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…
Agent Search mcp is an MCP project maintained in the lennney/agent-search-mcp repository. The maintainer describes its purpose as “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…”. Read the project documentation for the complete scope.
The documented npm package is agent-search-mcp. The configuration below comes from the maintainer’s example; adapt its paths and account values to your environment.
Project documentation · Repository · Discovery listing. This profile records the public documentation checked on 2026-10-08.
Check the linked publisher documentation and your connected client's tool list. Names and availability can vary with the server version and account permissions.
| Tool | What it does |
|---|---|
| free_search | Multi-engine Web Search with bounded fallback |
| free_search_advanced | Filtered waterfall search and optional enrichment |
| free_extract | Extract a URL as clean Markdown |
| fetch_github_readme | Fetch a public GitHub repository README |
| fetch_csdn_article | Fetch a CSDN article |
| fetch_juejin_article | Fetch a Juejin article |
| search_with_synthesis | Search evidence with an LLM synthesis hint |
| Environment | Default |
| SEARCH_PROVIDER_MODE | free_first |
| PAID_ENGINE_ORDER | brave,exa,tavily,youcom,tencent_wsa,bocha,serper |
| SEARCH_BUDGET_MAX_CALLS | 16 |
| SEARCH_BUDGET_MAX_ELAPSED_MS | 30000 |
| SEARCH_BUDGET_MAX_RESULTS | 100 |
| EVIDENCE_BUDGET_CHARS | 1200 |
{
"mcpServers": {
"agent-search": {
"command": "npx",
"args": [
"-y",
"agent-search-mcp"
]
}
}
}From the project documentation. Replace placeholders and example paths before connecting.
Retrieve public web pages as readable Markdown with the reference Fetch MCP server, including pagination for longer responses.
Use Firecrawl MCP to retrieve website content and extract information for research through Firecrawl’s API-backed web tools.
MCP server for SignalFuse — AI trading intelligence with 11 tools: real-time signals, market sentiment, macro regime, live strategy arena, web search
Production-ready RAG out of the box to search and retrieve data from your own documents.
Enables web scraping, content searching, site crawling, and data extraction using the Firecrawl API.
Scrape any public Discourse forum: topic titles, authors, reply counts, views and canonical URLs…