Seta MCP - Up-to-date Local Docs for Coding

What is Seta MCP - Up-to-date Local Docs for Coding?

Seta MCP is a Model Context Protocol server designed for Salesforce developers to create code and configuration. It fetches documentation from a user-defined local file system, giving complete control over the context provided to an AI assistant. Unlike cloud-dependent alternatives, it works entirely offline and uses local documentation libraries.

How to use Seta MCP - Up-to-date Local Docs for Coding?

Set the LOCAL_DOCS_PATH environment variable to point to a root directory containing documentation libraries. Each library folder must include a manifest.json file describing topics, difficulty levels, and learning paths. Then invoke the tools get-library-id (to find matching libraries) and get-library-docs (to fetch document content) from any MCP client like VSCode, Cursor, or Claude Desktop. Optionally run seta-indexer to enable semantic search.

Key features of Seta MCP - Up-to-date Local Docs for Coding

• Works fully offline with local documentation
• Fine-grained control over documentation versions and content
• Fast iteration: update docs and make them immediately available to the LLM
• Optional semantic search via vector database indexing
• Enhanced manifest.json with difficulty levels, use cases, and learning paths
• Tools for library identification and document fetching

Use cases of Seta MCP - Up-to-date Local Docs for Coding

• Provide up-to-date Apex, LWC, and configuration docs to an AI coding assistant
• Deliver internal or proprietary documentation offline to developers
• Create custom learning paths for Salesforce onboarding or certification prep
• Iterate on documentation and instantly test how the AI uses the new content

FAQ from Seta MCP - Up-to-date Local Docs for Coding

What are the runtime requirements?

Node.js version 18.0.0 or higher, a local directory of structured documentation, and an MCP client (VSCode, Cursor, Windsurf, or Claude Desktop).

How does this compare to context7?

Unlike context7 which fetches documentation from the web, Seta MCP reads from a local file system, enabling offline use and full control over documentation versions and content.

Where is the documentation data stored?

All documentation lives on your local machine under the directory pointed to by the LOCAL_DOCS_PATH environment variable. The server never sends your docs to an external service.

Do I need to run the semantic indexer?

No, semantic search is optional. You can use the server with just the manifest.json files for keyword-based matching. The indexer creates a vector database for semantic discovery when you need it.

What transports and authentication are supported?

The server uses the standard MCP protocol over stdio, as shown in the client configuration examples. No authentication is built in; it is designed for local or trusted remote use.