About π Wiki MCP Server
Wiki MCP Server lets teams manage Confluence wiki pages through an MCP server. It supports page edits and keyword search, and infers which Confluence knowledge base to use from the query.
Key features
- 01Create, update, and delete pages
- 02Search pages by keyword
- 03Infer Confluence wiki type from query
- 04Manually specify wiki type
Use cases
- 01Create a page in the selected wiki
- 02Revise or remove an existing page
- 03Find pages matching a keyword
MCP support
Provides MCP tools, prompts, and resources for working with Confluence wiki pages. MCP clients can use it to create, update, delete, and search pages.
Configuration
Local server config is the same for every client. Copy it into your clientβs MCP config file.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEπ Wiki MCP Server
An MCP (Model Context Protocol) Server implementation for managing Confluence wiki pages.
Supports:
- Creating new wiki pages
- Updating existing wiki pages
- Deleting wiki pages
- Searching wiki pages by keyword
- Auto-selecting correct Confluence knowledge base (
alm,wpb, etc.) based on user query
Built with FastAPI, following MCP Server Best Practices, and ready for production deployment.
π Tech Stack
- Python 3.10+
- FastAPI
- MCP SDK
- Requests (for Confluence API interaction)
- ContextVars (for session management)
π¦ Project Structure
wiki_mcp_server/
βββ src/wiki_mcp_server/
β βββ server.py # MCP server entry point
β βββ service.py # Business logic (Confluence API interactions)
β βββ tools.py # MCP tool definitions
β βββ prompts.py # MCP prompt definitions
β βββ resources.py # MCP resource definitions
β βββ utils.py # Helper functions (wiki_type inference etc.)
β βββ utils/session_context.py # Session context manager
β βββ middleware.py # Authentication and session initialization middleware
βββ Dockerfile # Container configuration
βββ requirements.txt # Python dependencies
βββ README.md # Project documentation
βββ smithery.yaml # Smithery integration config (optional)
βββ pyproject.toml # Python project metadata
βοΈ Installation
- Clone the repository:
git clone https://your-repo-url/wiki_mcp_server.git
cd wiki_mcp_server
- Install dependencies:
pip install -r requirements.txt
- (Optional) Configure your environment variables if needed.
π Running Locally
Run the server:
cd src
uvicorn wiki_mcp_server.server:app --host 0.0.0.0 --port 9999 --reload
After startup, you can visit:
- OpenAPI docs (Swagger UI): http://localhost:9999/docs
- ReDoc docs: http://localhost:9999/redoc
π§ͺ Example Request
Headers Required:
| Key | Example Value |
|---|---|
| user_name | [email protected] |
| alm_confluence_base_url | https://your-confluence-site/wiki/rest/api |
| alm_confluence_api_token | your-api-token |
| wpb_confluence_base_url | (optional if available) |
| wpb_confluence_api_token | (optional if available) |
β οΈ If headers are missing or invalid, server will return HTTP 400 error.
Example: Create Page
POST /create_page
{
"space_key": "TEST",
"title": "Test Page Created by MCP Server",
"content": "<p>Hello, World!</p>",
"user_query": "Please create a page in GSNA knowledge base."
}
Behavior:
- Server will infer
wiki_type=almfrom user_query. - Create the page in Confluence and return page metadata.
π§ Auto Inference Logic
- If the query mentions
gsna,global,alm-confluenceβ alm - If the query mentions
wpb,wealthβ wpb - Otherwise default to alm
(You can also manually specify wiki_type in input)
π³ Docker (Optional)
Build and run containerized server:
docker build -t wiki-mcp-server .
docker run -d -p 9999:9999 --name wiki-mcp-server wiki-mcp-server
π License
MIT License.
π Contact
For issues or collaboration requests, please contact:
- Developer: Shawn
- Email: [email protected]
- Project maintained by internal MCP Working Group
---# wiki_mcp_server
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.