Skip to content
Space Kitty Archive logo

Space Kitty Archive MCP server

Which MCP servers are Space Kitty Archive'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 2026-10-30

← Back to Space Kitty Archive

Whose server it is
  • Registry namecom.space-kitty/research-archiveverified in the MCP registry

The registry name sits under space-kitty.com. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.

When we asked itchecked 2026-10-30
  • Staterequires sign-inchecked 2026-10-30

On 2026-10-30 the server answered and asked for a sign-in with a Space Kitty Archive account (OAuth). It shows its tool list only to signed-in users, so we list none here.

Should an agent connect itNot proven either way yet
  • Whether its tools do the product's job has not been judged yet.
  • Checked on 3 of the 7 days it takes to judge reliability.

Once connected

  • For "pull topic dossiers with benchmarks and open problems", the likely first call is get_dossier.
  • create_discussion change data without a sign-in: anyone with the address can call them.
  • Parameters are untyped or undescribed in 10 of 12 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.

Measured dailydaily checks: 3, the first on 2026-10-30
  • INITE MCP scoreafter a weeka score needs 7 daily checks: 3 so far
  • Answeredmeasuring3 of the 7 daily checks it takes to print a share
  • Median first answer144 ms
  • Space in an agent's context≈ 1,331 tokensthe definitions of all its tools (12), which an agent carries on every turn
  • Tool definitionsB · 86 of 100
  • Typed results0 of 12 toolsdeclared outputSchema: results come typed, read once
  • Parameters without a description: in 10 of 12

What an agent can do with it

  • not sure · search a 16,061-paper index of frontier research
  • not sure · check each dossier claim against its cited papers
  • can do · pull topic dossiers with benchmarks and open problems

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

  • Tools that change data, on a server that answers without a sign-in: create_discussion

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 →

How to connect

Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:

{
  "mcpServers": {
    "research-archive": {
      "type": "http",
      "url": "https://space-kitty.com/mcp"
    }
  }
}

Add it

Claude Code, in a terminal

claude mcp add --transport http space-kitty https://space-kitty.com/mcp

Add to CursorAdd to VS Code

claude.ai, ChatGPT and other clients: add https://space-kitty.com/mcp as a custom connector in the settings.

The first time it connects, the client opens a Space Kitty Archive sign-in.

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.