avr-docs-mcp
About
This MCP (Model Context Protocol) server provides integration with Wiki.JS for searching and listing pages from Agent Voice Response Wiki.JS instance.
Details
- Author
- agentvoiceresponse
- Categories
- Search, Other, Knowledge Base
Jump to
Option 2: Using system environment variables
export WIKI_JS_BASE_URL="https://your-wiki-instance.com" export WIKI_JS_API_KEY="your-api-key-here" export LOG_LEVEL="info" export MCP_MODE="stdio" export PORT="3000"
The server supports two modes of operation:
The server runs in stdio mode by default, communicating through standard input/output. This is the traditional MCP mode.
npm start # or npm run start:http # for HTTP mode # or MCP_MODE=stdio npm start
The server can also run in HTTP mode, providing a REST API with Server-Sent Events (SSE) for MCP communication.
npm run start:http # or MCP_MODE=http npm start
When running in HTTP mode, the server provides:
- Health Check:GET /health- Returns server status
- MCP Endpoint:POST /mcp- MCP communication endpoint using JSON-RPC 2.0
You can test the HTTP mode using curl or Postman:
# Health check curl http://localhost:3000/health # Initialize MCP session curl -X POST http://localhost:3000/mcp \ -H "Content-Type: application/json" \ -d '{ "jsonrpc": "2.0", "id": 1, "method": "initialize", "params": { "protocolVersion": "2024-11-05", "capabilities": {}, "clientInfo": { "name": "curl-client", "version": "1.0.0" } } }' # List available tools (use session ID from initialize response) curl -X POST http://localhost:3000/mcp \ -H "Content-Type: application/json" \ -H "mcp-session-id: <session-id-from-initialize>" \ -d '{"jsonrpc": "2.0", "id": 2, "method": "tools/list"}' # Call a tool (use session ID from initialize response) curl -X POST http://localhost:3000/mcp \ -H "Content-Type: application/json" \ -H "mcp-session-id: <session-id-from-initialize>" \ -d '{ "jsonrpc": "2.0", "id": 3, "method": "tools/call", "params": { "name": "search_wiki_pages", "arguments": { "query": "deepgram", "page": 1, "limit": 10 } } }'
# Run in stdio mode (default) docker run -d \ --name avr-docs-mcp \ -e WIKI_JS_BASE_URL="https://your-wiki-instance.com" \ -e WIKI_JS_API_KEY="your-api-key-here" \ agentvoiceresponse/avr-docs-mcp:latest # Run in HTTP mode docker run -d \ --name avr-docs-mcp \ -p 3000:3000 \ -e WIKI_JS_BASE_URL="https://your-wiki-instance.com" \ -e WIKI_JS_API_KEY="your-api-key-here" \ -e MCP_MODE="http" \ -e PORT="3000" \ agentvoiceresponse/avr-docs-mcp:latest
version: '3.8' services: avr-docs-mcp: image: agentvoiceresponse/avr-docs-mcp:latest container_name: avr-docs-mcp ports: - "3000:3000" # Only needed for HTTP mode environment: - WIKI_JS_BASE_URL=https://your-wiki-instance.com - WIKI_JS_API_KEY=your-api-key-here - MCP_MODE=http - PORT=3000 - LOG_LEVEL=info restart: unless-stopped healthcheck: test: ["CMD", "curl", "-f", "http://localhost:3000/health"] interval: 30s timeout: 10s retries: 3
Search for pages in Wiki.JS using keywords.
- query(required): The search query
- page(optional): Page number for pagination (default: 1)
- limit(optional): Number of results per page (default: 10, max: 50)
- page(optional): Page number for pagination (default: 1)
- limit(optional): Number of results per page (default: 20, max: 50)
- pageId(required): The ID (numeric) or path (string) of the page to retrieve. Examples: '3' for ID, 'deepgram' for path
This MCP server uses Wiki.JS GraphQL API (/graphqlendpoint). Make sure your Wiki.JS instance has API access enabled and that your API key has the following permissions:
- page:read- To read page content
- page:list- To list pages
- search:read- To search pages
The server automatically handles GraphQL queries and responses for all operations. Note that Wiki.JS GraphQL API has some limitations:
- Search and list operations don't support native pagination, so pagination is simulated client-side
- Search results don't include full page content
- List results don't include full page content (useget_wiki_pagefor full content)
- Tags are returned as arrays of strings, not comma-separated strings
The server includes comprehensive logging with configurable log levels:
- debug- Detailed debug information
- info- General information (default)
- warn- Warning messages only
- error- Error messages only
Set theLOG_LEVELenvironment variable to control logging verbosity.
