F
licenseB
qualityD
maintenanceEnables web search capabilities through the Tavily API. Allows users to search the web for information using natural language queries via the MCP protocol.
4
1
-
agent-web-search-mcp
by blueewhitee
Click on "Install 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-mcpsearch 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: DeepSearch 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.
ParametersJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| params | Yes |
Output Schema
ParametersJSON Schema
| Name | Required | Description |
|---|---|---|
| result | Yes |
TDQS
A4.6/5.0
Behavior5/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description discloses substantial behavioral details beyond the annotations: it queries multiple engines, fetches full page content, scrubs prompt injections, chunks by semantic boundaries, and ranks by cosine similarity. This gives the agent a realistic expectation of processing scope and security measures, far exceeding the minimal readOnly/idempotent hints from annotations.
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 efficiently structured: a one-sentence purpose statement, a compact process overview, a clear usage trigger, and a concise return-format note. No word is wasted, and it is appropriately 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?
Despite the tool's complexity, the description covers the core function, internal processing steps, usage context, and output structure. The presence of an output schema further fills in return details, so the description is complete enough for an agent to select and invoke the tool confidently.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description does not explicitly mention the 'query' or 'render_js' parameters, despite schema description coverage being 0%. While the schema itself provides robust descriptions, the fail here is that the tool description adds no direct value for parameter selection, failing to compensate for the low coverage as required.
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 opens with 'Search the web and return ranked, content-rich results,' which clearly specifies the verb (search), resource (web), and output format (ranked results). It further details the multi-step process, making it unambiguous and distinguishing it from generic search tools.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines5/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explicitly states when to use the tool: 'Use this when the user asks about current information, facts, documentation, or anything that requires up-to-date web results.' This provides clear, actionable guidance for an AI agent, even without sibling tools to compare against.
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. Dates show when Glama detected each change.
1 tool update
v0.1.0- First observed
web_search
TDQS
A4.5/5.0
Disambiguation5/5
Only one tool exists, so there is zero chance of selecting the wrong tool. The tool's purpose is clearly defined as web search.
Naming Consistency5/5
The single tool name 'web_search' follows a clear verb_noun pattern, but there are no other tools to compare consistency.
Tool Count2/5
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.
Completeness5/5
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
ActivitySlowing
ResponsivenessNo issues
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
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.
Search the agentic web. 4,100+ sites, 11 tools incl. check_url + verify_mcp for probe-before-use.
Live AI-native web search with citations. One tool for every MCP client. Flat per-request pricing.
Related MCP Servers
- AlicenseBqualityCmaintenanceEnables web search and site-specific search capabilities through the Deepsearch model. Provides unified access to broad web retrieval and targeted site search functionality within the MCP ecosystem.2185Apache 2.0
- 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.32Apache 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.195MIT
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/blueewhitee/agent-web-search-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server