# Shepherd MCP

> Use this tool when you need to debug and optimize AI agent performance, compare sessions, and analyze large language model (LLM) usage patterns. It enables querying and analysis of AI agent sessions from observability providers, allowing for informed decision-making and improved agent runs. Ideal for use cases requiring performance tracking, session comparison, and LLM usage analysis.

Canonical page: https://skillsregistry.net/skills/neuralis-in-shepherd-mcp  
JSON: https://api.skillsregistry.net/v1/skills/neuralis-in-shepherd-mcp

## Description

Enables AI assistants to query and analyze AI agent sessions from observability providers like Shepherd (AIOBS) and Langfuse, allowing users to debug agent runs, compare sessions, track performance, and analyze LLM usage patterns.

## Trust

- **Trust score (0–1):** 0.96
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-09-28

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/jw7hkr9sgo)
- **Repository:** <https://github.com/neuralis-in/shepherd-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": "neuralis-in-shepherd-mcp"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/neuralis-in-shepherd-mcp` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/neuralis-in-shepherd-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