# ABIS MCP Server

> Use this tool when you need to monitor and detect changes in AI model behavior, enabling real-time tracking of drift across multiple models. It solves problems related to model compliance and version control, providing outputs such as scorecards and compliance reports. Ideal for use cases requiring ongoing model performance evaluation and risk management, it takes in Claude Code models as input and provides actionable insights for maintenance and updates.

Canonical page: https://skillsregistry.net/skills/cijlabs-abis-mcp  
JSON: https://api.skillsregistry.net/v1/skills/cijlabs-abis-mcp

## Description

Enables real-time AI behavioral drift monitoring and detection for Claude Code, tracking shifts in model behavior across 11 major models with tools for scorecards, version changes, and compliance reports.

## Trust

- **Trust score (0–1):** 0.68
- **Verification tier:** scanned
- **Last scanned:** 2026-09-01

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** monitoring
- **Updated:** 2026-09-01

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/u6r8oz3ajb)
- **Repository:** <https://github.com/cijlabs/abis-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": "cijlabs-abis-mcp"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/cijlabs-abis-mcp` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/cijlabs-abis-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