Unified Docs Hub Server

How to use

You connect an MCP client to Unified Docs Hub to perform fast, full-text searches across the stored documentation. Use the unified_search tool to query by topic, category, or technology and receive results drawn from the curated and discovered repositories. You can also fetch documentation for specific repositories with get_repository_docs to compare APIs, frameworks, and guidelines side by side. When you want a snapshot of the entire knowledge base or statistics about what’s indexed, run get_statistics.

How to install

Prerequisites: Python 3.8 or higher.

Step 1: Clone the project.

git clone https://github.com/yourusername/unified-docs-hub.git
cd unified-docs-hub

Step 2: Set up a Python virtual environment and install dependencies.

python3 -m venv venv
source venv/bin/activate  # On Windows: venv\Scripts\activate
pip install -r requirements.txt

Step 3: Configure your MCP client with the local server details. The server runs via Python and uses a virtual environment.

# Example client configuration path and content
# This is an example; replace with your actual path and values
{
  "mcpServers": {
    "unified_docs_hub": {
      "command": "/path/to/unified-docs-hub/venv/bin/python",
      "args": ["/path/to/unified-docs-hub/unified_docs_hub_server.py"],
      "env": {
        "GITHUB_TOKEN": "your-github-token-here"
      }
    }
  }
}

Step 4: Run initial indexing (optional; server can index automatically on first start).

# Index all curated repositories
python -c "import asyncio; from unified_docs_hub_server import index_repositories; asyncio.run(index_repositories('smart'))"

Additional setup notes

The server supports automated updates to keep the knowledge base fresh, including daily indexing of curated repositories and weekly discovery of new repositories. You can control indexing with the available MCP tools described in the Tools section.

Configuration and security

The config snippet shown above exposes a GitHub token to the server environment. Treat tokens as sensitive credentials and limit their scope. Store tokens securely and rotate them regularly. If you use automated updates, ensure the updater runs with appropriate permissions and network access.

Examples and guidance

Search examples show how to retrieve documentation quickly across domains. For instance, you can search for trading and finance topics, Kubernetes deployment strategies, or machine learning pipelines, and then open the most relevant docs from the results.

Troubleshooting

If indexing or searches fail, check that the virtual environment is activated, the Python path to unified_docs_hub_server.py is correct, and the GITHUB_TOKEN (if used) is valid. Review logs for rate-limit messages from the GitHub API and adjust token scope or throttling as needed.

unified_search

Search across all indexed documentation with optional filters such as category and minimum stars to refine results.

index_repositories

Control which repositories are indexed, including smart discovery of popular repos and updates to existing entries.

list_repositories

Browse indexed repositories by category or source (curated vs discovered).

get_repository_docs

Retrieve all documentation for a specific repository to compare docs side by side.

get_statistics

Return database statistics including total repos, documents, categories, and languages.