
公开资料查询 MCP server
Which MCP servers are 公开资料查询's own, from the official registry and from asking its own domain, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.
read 2026-10-29
- Registry namecn.infimeta/public-source-searchverified in the MCP registry
The registry name sits under infimeta.cn. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.
- Stateanswerschecked 2026-10-29
- Tools2
- Server calls itselfinfimeta-public-search
- Server version1.0.0
- Protocol version2025-06-18
On 2026-10-29 the server answered initialize and tools/list without a sign-in. First answer in 514 ms.
- Its tools do every use case we checked: search Wikipedia, Crossref, Hacker News and Stack Overflow; answer questions with traceable public sources; query public knowledge through an API or MCP.
- Checked on 5 of the 7 days it takes to judge reliability.
Once connected
- For "search Wikipedia, Crossref, Hacker News and Stack Overflow", the likely first call is search_public_sources.
- For "answer questions with traceable public sources", the likely first call is search_public_sources.
- For "query public knowledge through an API or MCP", the likely first call is search_public_sources.
- Parameters are untyped or undescribed in 2 of 2 tools: check arguments before calling.
Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.
- INITE MCP scoreafter a weeka score needs 7 daily checks: 5 so far
- What an agent can do with it3 of 3 use cases
- Answeredmeasuring5 of the 7 daily checks it takes to print a share
- Median first answer1382 ms
- Space in an agent's context≈ 271 tokensthe definitions of all its tools (2), which an agent carries on every turn
- Tool definitionsB · 83 of 100
- Typed results0 of 2 toolsdeclared outputSchema: results come typed, read once
- Parameters without a description: in 2 of 2
What an agent can do with it
- can do · search Wikipedia, Crossref, Hacker News and Stack Overflow
- can do · answer questions with traceable public sources
- can do · query public knowledge through an API or MCP
Each of the product's use cases, put to Jev against this server's tool list: can an agent do it with these tools?
Worth a look
None of the five warning signs in these definitions.
A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (25%), doing the product's job (25%), definitions (20%), context (10%), use (10%) and how readily a client connects (10%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →
search_public_sourcesSearch encyclopedias, scholarly metadata and communities. Not whole-web search. Optional purpose does not affect results. Submitted queries are recorded for research.
report_search_gapOptionally report whether a previous search helped and which information is missing. Stored privately for research.
How to connect
Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:
{
"mcpServers": {
"public-source-search": {
"type": "http",
"url": "https://infimeta.cn/mcp"
}
}
}Add it
Claude Code, in a terminal
claude mcp add --transport http infimeta https://infimeta.cn/mcpclaude.ai, ChatGPT and other clients: add https://infimeta.cn/mcp as a custom connector in the settings.
OpenAPI spec
2 paths, read 2026-10-29. Open the spec ↗
Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.
Cookies
Before we count this visit
Analytics and ad measurement tell us which pages and which of our ads do their job: Google Analytics and Google Ads, the Meta pixel, Yandex Metrica, and one first-party id of our own. Nothing is stored until you answer, and declining changes nothing about the site.