agent-web-search-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., "@agent-web-search-mcp search the web for the latest stable version of Python"
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.
agent-web-search-mcp
Standalone Model Context Protocol (MCP) server for the agent-web-search API.
A thin stdio wrapper — it just calls the API over HTTP and formats results for any MCP-compatible agent (Claude Desktop, Cursor, Pi, etc.).
This package is a client of the
agent-web-searchengine, not the engine itself. You need a running instance of the engine (see below) before the MCP can do anything.
Install
uv tool install git+https://github.com/blueewhitee/agent-web-search-mcpRelated MCP server: groundlink-mcp
Configure your MCP client
Add this to your MCP config (e.g. ~/.pi/agent/mcp.json for Pi,
claude_desktop_config.json for Claude Desktop):
{
"mcpServers": {
"agent-web-search": {
"command": "agent-web-search-mcp",
"env": {
"AGENT_WEB_SEARCH_API_URL": "http://localhost:8000"
}
}
}
}AGENT_WEB_SEARCH_API_URL defaults to http://localhost:8000 — set it to wherever your
engine is reachable.
What you get
A single tool, web_search, that:
routes the query to the engine's intent detector (code / news / general),
fetches + extracts + ranks results,
returns ranked chunks with scores and source URLs.
Requirements
A running
agent-web-searchengine (the FastAPI service from the agent-web-search repo). Easiest path: clone that repo anddocker compose up.Python ≥ 3.12.
Development
git clone https://github.com/blueewhitee/agent-web-search-mcp
cd agent-web-search-mcp
uv tool install --editable .The agent-web-search-mcp command will then reflect local changes on restart.
License
MIT (same as the engine).
Available Tools
1 toolweb_searchARead-onlyIdempotent
Search the web and return ranked, content-rich results.
Queries multiple search engines, fetches full page content, extracts clean text, scrubs prompt injections, chunks by semantic boundaries, and ranks chunks by cosine similarity to the query.
Use this when the user asks about current information, facts, documentation, or anything that requires up-to-date web results.
Returns markdown-formatted ranked chunks with cosine similarity scores, source URLs, and surrounding parent context for each chunk.
Inputs: params (required). 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 zero chance of selecting the wrong tool. The tool's purpose is clearly defined as web search.
The single tool name 'web_search' follows a clear verb_noun pattern, but there are no other tools to compare consistency.
The server has only one tool, which falls below the typical minimum for a useful server. While search can be a single operation, the rubric considers 1 tool too few.
For the stated purpose of web search, the tool provides comprehensive functionality including content fetching and ranking. There are no obvious missing operations within its scope.
Maintenance
Related MCP Connectors
Scrape, crawl and search the web for AI agents via MCP.
Provides AI assistants with access to Seltz's powerful Web Search capabilities.
Web search API and MCP server for developers building AI agents.
Free web search for AI agents. No API key required. Hosted MCP in active development.
Related MCP Servers
- AlicenseNot gradedqualityBmaintenanceEnables AI agents to perform web searches with full content retrieval and multi-engine provenance, including trust scoring and local corpus persistence, via MCP integration.8 npm4Apache 2.0
- AlicenseAqualityCmaintenanceEnables MCP hosts to perform cited web searches and receive source-bearing results with titles, URLs, snippets, and sources for evidence-grounded answers.139 npmMIT
- AlicenseBqualityBmaintenanceEnables AI agents to perform web searches and extract full-text content from web pages via standard MCP tools, with fallback search and semantic reranking.22MIT
- AlicenseAqualityBmaintenanceEnables any MCP-compatible AI client to search the live web via Google's Custom Search JSON API, returning top results with titles, links, and snippets.11MIT