The server includes comprehensive error handling for:
- Missing environment variables
- Network connectivity issues
- API authentication failures
- Invalid page IDs
- Rate limiting
To run in development mode with hot reloading:
The compiled JavaScript will be in thedist/directory.
- GitHub:https://github.com/agentvoiceresponse- Report issues, contribute code.
- Discord:https://discord.gg/DFTU69Hg74- Join the community discussion.
- Docker Hub:https://hub.docker.com/u/agentvoiceresponse- Find Docker images.
- Wiki:https://wiki.agentvoiceresponse.com/en/home- Project documentation and guides.
AVR is free and open-source. Any support is entirely voluntary and intended as a personal gesture of appreciation. Donations do not provide access to features, services, or special benefits, and the project remains fully available regardless of donations.
MIT License - see theLICENSEfile for details.
Search global news using natural language. Webz.io News Search API returns the most relevant articles and content, with filters for source, country, language, date, sentiment, and category.
Fetch, convert, and search AWS documentation pages, with recommendations for related content.
Production-ready RAG out of the box to search and retrieve data from your own documents.
Quran-focused MCP server for ayah translation, tafsir, mutashabihat lookups, recitation playlists, and prayer times.
Vectorize MCP server for advanced retrieval, Private Deep Research, Anything-to-Markdown file extraction and text chunking.
Provides AI assistants with intelligent access to ML textbook content for creating accurate, source-grounded documentation.
一条工務店で家を建てた施主「ろれさん」のブログ記事と、YouTube/X/Instagram/Web から集めた約3,000件の家づくり Tips を横断検索できる MCP サーバ。すべての結果に出典URLが付きます。
A flexible service for searching and analyzing academic papers on arXiv.
A local server to query Bucketeer documentation, which automatically fetches and caches content from its GitHub repository.
Caesar is a free, keyless web search API for AI agents. Its remote MCP server exposes web_search (ranked results with citable provenance) and web_fetch (full pages as clean markdown), and works anonymously with no API key.
CatchAll is a web search API built for comprehensive event retrieval — not ranked results, but all matching records.
AVR Docs MCP Server with Wiki.JS Integration
This MCP (Model Context Protocol) server provides integration with Wiki.JS for searching and listing pages from your Wiki.JS instance.
- Search Wiki.JS Pages: Search for pages using keywords or topics
- List Wiki.JS Pages: Get a paginated list of all available pages
- Get Specific Page: Retrieve a specific page by its ID
- Connection Testing: Test the connection to your Wiki.JS instance
- Multiple Transport Modes: Support for both stdio and HTTP stream modes
- Docker Support: Ready-to-use Docker image with health checks
- A running Wiki.JS instance
- An API key with appropriate permissions for reading pages
You can set environment variables in two ways:
Option 1: Using a .env file (Recommended)
- Edit the.envfile with your actual values:
# Wiki.JS Configuration WIKI_JS_BASE_URL=https://your-wiki-instance.com WIKI_JS_API_KEY=your-api-key-here LOG_LEVEL=info # MCP Server Configuration MCP_MODE=stdio PORT=3000
Option 2: Using system environment variables
export WIKI_JS_BASE_URL="https://your-wiki-instance.com" export WIKI_JS_API_KEY="your-api-key-here" export LOG_LEVEL="info" export MCP_MODE="stdio" export PORT="3000"
The server supports two modes of operation:
The server runs in stdio mode by default, communicating through standard input/output. This is the traditional MCP mode.
npm start # or npm run start:http # for HTTP mode # or MCP_MODE=stdio npm start
The server can also run in HTTP mode, providing a REST API with Server-Sent Events (SSE) for MCP communication.
