広告掲載
MCP.so
ログイン
S

Semantic Context MCP Server

@zishengwu

リポジトリ

基本情報

カテゴリ

メモリとナレッジ

トランスポート

stdio

作者

zishengwu

投稿者

william cris

Semantic Context MCP Server について

A Model Context Protocol (MCP) server that leverages a vector database to efficiently index and query the codebase.

#semantic-context-mcp#code-search#vector-database

Semantic Context MCP Server 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": {
    "Semantic Context MCP Server": {
      "command": "fastmcp",
      "args": [
        "run",
        "your_code_base/semantic-context-mcp/vector_search/fast_mcp_server.py:mcp"
      ],
      "env": {
        "OPENAI_API_KEY": "your_api_key",
        "OPENAI_BASE_URL": "your_api_base_url",
        "OPENAI_MODEL_NAME": "your_embedding_model_name"
      }
    }
  }
}

Semantic Context MCP Server 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。

ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。

概要

What is Semantic Context MCP Server?

Semantic Context MCP Server is a Model Context Protocol (MCP) server that uses a vector database to index your codebase and perform semantic searches. It parses code into structural blocks (functions, classes), converts them to vector embeddings, and stores them locally, allowing you to find code snippets using natural language queries rather than keyword matching. The server runs in the background, automatically tracks file changes, and incrementally updates its index to keep context up-to-date.

How to use Semantic Context MCP Server?

Install by cloning the repository and setting environment variables for an OpenAI-compatible API (OPENAI_API_KEY, OPENAI_BASE_URL, OPENAI_MODEL_NAME). Configure the MCP JSON file in your IDE with the command fastmcp run pointing to the server script. The server provides three tools: full_index, status, and query. It automatically performs an initial full index and then runs periodic incremental updates every 5 minutes.

Key features of Semantic Context MCP Server

  • Incremental indexing using a Merkle Tree for efficient updates.
  • Multi-language AST parsing: Python, Java, C++, JavaScript, TypeScript, Go.
  • Semantic code search via natural language queries.
  • Background automation with periodic incremental updates every 5 minutes.
  • Local-first storage: all data kept in ~/.chromadb.

Use cases of Semantic Context MCP Server

  • Finding semantically relevant code snippets without manual keyword guessing.
  • Keeping code context automatically updated as you edit files.
  • Integrating semantic search into MCP-compatible IDEs.

よくある質問

1

What dependencies are required?

Python 3.8+ and an OpenAI-compatible API for generating embeddings. You must set `OPENAI_API_KEY`, `OPENAI_BASE_URL`, and `OPENAI_MODEL_NAME`.

2

Where is the indexed data stored?

All data (vector database and index metadata) is stored locally in the user’s home directory under `~/.chromadb`.

3

How does incremental indexing work?

A Merkle Tree built from file content hashes detects changes. Only added, modified, or deleted files are re-parsed and re-indexed, making the process efficient.

4

Which languages are supported for code parsing?

AST parsing supports Python, Java, C++, JavaScript, TypeScript, and Go.

5

How often does the server update its index?

It performs a full index on startup, then runs periodic incremental updates every 5 minutes.

コメント

「メモリとナレッジ」の他のコンテンツ

Takibi Base

Deian Isac

Ask your Takibi Base collections anything; get answers with cited passages and a support score.

M1K3

Round-Tower

Local AI agent for your Mac with a built-in MCP server: 18 tools for your notes and PDFs, a temporal memory graph, an on-device LLM and a neural voice. No account, no telemetry. No data centers required.

7

Snipara

alopez3006

MCP connector for Snipara, the Project Brain for AI coding agents

1

UmmahAPI

Yousuf Kazmi

Islamic source data for assistants: Quran, hadith, tafsir, duas, prayer times and qibla. Answers come from real sources with citations instead of recalled text, so verses and hadith are not hallucinated. 36,000+ hadiths

OpenLore

aakarim

Serve your docs to AI agents over SSH and MCP. Agents use ls, cat, grep, find, and pipes against a virtual filesystem backed by your documentation. Identity-scoped access, governed writing with human approval, and portab

66
広告掲載