# ML On-Call Agent

> ML On-Call Agent — kanishqtanwar35-hub-ml-oncall-agent. Use this tool when you need to diagnose and investigate machine learning model regressions, as it correlates drift reports, evaluation runs, and deployment logs to provide detailed incident reports. It solves problems related to model performance degradation and data drift, offering a set of investigation tools to identify root causes. Ideal for use when model accuracy decreases or unexpected behavior occurs, providing evidence-cited reports as output.

Canonical page: https://skillsregistry.net/skills/kanishqtanwar35-hub-ml-oncall-agent  
JSON: https://api.skillsregistry.net/v1/skills/kanishqtanwar35-hub-ml-oncall-agent

## Description

MCP server that diagnoses ML model regressions by correlating drift reports, eval runs, and deploy logs, providing evidence-cited incident reports through a set of investigation tools.

## Trust

- **Trust score (0–1):** 0.69
- **Verification tier:** scanned
- **Last scanned:** 2026-09-03

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** devops-ci
- **Updated:** 2026-09-03

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/gvmq5v5uoc)
- **Repository:** <https://github.com/kanishqtanwar35-hub/ml-oncall-agent>

## 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": "kanishqtanwar35-hub-ml-oncall-agent"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/kanishqtanwar35-hub-ml-oncall-agent` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/kanishqtanwar35-hub-ml-oncall-agent/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
