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

@techformist

リポジトリ

基本情報

カテゴリ

メモリとナレッジ

ライセンス

MIT

トランスポート

stdio

作者

techformist

Seta MCP - Up-to-date Local Docs for Coding について

MCP server powered by local documentation

#local #offline #mcp #model-context-protocol #mcp-server

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

以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。

{
  "mcpServers": {
    "seta-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/inspector",
        "npx",
        "seta-mcp@latest"
      ]
    }
  }
}

Seta MCP - Up-to-date Local Docs for Coding のツール

ツール一覧はまだありません

この掲載には表示できるツール一覧がまだありません。サーバーにツールがないという意味ではありません。対応機能はプロジェクトのドキュメントをご確認ください。

上のボタンで一時的なサンドボックスでこのサーバーを実行し、ツール一覧を取得できます。

概要

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

よくある質問

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.

「メモリとナレッジ」の他のコンテンツ

Tempreon

Person-owned, portable AI memory served over MCP. Your knowledge, preferences, and decisions — captured in one assistant, available in all of them.

Leviathan Systems Public Content MCP

Leviathan Systems

Search published GPU deployment, rack integration and structured cabling resources; read canonical documents and Leviathan Systems company service scope. Anonymous, read-only Streamable HTTP MCP. No credentials required.

PLUR

plur-ai

AI agents start every session with amnesia — you re-explain the project, repeat your preferences, and correct the same mistakes over and over. PLUR gives them a memory that persists. Your agent's corrections, preference

226