Azure Wiki Search

What is Azure Wiki Search Server?

Azure Wiki Search Server is an MCP (Multi-Agent Communication Protocol) server that enables AI agents to search and retrieve information from Azure DevOps wikis. It implements the MCP specification, allowing seamless integration with AI systems for knowledge retrieval.

How to use Azure Wiki Search Server?

To use Azure Wiki Search Server, you need to set up the server locally and configure it within your development environment, such as VS Code.

Prerequisites:

1. Install the latest VS Code.
2. Install GitHub Copilot and GitHub Copilot Chat extensions.
3. Install Python 3.10 or higher.
4. Install uv (a Python package installer and dependency resolver).
5. Prepare a Personal Access Token (PAT) with read permissions for your Azure DevOps wiki.

Local Setup:

1. Clone the repository: git clone https://github.com/coder-linping/azure-wiki-search-server.git
2. Navigate to the project directory: cd azure-wiki-search-server
3. Set up a virtual environment using uv:
   • Windows: uv venv then .venv\Scripts\activate
   • Mac/Linux: uv venv then source .venv/bin/activate
4. Configure VS Code by adding the provided JSON block to your User Settings (JSON) or a .vscode/mcp.json file in your workspace. This configuration specifies the command to run the server and environment variables for your PAT, organization, and project.

Once set up, AI agents can interact with the server to perform search queries on the Azure wiki.

Key Features of Azure Wiki Search Server

• MCP Specification Implementation: Adheres to the Multi-Agent Communication Protocol for interoperability with AI agents.
• Wiki Search Capability: Allows AI agents to search for related materials within Azure DevOps wikis using a search_wiki tool.
• Wiki Content Retrieval: Provides a get_wiki_by_path tool to retrieve specific wiki content by its path.
• Configurable: Supports configuration of Personal Access Tokens, Azure DevOps organization, and project for targeted wiki access.
• Local Deployment: Can be easily set up and run locally for development and testing.

Use Cases of Azure Wiki Search Server

• AI-powered Knowledge Retrieval: AI agents can quickly find relevant information within an organization's Azure DevOps wiki for answering questions, providing context, or assisting with tasks.
• Automated Documentation Access: Integrate with AI workflows to automatically pull documentation from Azure wikis for various purposes.
• Enhanced Developer Productivity: Developers using AI assistants can leverage this server to get instant access to project-specific wiki content without leaving their development environment.
• Chatbot Integration: Power chatbots with the ability to search and retrieve information from internal Azure wikis to provide more comprehensive answers to user queries.

FAQ about Azure Wiki Search Server

Q: What is an MCP server? A: An MCP (Multi-Agent Communication Protocol) server is a component that implements a standard protocol for AI agents to communicate and interact with external services, in this case, an Azure wiki.

Q: What permissions does the Personal Access Token (PAT) need? A: The PAT needs to have read permissions for the Azure DevOps wiki you intend to search.

Q: Can I use this with other wiki platforms? A: This specific server is designed for Azure DevOps wikis. Its functionality is tied to the Azure Wiki API.

Q: How do I specify which Azure DevOps organization and project to search? A: You configure the ORG and PROJECT environment variables in the mcp settings within your VS Code configuration.

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
   

5. Prepare a Personal Access Token and make sure it has permission to read wiki.

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": {
               "PAT": "Your personal access token",
               "ORG": "Your organization，default is microsoft",
               "PROJECT": "Your project, default is Edge"
           },
         }
       }
     }