Claude 6cc1c7d5

MCP搜索检索

提供方 未标注

搜索检索 stdio · 本地进程 Token 社区 / 第三方

全面解析Claude Context LocalMCP Server的核心功能、安装配置和实用案例。作为顶级Model Context Protocol服务器,Claude Context Local能让AI助手访问实时数据、执行操作,为您提供更智能的工作体验和自动化解决方案。

一句话选型结论

按资料字段整理

Claude 6cc1c7d5 属于搜索检索类 MCP 服务器,stdio · 本地进程,Token,没有现成安装命令,需按官方文档接入。接入前先确认权限范围;涉及写入、删除或付款的操作,建议先在测试环境验证。

分类搜索检索 传输方式stdio · 本地进程 鉴权Token 部署方式本地部署
GitHub 星标 未标注 仓库热度,无公开仓库时显示未标注
工具数 未标注 暴露给模型的工具数量
资源 / 提示词 0 / 0 资源与提示词模板数量
维护方 社区 / 第三方 核验等级 仅资料核对

工具与能力

搜索检索
数量来自来源目录的标注,具体工具清单以官方文档为准
工具数量未标注暴露给模型可调用的工具个数
资源数量0可读取的资源条目
提示词数量0内置提示词模板数量

能力标签

安装与配置

stdio · 本地进程 Token
客户端在本机拉起子进程,数据不出本机
  1. 1
    准备运行环境

    stdio 服务在本地起进程,需要先装好 Node.js 等运行时,再按安装命令拉取依赖。

  2. 2
    安装服务

    复制上面的安装命令执行;命令里带占位符的位置,换成自己的密钥或路径。

  3. 3
    写入客户端配置

    在客户端的 MCP 配置里填好启动命令和参数,保存后完全退出客户端再打开,让新配置生效。

  4. 4
    验证是否可用

    连接成功后随便调一个只读工具,确认能返回结果,再接入正式流程。

典型使用场景

3 类
按分类与标签整理的常见用法,具体以官方文档为准
联网搜索取证

让模型查最新资料并给出出处。

资料聚合

把一个主题的网页、文档集中抓回来整理。

情报与竞品检索

按关键词持续检索行业动态和竞品信息。

选择建议

选之前先看这几条
按条目字段给出的判断,不替你决定用不用

值得选的地方

  • 基础信息齐全,可以先按官方文档接入试跑。

先想清楚的地方

  • stdio 方式要求本地装好运行时(如 Node.js),换机器要重新装一遍。
  • 没有现成安装命令,需要按官方文档自己填启动命令和参数。
  • 使用前要准备好Token对应的凭据,并按最小权限配置。
  • 资料没标注工具数量,实际能力要装好后确认。
  • 版本更新与行为细节以官方仓库为准。

更适合

  • 需要在搜索检索场景里让模型直接调用外部能力的人。
  • 想先快速试一下、能接受在本地或自有环境跑服务的人。

不太适合

  • 完全不想在本地装环境的人。
  • 不方便管理密钥或第三方授权的人。
  • 需要厂商级 SLA 和技术支持的生产环境。

同类对比

6 个同类
同分类里挑最接近的几条,字段以各自详情页为准
MCP 服务器工具数传输方式部署方式安装命令最后核验
Claude 6cc1c7d5当前 未标注 stdio · 本地进程 本地部署 无 2026-05-17
Brave Search 433812ff 2 未标注 未标注 无 2026-05-17
Sequentialthinking 1 SSE · 服务端推送 远程部署 有 2026-05-18
Baidu Netdisk 未标注 未标注 未标注 无 2026-05-17
ragflow 未标注 stdio · 本地进程 本地部署 有 2026-04-11
mindsdb (430e18) 未标注 未标注 未标注 有 2026-05-17

服务器档案

搜索检索
字段来自项目仓库与公开索引,中文说明由本站标注
提供方未标注上游标注的维护方 未标注
分类搜索检索本站按上游分类展示
连接方式stdio · 本地进程客户端在本机拉起子进程,数据不出本机
鉴权方式Token远程服务建议用最小权限凭据
维护方社区 / 第三方核验等级 仅资料核对
包名 / 运行时未标注 · 未标注本地安装时用到的包标识与运行时
部署类型本地部署上游给出的部署形态
最近核验2026-05-17上游最后核验时间

