yacy-mcp
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@yacy-mcp search for recent articles about climate change"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
YaCy MCP Server
MCP (Model Context Protocol) Server implementation that provides AI tools to search using YaCy web search API.
Installation
Make sure you have
uvinstalled:
pip install uvInstall the package in development mode:
cd yacy-mcp
uv sync # Sync all dependencies from pyproject.toml and uv.lockOr alternatively:
cd yacy-mcp
uv pip install -e .Related MCP server: MCP WebScout
Usage
Make sure you have a YaCy server running (typically on http://localhost:8090)
Set environment variables (optional):
export YACY_URL=http://localhost:8090Run the MCP server:
python -m yacy_mcpConfiguration
The server can be configured using environment variables:
YACY_URL: URL of your YaCy instance (default: http://localhost:8090)
Available Tools
yacy-search: Search using YaCy web search engineParameters:
query(string, required): Search query stringmax_results(integer, optional): Maximum number of results to return (default: 10)resource(string, optional): Search resource (local or global, default: global)
MCP Configuration for AI Applications
To use this server with AI applications that support the Model Context Protocol (MCP), configure your MCP client to connect to the server using stdio transport.
Example configuration for Claude Desktop (settings.json):
{
"mcpServers": {
"yacy-mcp": {
"command": "uvx",
"args": ["yacy_mcp"],
"env": {
"YACY_URL": "http://localhost:8090"
}
}
}
}For other MCP-compatible applications, use the command uvx yacy_mcp as the server executable. The server will be automatically fetched and run from PyPI.
Integration with AI Applications
This MCP server can be used with AI applications that support the Model Context Protocol to perform web searches using the YaCy search engine.
Available Tools
1 toolyacy_searchA
Search using YaCy web search engine.
Args: query: Search query string max_results: Maximum number of results to return (default: 10) resource: Search resource (local or global, default: global)
Inputs: query (required), resource, max_results. Returns: result
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 1 tool
Only one tool exists, so there is no possibility of confusion between tools. The tool's purpose is clearly defined as a web search operation.
The single tool name 'yacy_search' is descriptive and follows a verb-like pattern, but with only one tool there is no pattern to compare against for consistency.
A single search tool is too few for a full-featured MCP server, even one focused on a single search engine. Users would expect additional capabilities like managing resources or getting engine status.
The search tool provides the core search functionality, but lacks any supporting operations such as retrieving specific results, filtering, or examining engine state. This leaves significant gaps for agents that might need more than a basic search.
Maintenance
Related MCP Connectors
Provides AI assistants with access to Seltz's powerful Web Search capabilities.
Scrape, crawl and search the web for AI agents via MCP.
Free web search for AI agents. No API key required. Hosted MCP in active development.
Web search API and MCP server for developers building AI agents.
Related MCP Servers
- AlicenseBqualityDmaintenanceProvides web search capabilities using Google Custom Search API, enabling users to perform searches through a Model Context Protocol server.271MIT
- AlicenseNot gradedqualityDmaintenanceA Model Context Protocol server that provides web search capabilities via DuckDuckGo and advanced content extraction using Crawl4AI and LLM-powered analysis. It enables users to perform web-wide searches and fetch processed website data through automated browser interaction and intelligent summarization.2MIT
- AlicenseAqualityDmaintenanceProvides a bridge between AI assistants and SearXNG, a privacy-respecting metasearch engine, enabling web searches and engine discovery via the Model Context Protocol.230 npm2Apache 2.0
- FlicenseNot gradedqualityDmaintenanceEnables Yandex search with advanced content extraction, analysis, and LLM-context formatting through a Model Context Protocol server.4-