Skip to main content
Glama
Dedalus MCP Documentation Server

Dedalus MCP Documentation Server

by kitan23

Dedalus MCP Documentation Server

An MCP server for serving and querying documentation with AI capabilities. Built for the YC Agents Hackathon.

Quick Start (Local Development)

# Install uv package manager (same as Dedalus uses)
brew install uv  # or pip install uv

# Install dependencies
uv sync --no-dev

# Configure API keys for AI features
cp config/.env.example .env.local
# Edit .env.local and add your OpenAI API key

# Test
uv run python tests/test_server.py

# Run
uv run main

Related MCP server: Dedalus MCP Documentation Server

Deploy to Dedalus

What Dedalus Needs

  • pyproject.toml - Package configuration with dependencies

  • main.py (root) - Entry point that Dedalus expects

  • src/main.py - The actual MCP server code

  • docs/ - Your documentation files

Deployment Steps

  1. Set Environment Variables in Dedalus UI:

    • OPENAI_API_KEY - Your OpenAI API key (required for AI features)

  2. Deploy:

dedalus deploy . --name "your-docs-server"

How Dedalus Runs Your Server

  1. Installs dependencies using uv sync from pyproject.toml

  2. Runs uv run main to start the server

  3. Server runs in /app directory in container

  4. Docs are served from /app/docs

Features

  • Serve markdown documentation

  • Search across docs

  • AI-powered Q&A (with OpenAI)

  • Rate limiting (10 requests/minute) to protect API keys

  • Ready for agent handoffs

Tools Available

  • list_docs() - List documentation files

  • search_docs() - Search with keywords

  • ask_docs() - AI answers from docs

  • index_docs() - Index documents

  • analyze_docs() - Analyze for tasks

Documentation

See docs/ directory for:

License

MIT

Available Tools

5 tools
analyze_docsC
Analyze documentation for specific tasks (foundation for agent handoffs)

Args:
    task: Analysis task (e.g., "find_gaps", "generate_outline", "check_consistency")
    docs: Optional list of specific documents to analyze
    output_format: Output format (summary, detailed, structured)

Returns:
    Analysis results ready for agent handoff

Inputs: task (required), docs, output_format. Returns: result

ask_docsC
Answer questions about documentation using AI

Args:
    question: The question to answer
    context_docs: Optional list of document paths to use as context
    max_context_length: Maximum characters of context to include
    user_id: Optional user identifier for rate limiting

Returns:
    AI-generated answer with sources

Inputs: question (required), context_docs, max_context_length, user_id. Returns: result

index_docsB
Index or re-index all documentation for improved search

Args:
    rebuild: Whether to rebuild the entire index from scratch

Returns:
    Indexing statistics

Inputs: rebuild. Returns: result

list_docsB
List all available documentation files

Args:
    directory: Optional subdirectory to list (relative to docs root)

Returns:
    List of document metadata

Inputs: directory. Returns: result

search_docsA
Search documentation using keyword matching (semantic search ready)

Args:
    query: Search query string
    max_results: Maximum number of results to return
    search_content: Whether to search in document content
    search_titles: Whether to search in document titles

Returns:
    List of matching documents with relevance scores

Inputs: query (required), max_results, search_content, search_titles. Returns: result

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A3.6/5.0

    Scored across 5 tools

    Disambiguation5/5

    Each tool has a clearly distinct purpose with no overlap: analyze_docs performs analysis tasks, ask_docs answers questions via AI, index_docs handles indexing, list_docs enumerates files, and search_docs performs keyword searches. The descriptions reinforce these distinct roles, making tool selection unambiguous for an agent.

    Naming Consistency5/5

    All tools follow a consistent verb_noun pattern with snake_case naming (e.g., analyze_docs, ask_docs, index_docs, list_docs, search_docs). This predictable structure enhances readability and usability, with no deviations or mixed conventions across the set.

    Tool Count5/5

    With 5 tools, this server is well-scoped for documentation management, covering core operations like listing, searching, indexing, analyzing, and querying. Each tool earns its place without redundancy, making the count appropriate for the domain's typical workflows.

    Completeness5/5

    The tool set provides complete coverage for documentation management, including CRUD-like operations (list, search, index) and advanced AI functionalities (analyze, ask). There are no obvious gaps; agents can perform end-to-end tasks from discovery to analysis without dead ends.

    Maintenance

    ActivityInactive
    ResponsivenessOutdated data

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      Not graded
      maintenance
      Enables serving and querying documentation with AI capabilities, allowing users to search, ask questions, and get AI-powered answers from their documentation files. Built for seamless deployment on the Dedalus platform with OpenAI integration for enhanced document analysis.
      MIT
    • A
      license
      Not graded
      quality
      Not graded
      maintenance
      Enables AI-powered querying and serving of markdown documentation with search, Q\&A capabilities, and document analysis. Built for the YC Agents Hackathon with OpenAI integration and rate limiting protection.
      MIT
    • A
      license
      A
      quality
      C
      maintenance
      Enables AI assistants to navigate and query hierarchical documentation structures, supporting markdown files with YAML metadata and OpenAPI 3.x specifications. It features intelligent full-text search, metadata filtering, and a built-in web interface for both human and AI-driven documentation access.
      6
      MIT