# SushiMCP

> Use this tool when you need to provide AI IDEs with relevant technical documentation context to improve code generation performance. SushiMCP solves the problem of limited model knowledge by fetching and serving documentation from various sources, supporting both stdio and SSE transport methods. It takes in requests for documentation and outputs relevant context, making it ideal for use cases where accurate and efficient code generation is crucial.

Canonical page: https://skillsregistry.net/skills/sushi  
JSON: https://api.skillsregistry.net/v1/skills/sushi

## Description

SushiMCP is a Model Context Protocol server designed to assist developers by delivering documentation context to AI IDEs. Developed by Chris White, it specializes in fetching and serving llms.txt documentation from various technology sources, with built-in tools for listing available documentation sources and retrieving their content. The implementation supports both stdio and SSE transport methods, features domain access controls for security, and includes a comprehensive default collection of documentation sources covering popular frameworks and libraries. SushiMCP significantly improves the performance of both base and premium LLM models when generating code by providing relevant technical documentation context on demand.

## Trust

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

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-04-25

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/sushi)
- **Repository:** <https://github.com/maverickg59/sushimcp>

## 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": "sushi"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/sushi` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/sushi/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