A
licenseB
qualityD
maintenanceProvides web search capabilities using Google Custom Search API, enabling users to perform searches through a Model Context Protocol server.
2
219 npm
68
MIT
yacy-mcp
by koosty
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-mcpsearch 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 Google Server
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)
ParametersJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | ||
| resource | No | global | |
| max_results | No |
Output Schema
ParametersJSON Schema
| Name | Required | Description |
|---|---|---|
| result | Yes |
TDQS
A4.4/5.0
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It discloses the main behavior (search) and parameter defaults (max_results, resource), but does not add additional behavioral context such as return format, error handling, network requirements, or rate limits. The output schema covers return values, but other traits are not mentioned.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a succinct single-sentence purpose followed by a structured Args list. Every sentence earns its place; there is no fluff. The format is front-loaded with the primary action.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness5/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple search tool with three parameters (one required), the description fully covers all parameters and defaults. The output schema exists, so return values are documented externally. There are no siblings or complex edge cases, making the description complete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters5/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema has 0% description coverage, meaning parameter titles only. The description compensates by providing a clear Args list with explanations for query, max_results (with default), and resource (with default). This adds significant meaning beyond the raw schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states 'Search using YaCy web search engine', which is a specific verb ('Search') and resource ('YaCy web search engine'). It is concise and directly indicates what the tool does. Since there are no sibling tools, there is no need for differentiation.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides clear context on when to use the tool: when a search against the YaCy web search engine is needed. It does not explicitly mention alternatives (none exist in the sibling list) or exclusions, but the context is unambiguous for a search tool.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
1 tool update
v0.1.0- First observed
yacy_search
TDQS
A4.1/5.0
Scored across 1 tool
Disambiguation5/5
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.
Naming Consistency4/5
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.
Tool Count2/5
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.
Completeness2/5
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
ActivityInactive
ResponsivenessNo issues
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.
Search remote Model Context Protocol servers and tools discovered by BuiltWith, without an API key.
Independent web search index for AI agents. Fast structured results via MCP and API.
Related MCP Servers
- AlicenseBqualityDmaintenanceA Model Context Protocol server providing web search capabilities using Google Custom Search API and webpage content extraction functionality.2MIT
- 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
- AlicenseAqualityCmaintenanceProvides a bridge between AI assistants and SearXNG, a privacy-respecting metasearch engine, enabling web searches and engine discovery via the Model Context Protocol.224 npm1Apache 2.0