详细介绍

13.0 KB
来自项目仓库与上游目录的原文,未做删改
  ██████╗ ██╗       █████╗  ██╗   ██╗ ██████╗  ███████╗
 ██╔════╝ ██║      ██╔══██╗ ██║   ██║ ██╔══██╗ ██╔════╝
 ██║      ██║      ███████║ ██║   ██║ ██║  ██║ █████╗
 ██║      ██║      ██╔══██║ ██║   ██║ ██║  ██║ ██╔══╝
 ╚██████╗ ███████╗ ██║  ██║ ╚██████╔╝ ██████╔╝ ███████╗
  ╚═════╝ ╚══════╝ ╚═╝  ╚═╝  ╚═════╝  ╚═════╝  ╚══════╝

  ██████╗  ██████╗  ███╗   ██╗ ████████╗ ███████╗ ██╗  ██╗ ████████╗
 ██╔════╝ ██╔═══██╗ ████╗  ██║ ╚══██╔══╝ ██╔════╝ ╚██╗██╔╝ ╚══██╔══╝
 ██║      ██║   ██║ ██╔██╗ ██║    ██║    █████╗    ╚███╔╝     ██║
 ██║      ██║   ██║ ██║╚██╗██║    ██║    ██╔══╝    ██╔██╗     ██║
 ╚██████╗ ╚██████╔╝ ██║ ╚████║    ██║    ███████╗ ██╔╝ ██╗    ██║
  ╚═════╝  ╚═════╝  ╚═╝  ╚═══╝    ╚═╝    ╚══════╝ ╚═╝  ╚═╝    ╚═╝

 ██╗       ██████╗   ██████╗  █████╗  ██╗
 ██║      ██╔═══██╗ ██╔════╝ ██╔══██╗ ██║
 ██║      ██║   ██║ ██║      ███████║ ██║
 ██║      ██║   ██║ ██║      ██╔══██║ ██║
 ███████╗ ╚██████╔╝ ╚██████╗ ██║  ██║ ███████╗
 ╚══════╝  ╚═════╝   ╚═════╝ ╚═╝  ╚═╝ ╚══════╝

Claude Context without the cloud. Semantic code search that runs 100% locally using EmbeddingGemma. No API keys, no costs, your code never leaves your machine.

  • 🔍 Find code by meaning, not strings
  • 🔒 100% local - completely private
  • 💰 Zero API costs - forever free
  • ⚡ Fewer tokens in Claude Code and fast local searches

🚧 Beta Release

  • Core functionality working
  • Installation tested on Mac/Linux
  • Benchmarks coming soon
  • Please report issues!

Demo

Features

  • Intelligent chunking: AST-based (Python) + tree-sitter (JS/TS/Go/Java/Rust/C/C++/C#)
  • Semantic search: Natural language queries to find code across all languages
  • Rich metadata: File paths, folder structure, semantic tags, language-specific info
  • MCP integration: Direct integration with Claude Code
  • Local processing: All embeddings stored locally, no API calls
  • Fast search: FAISS for efficient similarity search

Why this

Claude’s code context is powerful, but sending your code to the cloud costs tokens and raises privacy concerns. This project keeps semantic code search entirely on your machine. It integrates with Claude Code via MCP, so you keep the same workflow—just faster, cheaper, and private.

Requirements

  • Python 3.12+
  • Disk: 1–2 GB free (model + caches + index)
  • Optional: NVIDIA GPU (CUDA 11/12) for FAISS acceleration; Apple Silicon (MPS) for embedding acceleration. These also speed up running the embedding model with SentenceTransformer, but everything still works on CPU.

Install & Update

Install (one‑liner)```bash

curl -fsSL https://raw.githubusercontent.com/FarhanAliRaza/claude-context-local/main/scripts/install.sh | bash


If your system doesn't have `curl`, you can use `wget`:```bash
wget -qO- https://raw.githubusercontent.com/FarhanAliRaza/claude-context-local/main/scripts/install.sh | bash

Update existing installation

Run the same install command to update:```bash
curl -fsSL https://raw.githubusercontent.com/FarhanAliRaza/claude-context-local/main/scripts/install.sh | bash


The installer will:

- Detect your existing installation
- Preserve your embeddings and indexed projects in `~/.claude_code_search`
- Stash any local changes automatically (if running via curl)
- Update the code and dependencies

### What the installer does

- Installs `uv` if missing and creates a project venv
- Clones/updates `claude-context-local` in `~/.local/share/claude-context-local`
- Installs Python dependencies with `uv sync`
- Downloads the EmbeddingGemma model (~1.2–1.3 GB) if not already cached
- Tries to install `faiss-gpu` if an NVIDIA GPU is detected (interactive mode only)
- **Preserves all your indexed projects and embeddings** across updates

## Quick Start

### 1) Register the MCP server (stdio)```bash
claude mcp add code-search --scope user -- uv run --directory ~/.local/share/claude-context-local python mcp_server/server.py

Then open Claude Code; the server will run in stdio mode inside the uv environment.

