# kirk-mcp

> kirk-mcp — kavara-ai-kirk-mcp. Use this tool when you need to detect structural anomalies in real-time financial data, such as L2 order-book data, to identify unusual patterns and potential security threats. It solves problems related to model enumeration, engine identity attestation, and data validation, providing a set of discovery tools for secure and reliable analysis. The tool takes in financial data as input and outputs anomaly scores and model enumerations, enabling informed decision-making in high-stakes financial environments.

Canonical page: https://skillsregistry.net/skills/kavara-ai-kirk-mcp  
JSON: https://api.skillsregistry.net/v1/skills/kavara-ai-kirk-mcp

## Description

MCP server exposing Kirk, an algorithm for real-time unsupervised pairwise structural anomaly detection, as a set of validation and discovery tools. It enables scoring of L2 order-book data, model enumeration, and secure attestation of engine identity.

## Trust

- **Trust score (0–1):** 0.70
- **Verification tier:** verified
- **Last scanned:** 2026-08-29

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** other
- **Updated:** 2026-08-29

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/m3wobsrsz2)
- **Repository:** <https://github.com/Kavara-AI/kirk-mcp>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "kavara-ai-kirk-mcp"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/kavara-ai-kirk-mcp` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/kavara-ai-kirk-mcp/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt