Infimeta Public-source Search
MCP search across Wikipedia, Crossref and community sources that keeps original citations
- Pricing
- Free
- Platforms
- API, Web
- Runs
- Remotely
- Version
- 1.0.0
- Listing updated
- 2 days ago
About Infimeta Public-source Search
Infimeta Public-source Search is a free MCP server for web search and scraping. It runs as a hosted remote server, so there is nothing to install locally.
Infimeta runs one public retrieval service three ways: a web page, a JSON API and this MCP server. A query goes to the sources you pick, such as Crossref or English Wikipedia, and comes back with a query ID, items that keep their original source, per-source status, a fetch time and stated limitations. If a source fails, the status reads partial or unavailable instead of pretending there were no results.
Calls are logged for research. Queries and the optional purpose are kept for up to 90 days and are visible only to the operator; the query text is forwarded to the chosen sources but the purpose is not. The site warns against sending identities, private tasks or full chats. Source titles and abstracts are treated as untrusted and any instructions in them are not followed.
The API allows 30 requests a minute per network origin, returns at most 5 items per source and caches results for 10 minutes. The page itself is in Chinese with an English setup guide.
Install
Run in a terminal
claude mcp add --transport http public-source-search https://infimeta.cn/mcpAdd to Settings → Connectors → Add custom connector
https://infimeta.cn/mcpAdd to ~/.cursor/mcp.json
{
"mcpServers": {
"public-source-search": {
"url": "https://infimeta.cn/mcp"
}
}
}Add to .vscode/mcp.json
{
"servers": {
"public-source-search": {
"type": "http",
"url": "https://infimeta.cn/mcp"
}
}
}Add to ~/.codeium/windsurf/mcp_config.json
{
"mcpServers": {
"public-source-search": {
"serverUrl": "https://infimeta.cn/mcp"
}
}
}Add to your client's MCP settings (most use this shape)
{
"mcpServers": {
"public-source-search": {
"type": "http",
"url": "https://infimeta.cn/mcp"
}
}
}Tools this server provides (2)
Taken from the project documentation; the running server may differ.
- search_public_sources
- Search the chosen public sources; same parameters as the search API.
- report_search_gap
- Report results as useful, incomplete or irrelevant and describe what was missing.
What it does
- Multi-source search
- Queries encyclopedia, academic publishing and community sources.
- Source provenance
- Each item keeps its original source and the response lists coverage limits.
- Honest failure status
- Source failures show as partial or unavailable, not as zero results.
- Follow-up queries
- A later request can reference an earlier query_id.
- Gap feedback
- Report whether results were useful, incomplete or irrelevant.
Good for
- Pull sourced background on a research question
- Compare evidence across encyclopedic and academic sources
- Let an agent flag what its search missed
- Test an integration with the test-traffic header
Pricing
Free
No API key; rate limited to 30 requests a minute
Prices change. Check infimeta.cn before you buy.
Infimeta Public-source Search FAQ
Do I need an API key?
No. The service is described as keyless and does not call paid models.
What are the rate limits?
30 requests a minute per network origin, up to 5 items per source, cached for 10 minutes.
Is my query stored?
Yes. Queries and the optional purpose are kept up to 90 days and seen only by the operator.
What tools does the MCP server offer?
search_public_sources and report_search_gap.
Is Infimeta Public-source Search free?
Yes. Infimeta Public-source Search is free to use.
How do I add Infimeta Public-source Search to Claude Code?
Run this command in your terminal: claude mcp add --transport http public-source-search https://infimeta.cn/mcp
What are the best alternatives to Infimeta Public-source Search?
The closest alternatives to Infimeta Public-source Search are Scrapling MCP Server, Firecrawl MCP Server, SearXNG Search, NeuralVerge and AI-Powered directory.
Alternatives to Infimeta Public-source Search

Scrapling MCP Server
MCP serverMCP server for AI clients to scrape sites with HTTP and stealth browser sessions
Runs locally- 17 tools
- Open source
- 104K GitHub stars
- Web search and scraping

Firecrawl MCP Server
MCP serverMCP server that lets AI agents search, scrape and interact with web pages
- 3 tools
- Remote
- Freemium
- 7.8K GitHub stars
- Web search and scraping

SearXNG Search
MCP serverMCP server for web search and page reading through a SearXNG instance
Runs locally- 3 tools
- Open source
- 1.4K GitHub stars
- Web search and scraping

NeuralVerge
MCP serverStructured, source-tagged business and people data from 300+ sources for agents
- 200 tools
- Remote
- Free trial
- 1 GitHub star
- Web search and scraping

AI-Powered directory
MCP serverSearch AI tools, agents and MCP servers and get install configs from inside your AI assistant.
- 4 tools
- Remote
- Free
- Developer tools

Shopify MCP Server (any store)
MCP serverHosted MCP server that returns any Shopify store's products, prices and stock
Not checked yet- 4 tools
- Remote
- Paid
- E-commerce