Azure Wiki Search Server

What is Azure Wiki Search Server about?

Enables AI agents to perform knowledge lookup on Azure Edge Wiki using two MCP tools: search_wiki for keyword‑based queries and get_wiki_by_path for retrieving full page content.

How to use Azure Wiki Search Server?

1. Clone the repository.
2. Create a virtual environment with uv and activate it.
3. Add the server definition to VS Code’s settings.json or a workspace .vscode/mcp.json file, specifying the absolute path to the cloned folder and optional ORG/PROJECT environment variables.
4. AI agents can invoke the search_wiki or get_wiki_by_path tools defined by the server.

Key Features

• MCP‑compliant: Implements the Model Context Protocol for seamless integration with AI agents.
• Two primary tools:
  • search_wiki – returns relevant wiki entries for a free‑form query.
  • get_wiki_by_path – fetches the full content of a wiki page given its path.
• Configurable organization and project via ORG and PROJECT environment variables (defaults: microsoft and Edge).
• Lightweight Python setup using uv for dependency management.

Use Cases

• Automating internal documentation lookup for developers working on Azure Edge projects.
• Enabling conversational assistants to cite up‑to‑date wiki information.
• Building search‑augmented generation pipelines that source factual context from the Azure wiki.

FAQ

Q: Do I need any special credentials to access the wiki? A: The server uses the public Edge Wiki; no API keys are required.

Q: Can I change the default organization or project? A: Yes, set the ORG and PROJECT environment variables in the MCP server config.

Q: Which Python version is required? A: Python 3.10 or higher.

Q: Is uv mandatory? A: uv is the recommended tool for creating the virtual environment, but any standard Python venv manager can be used.

Azure Wiki Search Server

This mcp server implements the MCP specification to allow AI agents to search on Azure wiki.

Tools

• search_wiki

  Search Edge Wiki to find related material for {query}.

• get_wiki_by_path

  Get wiki content by provided path.

Prerequest

1. Install the latest VS code.

2. Install the GitHub Copilot and GitHub Copilot Chat extensions

3. Install Python 3.10 or higher.

4. Install uv. On Windows

   powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"
   

   On Mac|Linux

   curl -LsSf https://astral.sh/uv/install.sh | sh
   

Local Setup

1. Clone this repo.

   git clone https://github.com/coder-linping/azure-wiki-search-server.git 
   cd azure-wiki-search-server
   

2. Setup env. On Windows

   uv venv
   .venv/Scripts/activate
   

   On Mac | Linux

   uv venv
   source .venv/bin/activate
   

3. Configuration for VS Code

   For manual installation, add the following JSON block to your User Settings (JSON) file in VS Code. You can do this by pressing Ctrl + Shift + P and typing Preferences: Open User Settings (JSON).

   Optionally, you can add it to a file called .vscode/mcp.json in your workspace. This will allow you to share the configuration with others.

     "mcp": {
       "servers": {
         "edge_wiki": {
           "command": "uv",
           "args": [
               "--directory",
               "<absolute path to your cloned folder>",
               "run",
               "src/edge_wiki.py"
           ],
           "env": {
               "ORG": "Your organization，default is microsoft",
               "PROJECT": "Your project, default is Edge"
           },
         }
       }
     }