Search Azure DevOps Wiki Content
The Azure Wiki Search MCP server lets AI agents search Azure DevOps wiki content and fetch specific wiki pages by path directly from VS Code.
Why it matters
Enable AI agents to efficiently search and retrieve information directly from Azure DevOps Wiki. This connector allows for seamless integration with tools like GitHub Copilot for enhanced knowledge discovery.
Outcomes
What it gets done
Search Azure DevOps Wiki using natural language queries.
Retrieve specific wiki pages by their path.
Integrate with VS Code and GitHub Copilot for contextual information retrieval.
Install
Add it to your toolbox
Run in your project directory:
curl -fsSL https://spark.entire.vc/get/vb-azure-wiki-search | bash Capabilities
Tools your agent gets
Search Edge Wiki to find related materials for a given query
Retrieve wiki content by the specified path
Overview
Azure Wiki Search MCP Server
This MCP server exposes two tools, search_wiki and get_wiki_by_path, letting an AI assistant like GitHub Copilot Chat search and retrieve content from an Azure DevOps wiki directly from VS Code. Use it when your AI assistant needs to look up or fetch documentation from your team's Azure DevOps wiki. It only covers Azure DevOps wikis, scoped to the organization and project set in its configuration.
What it does
The Azure Wiki Search Server is an MCP server implementing the MCP specification so AI agents (such as GitHub Copilot Chat in VS Code) can search an Azure wiki and retrieve wiki content directly. It exposes two tools: search_wiki, which searches the Edge Wiki to find material related to a query, and get_wiki_by_path, which fetches wiki content for a given path.
When to use - and when NOT to
Use it when an AI coding assistant needs to look up documentation stored in an Azure DevOps wiki (for example, an internal Edge/Microsoft-org wiki) without leaving the editor - searching for relevant pages by keyword or pulling a specific page's content by its path. It is not a general web search tool and does not cover wikis outside Azure DevOps; it is scoped specifically to the wiki of the configured organization and project.
Inputs and outputs
Input is a search query (for search_wiki) or a wiki path (for get_wiki_by_path). Output is the matching wiki search results or the raw wiki page content for the requested path.
How to install
Requires VS Code with the GitHub Copilot and GitHub Copilot Chat extensions, Python 3.10 or higher, and uv. Clone the repository, create and activate a virtual environment with uv venv, then register the server in VS Code's user settings (JSON) or a workspace .vscode/mcp.json file:
{
"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"
}
}
}
}
}
Who it's for
Developers using GitHub Copilot Chat (or another MCP-compatible AI assistant) in VS Code who need quick, in-editor access to their team's Azure DevOps wiki documentation.
Source README
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
Install the latest VS code.
Install the GitHub Copilot and GitHub Copilot Chat extensions
Install Python 3.10 or higher.
Install uv.
On Windowspowershell -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
Clone this repo.
git clone https://github.com/coder-linping/azure-wiki-search-server.git cd azure-wiki-search-serverSetup env.
On Windowsuv venv .venv/Scripts/activateOn Mac | Linux
uv venv source .venv/bin/activateConfiguration 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" }, } } }
FAQ
Common questions
Discussion
Questions & comments · 0
Sign In Sign in to leave a comment.
