Agent Search MCP

Install

Works with Claude Code, Codex, VS Code, Cursor, Windsurf, Claude Desktop. Read the repository before you give any tool access to your data.

npx agentmarket install connector/lennney-agent-search-mcp

About

Use cases: web-search, web-scraping, deep-research

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this server can do and what it asks for, from its tool list and install config. Checked Oct 25, 2026.

Tools

8 read · 0 write · 0 deleteRead-only

Secrets

7 (API keys, tokens or passwords)

Install scripts

Not scanned yet

Runs as

Node.js package

Tools (8)

Read from the source code; the running server may differ. Descriptions are the server’s own words; hidden characters are shown as [U+…].

• fetch_csdn_articleread-only

  Fetch content from a CSDN blog article. Best for: Chinese developer blog content on CSDN. Not recommended for: Other Chinese sites — use free_extract instead. @readOnly true @idempotent true — makes outbound HTTP requests to the CSDN article URL.

• fetch_github_readmeread-only

  Fetch README content from a GitHub repository. Best for: Getting project documentation quickly. Not recommended for: Non-GitHub URLs — use free_extract instead. @readOnly true @idempotent true — makes outbound HTTP requests to raw.githubusercontent.com.

• fetch_juejin_articleread-only

  Fetch content from a Juejin article. Best for: Chinese developer articles on Juejin. Not recommended for: Non-Juejin content — use free_extract instead. @readOnly true @idempotent true — makes outbound HTTP requests to juejin.cn API.

• free_extractread-only

  Extract one selected URL into clean Markdown. Use after search when snippets are insufficient, or for a URL supplied by the user. It fetches one page; it does not search or bulk-extract URLs. Behavior: Makes an outbound HTTP request to Jina Reader (r.jina.ai) which fetches and converts the page to markdown. Has SSRF protection: blocks private IPs, localhost, and metadata endpoints. 10s request timeout — pages exceeding this will fail with a timeout error. HTTP errors (4xx, 5xx) are returned as structured error responses.

• free_searchAgent Searchread-only

  Search the web through the Agent Search multi-engine router. Read-only and idempotent.

• free_search_advancedread-only

  Verification-oriented search with domain filters and waterfall fallback. Use for claim checking, Chinese-source search, or publisher restrictions. Start with free_search for quick discovery. The response exposes source_count, stop_reason, evidence_budget, and partialFailures. @readOnly true @idempotent true — runs waterfall progressive search across policy-allowed engines. Makes outbound HTTP requests to search engines and optionally to Jina Reader for content enrichment.

• search_quality_judgment

  Pointwise relevance and citation-support judgment.

• search_with_synthesisread-only

  Opt-in deep search with waterfall verification and content enrichment. Returns structured results plus a prompt_hint; it does not call an external LLM. Use when multi-source evidence needs a synthesis handoff. free_search is the default for discovery; this path uses more tokens and network time. @readOnly true @idempotent true — runs waterfall search across free+paid engines with content enrichment.

Compare and alternatives

Featured in

• Best MCP servers for web search

Signals

Stars

112

Forks

13

Open issues

0

Contributors

5

Last commit

Sep 16, 2026 (1 month ago)

Last release

Aug 11, 2026 (2 months ago)

From GitHub (fetched Oct 24, 2026).

Details

Registry name

io.github.lennney/agent-search-mcp

Version

3.2.1

Auth

API key

Packages

npm agent-search-mcp

License

Apache-2.0

Repository

github.com/lennney/agent-search-mcp

First seen

Oct 24, 2026

Last checked

Oct 24, 2026

Source

Official MCP Registrygithub-graphql