npm run start:http # or MCP_MODE=http npm start
When running in HTTP mode, the server provides:
- Health Check:GET /health- Returns server status
- MCP Endpoint:POST /mcp- MCP communication endpoint using JSON-RPC 2.0
You can test the HTTP mode using curl or Postman:
# Health check curl http://localhost:3000/health # Initialize MCP session curl -X POST http://localhost:3000/mcp \ -H "Content-Type: application/json" \ -d '{ "jsonrpc": "2.0", "id": 1, "method": "initialize", "params": { "protocolVersion": "2024-11-05", "capabilities": {}, "clientInfo": { "name": "curl-client", "version": "1.0.0" } } }' # List available tools (use session ID from initialize response) curl -X POST http://localhost:3000/mcp \ -H "Content-Type: application/json" \ -H "mcp-session-id: <session-id-from-initialize>" \ -d '{"jsonrpc": "2.0", "id": 2, "method": "tools/list"}' # Call a tool (use session ID from initialize response) curl -X POST http://localhost:3000/mcp \ -H "Content-Type: application/json" \ -H "mcp-session-id: <session-id-from-initialize>" \ -d '{ "jsonrpc": "2.0", "id": 3, "method": "tools/call", "params": { "name": "search_wiki_pages", "arguments": { "query": "deepgram", "page": 1, "limit": 10 } } }'
# Run in stdio mode (default) docker run -d \ --name avr-docs-mcp \ -e WIKI_JS_BASE_URL="https://your-wiki-instance.com" \ -e WIKI_JS_API_KEY="your-api-key-here" \ agentvoiceresponse/avr-docs-mcp:latest # Run in HTTP mode docker run -d \ --name avr-docs-mcp \ -p 3000:3000 \ -e WIKI_JS_BASE_URL="https://your-wiki-instance.com" \ -e WIKI_JS_API_KEY="your-api-key-here" \ -e MCP_MODE="http" \ -e PORT="3000" \ agentvoiceresponse/avr-docs-mcp:latest
version: '3.8' services: avr-docs-mcp: image: agentvoiceresponse/avr-docs-mcp:latest container_name: avr-docs-mcp ports: - "3000:3000" # Only needed for HTTP mode environment: - WIKI_JS_BASE_URL=https://your-wiki-instance.com - WIKI_JS_API_KEY=your-api-key-here - MCP_MODE=http - PORT=3000 - LOG_LEVEL=info restart: unless-stopped healthcheck: test: ["CMD", "curl", "-f", "http://localhost:3000/health"] interval: 30s timeout: 10s retries: 3
Search for pages in Wiki.JS using keywords.
- query(required): The search query
- page(optional): Page number for pagination (default: 1)
- limit(optional): Number of results per page (default: 10, max: 50)
- page(optional): Page number for pagination (default: 1)
- limit(optional): Number of results per page (default: 20, max: 50)
- pageId(required): The ID (numeric) or path (string) of the page to retrieve. Examples: '3' for ID, 'deepgram' for path
This MCP server uses Wiki.JS GraphQL API (/graphqlendpoint). Make sure your Wiki.JS instance has API access enabled and that your API key has the following permissions:
- page:read- To read page content
- page:list- To list pages
- search:read- To search pages
The server automatically handles GraphQL queries and responses for all operations. Note that Wiki.JS GraphQL API has some limitations:
- Search and list operations don't support native pagination, so pagination is simulated client-side
- Search results don't include full page content
- List results don't include full page content (useget_wiki_pagefor full content)
- Tags are returned as arrays of strings, not comma-separated strings
The server includes comprehensive logging with configurable log levels:
- debug- Detailed debug information
- info- General information (default)
- warn- Warning messages only
- error- Error messages only
Set theLOG_LEVELenvironment variable to control logging verbosity.
The server includes comprehensive error handling for:
- Missing environment variables
- Network connectivity issues
- API authentication failures
- Invalid page IDs
- Rate limiting
To run in development mode with hot reloading:
The compiled JavaScript will be in thedist/directory.
- GitHub:https://github.com/agentvoiceresponse- Report issues, contribute code.
- Discord:https://discord.gg/DFTU69Hg74- Join the community discussion.
- Docker Hub:https://hub.docker.com/u/agentvoiceresponse- Find Docker images.
- Wiki:https://wiki.agentvoiceresponse.com/en/home- Project documentation and guides.
AVR is free and open-source. Any support is entirely voluntary and intended as a personal gesture of appreciation. Donations do not provide access to features, services, or special benefits, and the project remains fully available regardless of donations.
MIT License - see theLICENSEfile for details.
Search global news using natural language. Webz.io News Search API returns the most relevant articles and content, with filters for source, country, language, date, sentiment, and category.
Fetch, convert, and search AWS documentation pages, with recommendations for related content.
Production-ready RAG out of the box to search and retrieve data from your own documents.
Quran-focused MCP server for ayah translation, tafsir, mutashabihat lookups, recitation playlists, and prayer times.
Vectorize MCP server for advanced retrieval, Private Deep Research, Anything-to-Markdown file extraction and text chunking.
Provides AI assistants with intelligent access to ML textbook content for creating accurate, source-grounded documentation.
一条工務店で家を建てた施主「ろれさん」のブログ記事と、YouTube/X/Instagram/Web から集めた約3,000件の家づくり Tips を横断検索できる MCP サーバ。すべての結果に出典URLが付きます。
A flexible service for searching and analyzing academic papers on arXiv.
A local server to query Bucketeer documentation, which automatically fetches and caches content from its GitHub repository.
Caesar is a free, keyless web search API for AI agents. Its remote MCP server exposes web_search (ranked results with citable provenance) and web_fetch (full pages as clean markdown), and works anonymously with no API key.
CatchAll is a web search API built for comprehensive event retrieval — not ranked results, but all matching records.
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.