2) Index your codebase

Open Claude Code and say: index this codebase. No manual commands needed.

3) Use in Claude Code

Interact via chat inside Claude Code; no function calls or commands are required.

Architecture```

claude-context-local/
├── chunking/ # Multi-language chunking (15 extensions)
│ ├── multi_language_chunker.py # Unified orchestrator (Python AST + tree-sitter)
│ ├── python_ast_chunker.py # Python-specific chunking (rich metadata)
│ └── tree_sitter.py # Tree-sitter: JS/TS/JSX/TSX/Svelte/Go/Java/Rust/C/C++/C#
├── embeddings/
│ └── embedder.py # EmbeddingGemma; device=auto (CUDA→MPS→CPU); offline cache
├── search/
│ ├── indexer.py # FAISS index (CPU by default; GPU when available)
│ ├── searcher.py # Intelligent ranking & filters
│ └── incremental_indexer.py # Merkle-driven incremental indexing
├── merkle/
│ ├── merkle_dag.py # Content-hash DAG of the workspace
│ ├── change_detector.py # Diffs snapshots to find changed files
│ └── snapshot_manager.py # Snapshot persistence & stats
├── mcp_server/
│ └── server.py # MCP tools for Claude Code (stdio/HTTP)
└── scripts/
├── install.sh # One-liner remote installer (uv + model + faiss)
├── download_model_standalone.py # Pre-fetch embedding model
└── index_codebase.py # Standalone indexing utility


### Data flow```mermaid
graph TD
    A["Claude Code (MCP client)"] -->|index_directory| B["MCP Server"]
    B --> C{IncrementalIndexer}
    C --> D["ChangeDetector<br/>(Merkle DAG)"]
    C --> E["MultiLanguageChunker"]
    E --> F["Code Chunks"]
    C --> G["CodeEmbedder<br/>(EmbeddingGemma)"]
    G --> H["Embeddings"]
    C --> I["CodeIndexManager<br/>(FAISS CPU/GPU)"]
    H --> I
    D --> J["SnapshotManager"]
    C --> J
    B -->|search_code| K["Searcher"]
    K --> I

Intelligent Chunking

The system uses advanced parsing to create semantically meaningful chunks across all supported languages:

Chunking Strategies

  • Python: AST-based parsing for rich metadata extraction
  • All other languages: Tree-sitter parsing with language-specific node type recognition

Chunk Types Extracted

  • Functions/Methods: Complete with signatures, docstrings, decorators
  • Classes/Structs: Full definitions with member functions as separate chunks
  • Interfaces/Traits: Type definitions and contracts
  • Enums/Constants: Value definitions and module-level declarations
  • Namespaces/Modules: Organizational structures
  • Templates/Generics: Parameterized type definitions

Rich Metadata for All Languages

  • File path and folder structure
  • Function/class/type names and relationships
  • Language-specific features (async, generics, modifiers, etc.)
  • Parent-child relationships (methods within classes)
  • Line numbers for precise code location
  • Semantic tags (component, export, async, etc.)

Configuration

Environment Variables

  • CODE_SEARCH_STORAGE: Custom storage directory (default: ~/.claude_code_search)

Model Configuration

The system uses google/embeddinggemma-300m by default.

Notes:

  • Download size: ~1.2–2 GB on disk depending on variant and caches
  • Device selection: auto (CUDA on NVIDIA, MPS on Apple Silicon, else CPU)
  • You can pre-download via installer or at first use
  • FAISS backend: CPU by default. If an NVIDIA GPU is detected, the installer
    attempts to install faiss-gpu-cu12 (or faiss-gpu-cu11) and the index will
    run on GPU automatically at runtime while saving as CPU for portability.

Hugging Face authentication (if prompted)

The google/embeddinggemma-300m model is hosted on Hugging Face and may require
accepting terms and/or authentication to download.

