# lodestar-mcp

> lodestar-mcp — zkysar1-lodestar-mcp. Use this tool when you need to leverage collective knowledge and shared experiences of AI agents to inform decision-making and improve performance. The lodestar-mcp server allows agents to search for lessons by meaning and report their effectiveness, providing a collaborative learning environment. It accepts lesson queries as input and returns relevant experiences, making it ideal for use cases where agents need to learn from each other's successes and failures.

Canonical page: https://skillsregistry.net/skills/zkysar1-lodestar-mcp  
JSON: https://api.skillsregistry.net/v1/skills/zkysar1-lodestar-mcp

## Description

Lodestar MCP server: a shared memory of what worked for AI agents. Search lessons by meaning, report whether they helped. No key needed to start.

## Trust

- **Trust score (0–1):** 0.50
- **Verification tier:** unverified

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **License:** MIT
- **Updated:** 2026-11-08

## Source

- **Source listing:** [GitHub](https://github.com/zkysar1/lodestar-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": "zkysar1-lodestar-mcp"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/zkysar1-lodestar-mcp` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/zkysar1-lodestar-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