories and browse paginated applications within a category
  • Find alternatives to a given tool and get curated editorial top picks, overall or per category
  • Compare two tools side by side on pricing, deployment, modality and content policy
When to use it
Useful when a user asks for a tool that does something specific, wants to explore AI tools by topic, asks what is similar to or cheaper than a named tool, or wants recommendations of the best tools in a category.
Requirements
A remote streamable HTTP endpoint at thataicollection.com; no packages, environment variables or headers are declared, and no authentication is declared.
Before you install
Results come from a third-party editorial directory, so rankings, curated picks and comparison attributes reflect that source rather than independent testing; verify pricing and policy details before relying on them. Queries are sent to the remote service.

Installation

In SourceWeft

  1. Open AI Collection in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/io.github.kerbelp%2Fai-collection/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config.

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

Tools

7

search_tools

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.

Parameterslimitqueryrequiredcategory

get_tool

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

ParameterslinkNamerequired

list_categories

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

Takes no parameters.

browse_category

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

ParameterslimitoffsetlinkNamerequired

get_alternatives

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.

ParameterslimitlinkNamerequired

get_top_picks

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.

Parameterslimitcategory

compare_tools

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.

ParameterslinkName_arequiredlinkName_brequired

Version history

1
  1. v0.1.0LatestOct 29, 2026

Score

83% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listedRequired15 pts
  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts

    Declare a GitHub repository with a README, or serve resource_documentation in the OAuth protected-resource metadata.

  • LicenseNot applicable

    A hosted service is used under its provider's terms, so no license is expected here. This check is left out of the percentage.