SushiMCP
<div align="center">
</div>
[](https://mseep.ai/app/7b84b486-4ccb-4fc5-8d3b-74d398fa59c0)
# SushiMCP
SushiMCP is a model context protocol server designed to assist developers with delivering context to their AI IDE's. It's simple to use and massively improves the performance of base and premium LLM models when generating code. The easiest way to get started is by registering SushiMCP with your client using the default configuration:
<br>
## Registering SushiMCP with an MCP Client
```json
{
"sushimcp": {
"command": "npx",
"args": [
"-y",
"@chriswhiterocks/sushimcp@latest",
"--llms-txt-source",
"cool_project:https://coolproject.dev/llms-full.txt",
"--openapi-spec-source",
"local_api:http://localhost:8787/api/v1/openapi.json"
]
}
}
```
<br>
## Advanced Configuration & Deeper Learning
Visit the [SushiMCP Docs](https://docs.sushimcp.com) for more information on advanced configuration and deeper learning about SushiMCP.
<br>
## Glama.ai Ratings
<a href="https://glama.ai/mcp/servers/@maverickg59/sushimcp">
<img width="380" height="200" src="https://glama.ai/mcp/servers/@maverickg59/sushimcp/badge" />
</a>
<br>
## Author
Chris White: [Email](mailto:chris@chriswhite.rocks) | [GitHub](https://github.com/maverickg59) | [Discord](https://discord.com/users/1115027188840939560) | [Personal Site](https://chriswhite.rocks) | [X](https://x.com/chriswhiterox) | [LinkedIn](https://www.linkedin.com/in/chrisewhite) | [Five9 Cyber](https://www.fiv9cyber.com/)
<br>
## License
This project is licensed under the AGPL-3.0-or-later. See the `license.txt` file for details.
TDQS
Scored across 4 tools
Each tool has a clearly distinct purpose: fetch_llms_txt and fetch_openapi_spec retrieve content from URLs, while list_llms_txt_sources and list_openapi_spec_sources list available sources for those URLs. There is no overlap in functionality, and the descriptions clearly differentiate between fetching and listing operations for two distinct resource types (llms.txt and OpenAPI specs).
All tool names follow a consistent verb_noun pattern with snake_case: fetch_llms_txt, fetch_openapi_spec, list_llms_txt_sources, and list_openapi_spec_sources. The naming is predictable and readable, with 'fetch' for retrieval actions and 'list' for source enumeration, maintaining uniformity throughout the set.
With 4 tools, the count is reasonable for a server focused on fetching and listing documentation sources. It covers two resource types (llms.txt and OpenAPI specs) with complementary operations, but it might feel slightly thin if expanded to handle more documentation formats or additional actions like validation or processing. Overall, it's well-scoped for its apparent purpose.
The tool set provides basic fetch and list operations for llms.txt and OpenAPI specs, covering retrieval and source discovery. However, there are notable gaps: no tools for updating, deleting, or validating these resources, and no operations for other documentation formats mentioned in descriptions (e.g., llms-full.txt or llms-mini.txt). This limits the surface to read-only actions, which may cause agents to hit dead ends in more complex workflows.