Google PageRank for AI agents. 25,000+ tools indexed.

agent-search-mcp MCP Server

lennney/agent-search-mcp

Score: 52.5 Rank #14789 Browser Automation
[![AgentRank](https://agentrank-ai.com/api/v1/badge/lennney--agent-search-mcp)](https://agentrank-ai.com/tool/lennney--agent-search-mcp/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge)
Are you the maintainer of lennney/agent-search-mcp? Claim this listing →

Free-first Chinese and English web search MCP using zero-key sources and inspectable evidence.

Add AgentRank to Claude Code Discover and compare tools like lennney/agent-search-mcp — your AI finds the right one automatically
Get API Access →
claude mcp add agentrank -- npx -y agentrank-mcp-server

Overview

lennney/agent-search-mcp is a TypeScript tool licensed under Apache-2.0. Free-first Chinese and English web search MCP using zero-key sources and inspectable evidence. Topics: mcp, ai-agent, chinese-search, mcp-server, self-hosted, typescript, web-search, model-context-protocol, claude, codex, cursor, streamable-http, token-efficient, zero-api-key, metasearch, privacy-first, search-aggregator, web-scraping, zero-config, evidence-first.

Ranked #14789 out of 24846 indexed tools.

Ecosystem

TypeScript Apache-2.0
mcpai-agentchinese-searchmcp-serverself-hostedtypescriptweb-searchmodel-context-protocolclaudecodexcursorstreamable-httptoken-efficientzero-api-keymetasearchprivacy-firstsearch-aggregatorweb-scrapingzero-configevidence-first

Score Breakdown

StarsFreshnessIssue HealthContributorsDependents
Stars 15% 111

111 stars → growing community

Freshness 25% 1mo ago

Last commit 1mo ago → moderate activity

Issue Health 25% 0%

0/6 issues closed → many open issues

Contributors 10% 6

6 contributors → small team

Dependents 25% 0

No dependents → no downstream usage

npm Downloads N/A
PyPI Downloads N/A
Forks 11
Description Good
License Apache-2.0

Weights: Freshness 20% · Issue Health 20% · Dependents 22% · Stars 10% · Contributors 8% · How we score →

How to Improve

Description low impact

Expand your description to 150+ characters for better discoverability

Freshness high impact

Last commit was 51 days ago — a recent commit would boost your freshness score

Issue Health high impact

You have 6 open vs 0 closed issues — triaging stale issues improves health

Badge all embed codes →

AgentRank score for lennney/agent-search-mcp
[![AgentRank](https://agentrank-ai.com/api/v1/badge/lennney--agent-search-mcp)](https://agentrank-ai.com/tool/lennney--agent-search-mcp/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge)
<a href="https://agentrank-ai.com/tool/lennney--agent-search-mcp/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge"><img src="https://agentrank-ai.com/api/v1/badge/lennney--agent-search-mcp" alt="AgentRank"></a>

Embed Widget docs →

Embed a rich score widget on your site or blog.

<script src="https://agentrank-ai.com/embed.js" data-tool="lennney/agent-search-mcp"></script>

Matched Queries

topic:mcptopic:mcp-servertopic:model-context-protocol

From the README

# Agent Search MCP: Free-first Web Search with Inspectable Evidence

**A Node.js MCP server and CLI for English and Chinese web search.**

Agent Search MCP starts without an API key. It returns compact multi-source
evidence, records provider failures, and bounds work with request and evidence
budgets. Paid providers run only when policy and credentials allow.

[中文文档](README_zh.md) · [Product page](https://take-a-deep-breath0.com/en/agent-search-mcp) · [Benchmarks](./benchmarks/) · [Architecture](./docs/architecture.md) · [CHANGELOG](./CHANGELOG.md)

---

## Install

```bash
npx -y agent-search-mcp
```

Requires Node.js >= 18.17. The default runtime does not require a browser,
database, Python, or a search API account.

### Connect an MCP client

Use this stdio configuration in MCP clients that accept `mcpServers` JSON,
including Claude Desktop, Cursor, VS Code, and Windsurf:

```json
{
  "mcpServers": {
    "agent-search": {
      "command": "npx",
      "args": ["-y", "agent-search-mc
Read full README on GitHub →

Get the weekly AgentRank digest

Top movers, new tools, ecosystem insights — straight to your inbox.