  1. Visit the model page and accept any terms:
  • https://huggingface.co/google/embeddinggemma-300m
  1. Authenticate one of the following ways:
  • CLI (recommended):bash uv run huggingface-cli login # Paste your token from https://huggingface.co/settings/tokens

  • Environment variable:bash export HUGGING_FACE_HUB_TOKEN=hf_XXXXXXXXXXXXXXXXXXXXXXXX

After the first successful download, we cache the model under ~/.claude_code_search/models
and prefer offline loads for speed and reliability.

Supported Languages & Extensions

Fully Supported (15 extensions across 9+ languages):

Language Extensions
Python .py
JavaScript .js, .jsx
TypeScript .ts, .tsx
Java .java
Go .go
Rust .rs
C .c
C++ .cpp, .cc, .cxx, .c++
C# .cs
Svelte .svelte

Total: 15 file extensions across 9+ programming languages

Storage

Data is stored in the configured storage directory:~/.claude_code_search/ ├── models/ # Downloaded models ├── index/ # FAISS indices and metadata │ ├── code.index # Vector index │ ├── metadata.db # Chunk metadata (SQLite) │ └── stats.json # Index statistics

Performance

  • Model size: ~1.2GB (EmbeddingGemma-300m and caches)
  • Embedding dimension: 768 (can be reduced for speed)
  • Index types: Flat (exact) or IVF (approximate) based on dataset size
  • Batch processing: Configurable batch sizes for embedding generation

Tips:

  • First index on a large repo will take time (model load + chunk + embed). Subsequent runs are incremental.
  • With GPU FAISS, searches on large indexes are significantly faster.
  • Embeddings automatically use CUDA (NVIDIA) or MPS (Apple) if available.

Troubleshooting

Common Issues

  1. Import errors: Ensure all dependencies are installed with uv sync
  2. Model download fails: Check internet connection and disk space
  3. Memory issues: Reduce batch size in indexing script
  4. No search results: Verify the codebase was indexed successfully
  5. FAISS GPU not used: Ensure nvidia-smi is available and CUDA drivers are installed; re-run installer to pick faiss-gpu-cu12/cu11.
  6. Force offline: We auto-detect a local cache and prefer offline loads; you can also set HF_HUB_OFFLINE=1.

Ignored directories (for speed and noise reduction)

node_modules, .venv, venv, env, .env, .direnv, __pycache__, .pytest_cache, .mypy_cache, .ruff_cache, .pytype, .ipynb_checkpoints, build, dist, out, public, .next, .nuxt, .svelte-kit, .angular, .astro, .vite, .cache, .parcel-cache, .turbo, coverage, .coverage, .nyc_output, .gradle, .idea, .vscode, .docusaurus, .vercel, .serverless, .terraform, .mvn, .tox, target, bin, obj

Contributing

This is a research project focused on intelligent code chunking and search. Feel free to experiment with:

  • Different chunking strategies
  • Alternative embedding models
  • Enhanced metadata extraction
  • Performance optimizations

License

Licensed under the GNU General Public License v3.0 (GPL-3.0). See the LICENSE file for details.

Inspiration

This project draws inspiration from zilliztech/claude-context. I adapted the concepts to a Python implementation with fully local embeddings.

常见问题

7 问
答案由本站依据条目字段整理,不引用上游原文
Claude 6cc1c7d5 怎么安装?

资料没有给出安装命令,请到官方仓库或文档按说明接入;这类条目多数是生态应用,或尚未发布可安装包。

Claude 6cc1c7d5 怎么在客户端里配置?

它的传输方式未标注,在客户端 MCP 配置里按官方文档填写启动命令和参数,保存后重启客户端生效。

Claude 6cc1c7d5 收费吗?

本站不代收费用,也没有标注具体价格。是否收费取决于服务本身和背后的接口额度,正式使用前按官方说明确认。

Claude 6cc1c7d5 需要 API Key 吗?

资料标注需要Token认证,使用前准备好对应凭据,并按最小权限配置。

Claude 6cc1c7d5 能提供哪些能力?

资料显示能力标签包括 本地运行、代码索引、搜索。具体工具清单以官方文档为准。

Claude 6cc1c7d5 需要什么运行环境?

属于本地进程,需要在本机装好运行环境。

Claude 6cc1c7d5 是本地还是远程?

它是本地进程(stdio),由客户端在本机拉起。传输方式为stdio · 本地进程。

热门专题

按标签挑服务器
全部专题 →

服务器信息以作者仓库与官方文档为准;分类、传输方式与鉴权方式的中文说明为中文整理,最近核验 2026-05-17。