Skip to content
Kyde logo

Kyde MCP server

Which MCP servers are Kyde'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 2026-11-02

← Back to Kyde

Whose server it is
  • Registry namecom.kyde/scoreverified in the MCP registry

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

When we asked itchecked 2026-11-02
  • Stateanswerschecked 2026-11-02
  • Tools4
  • Server calls itselfkyde-score
  • Server version2026.10.27-0
  • Protocol version2025-06-18

On 2026-11-02 the server answered initialize and tools/list without a sign-in. First answer in 523 ms.

Should an agent connect itNot proven either way yet
  • Whether its tools do the product's job has not been judged yet.
  • Checked on 2 of the 7 days it takes to judge reliability.

Once connected

  • create_key, set_webhook change data without a sign-in: anyone with the address can call them.
  • Parameters are untyped or undescribed in 2 of 4 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: 2, the first on 2026-11-02
  • INITE MCP scoreafter a weeka score needs 7 daily checks: 2 so far
  • Answeredmeasuring2 of the 7 daily checks it takes to print a share
  • Median first answer528 ms
  • Space in an agent's context≈ 359 tokensthe definitions of all its tools (4), which an agent carries on every turn
  • Tool definitionsA · 92 of 100
  • Typed results0 of 4 toolsdeclared outputSchema: results come typed, read once
  • Parameters without a description: in 2 of 4

What an agent can do with it

  • not sure · stop an agent whose behavior drifts from its assigned task
  • not sure · detect prompt-injection hijacks of agent actions
  • not sure · halt agent loops that rack up model costs

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_key, set_webhook

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 →

Tools it offers4 tools · read 2026-11-02
  • create_key

    Create a scoring key (no signup). One key covers all agents, identified by OTel service.name. webhook_url (https) is optional but recommended: it receives an HMAC-signed POST when any agent's score changes band.

  • get_scores

    Current drift score per agent under the key: 0-39 deviating, 40-69 watch, 70-100 normal; status 'learning' until the 30-run baseline freezes.

  • set_webhook

    Add or change the https webhook notified on band changes.

  • revoke_key

    Revoke the key and permanently delete all data stored under it. Requires confirm=true.

How to connect

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

{
  "mcpServers": {
    "score": {
      "type": "http",
      "url": "https://score.kyde.com/mcp"
    }
  }
}

Add it

Claude Code, in a terminal

claude mcp add --transport http kyde https://score.kyde.com/mcp

Add to CursorAdd to VS Code

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

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.