Koskamo

Kirk MCP

Kirk MCP exposes a sealed ML model for cross-section entropy scoring on non-stationary time series data. It provides tools for unsupervised structural change detection, validation, and discovery, allowing agents to compute pairwise structure and signal when system structure breaks using a Kalman filter-like approach for non-Gaussian streams.

Endpoint and access

API key: create a key with the vendor first; your client sends it as an authorization header on every request.

Kirk MCP logo, by Kavara-AICommunity listingStreamable HTTPAPI keyEndpoint checked 2026-11-06Published by Kavara-AI
You need:You need a credential. Kavara issues one of two kinds — use whichever you were given
MCP endpoint (Streamable HTTP)
https://kirk-mcp.kavara.ai/mcp
Vendor documentation

Checks and signals

Each line is separate evidence, not a trust score.

  • Passed Endpoint answered the live check ·
  • Availability 1 of 1 checks passed in 30 days

What you can do with it

  • Unsupervised structural change detection in non-stationary time series
  • Cross-section entropy scoring for system variables
  • Validating engine status and recording engine SHA
  • Checking billing balance and credit usage

Source and maintenance

Community listingRegistry 1.0.2
Maintenance checked

Tools

Reported by the attributed source; not independently observed by Koskamo.

No tool definitions available.

90-day uptime

A lightweight connection check about every six hours, sampled on hosts with many listings. It shows the server answered, not that its tools work.

Too few checks for a percentage yet (2 of 2 answered).

  1. 2026-11-06: 1 of 1 checks answered
  2. 2026-11-07: 1 of 1 checks answered

30-day availability

Aggregated from read-only remote checks; this is not a tool-execution or security guarantee.

Successful checks
1 of 1 (100%)
Average latency
288 ms
95th percentile latency
288 ms

Maintenance history

Public check and source-refresh events. Editorial and ownership records remain private.

  • · probe · passed · 288 ms · metadata changed · refuses unauthenticated initialize (HTTP 403)

Connect from your client

Each snippet registers the same endpoint; pick the client you use.

This server is operated by the named third party. Listing and endpoint checks are not an endorsement or a security audit. Review the operator's permissions, terms, and data handling before connecting. How listings are checked and corrected.

Claude Code

Run this once in a terminal. It registers the remote server. Use --scope project to write .mcp.json for the repo.
Claude Code configuration
claude mcp add --transport http kirk-mcp https://kirk-mcp.kavara.ai/mcp

Codex

Run this once. Codex stores MCP servers in ~/.codex/config.toml (or .codex/config.toml in a trusted project).
Codex configuration
codex mcp add kirk-mcp --url https://kirk-mcp.kavara.ai/mcp

Cursor

Merge this server into .cursor/mcp.json in your project, then enable kirk-mcp in your MCP settings.
Cursor configuration
{
  "mcpServers": {
    "kirk-mcp": {
      "url": "https://kirk-mcp.kavara.ai/mcp"
    }
  }
}

Cline

Merge this into cline_mcp_settings.json (Cline → MCP Servers → Configure).
Cline configuration
{
  "mcpServers": {
    "kirk-mcp": {
      "type": "streamableHttp",
      "url": "https://kirk-mcp.kavara.ai/mcp",
      "disabled": false
    }
  }
}

VS Code

Merge this server into .vscode/mcp.json. Use MCP: List Servers to start kirk-mcp and inspect its tools.
VS Code configuration
{
  "servers": {
    "kirk-mcp": {
      "type": "http",
      "url": "https://kirk-mcp.kavara.ai/mcp"
    }
  }
}

Gemini CLI

Run this once. It writes .gemini/settings.json in the current project; pass --scope user for ~/.gemini/settings.json.
Gemini CLI configuration
gemini mcp add --transport http kirk-mcp https://kirk-mcp.kavara.ai/mcp

Claude Desktop

Open Claude Settings > Connectors > Add custom connector, enter this server URL and enable it for the conversation. This is a manual remote-connector handoff, not a desktop JSON configuration.
Claude Desktop configuration
https://kirk-mcp.kavara.ai/mcp

Windsurf

Merge this into ~/.codeium/windsurf/mcp_config.json, then refresh MCP in Cascade. Windsurf remote servers use serverUrl, not url.
Windsurf configuration
{
  "mcpServers": {
    "kirk-mcp": {
      "serverUrl": "https://kirk-mcp.kavara.ai/mcp"
    }
  }
}

Let your agent find its tools

Find servers like Kirk MCP from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.