vector-search-workflows

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Vector Search Workflows (MCP Vector Search)

向量搜索工作流（MCP Vector Search）

Overview

概述

Use

mcp-vector-search

to index codebases into ChromaDB and search via semantic embeddings. The recommended flow is

setup

(init + index + MCP integration), then

search

, and use

index

auto-index

to keep data fresh.

使用

mcp-vector-search

将代码库索引到ChromaDB中，并通过语义嵌入进行搜索。推荐流程为：先执行

setup

（初始化+建索引+MCP集成），再执行

search

，后续使用

index

或

auto-index

保持数据最新。

Quick Start

快速开始

bash

pip install mcp-vector-search
mcp-vector-search setup
mcp-vector-search search "authentication logic"

setup

detects languages, initializes config, indexes the repo, and configures MCP integrations (Claude Code, Cursor, etc.).

bash

pip install mcp-vector-search
mcp-vector-search setup
mcp-vector-search search "authentication logic"

setup

会自动检测语言、初始化配置、为当前代码仓库构建索引，同时配置MCP集成（支持Claude Code、Cursor等）。

Core Commands

核心命令

Indexing

索引管理

bash

mcp-vector-search index
mcp-vector-search index --force
mcp-vector-search index reindex --all --force
mcp-vector-search index reindex path/to/file.py

bash

mcp-vector-search index
mcp-vector-search index --force
mcp-vector-search index reindex --all --force
mcp-vector-search index reindex path/to/file.py

Auto-Index Strategies

自动索引策略

bash

mcp-vector-search auto-index setup --method all
mcp-vector-search auto-index status
mcp-vector-search auto-index check --auto-reindex --max-files 10
mcp-vector-search auto-index teardown --method all

bash

mcp-vector-search auto-index setup --method all
mcp-vector-search auto-index status
mcp-vector-search auto-index check --auto-reindex --max-files 10
mcp-vector-search auto-index teardown --method all

Search

搜索功能

bash

mcp-vector-search search "error handling patterns"
mcp-vector-search search "vector store initialization"

bash

mcp-vector-search search "error handling patterns"
mcp-vector-search search "vector store initialization"

Status + Doctor

状态与健康检查

bash

mcp-vector-search status
mcp-vector-search doctor

bash

mcp-vector-search status
mcp-vector-search doctor

MCP Integration Pattern

MCP集成模式

setup

uses native

claude mcp add

when available, otherwise falls back to

.mcp.json

Typical

.mcp.json

entry:

json

{
  "mcpServers": {
    "mcp-vector-search": {
      "type": "stdio",
      "command": "uv",
      "args": ["run", "mcp-vector-search", "mcp"],
      "env": {
        "MCP_ENABLE_FILE_WATCHING": "true"
      }
    }
  }
}

当环境支持原生

claude mcp add

命令时，

setup

会优先调用该命令完成集成，否则回退到通过

.mcp.json

配置的方式。

典型的

.mcp.json

配置项如下：

json

{
  "mcpServers": {
    "mcp-vector-search": {
      "type": "stdio",
      "command": "uv",
      "args": ["run", "mcp-vector-search", "mcp"],
      "env": {
        "MCP_ENABLE_FILE_WATCHING": "true"
      }
    }
  }
}

Reindex Triggers

重建索引触发场景

Dependency updates or parser changes
Large refactors
Adding new languages or file extensions
Tool upgrades (version tracking triggers reindex)

依赖更新或解析器变更
大规模代码重构
新增支持的语言或文件扩展名
工具升级（版本追踪机制会自动触发重建索引）

Local Patterns

本地使用最佳实践

Use
```
uv
```
for dev installs:
```
uv sync --dev
```
Use
```
setup --force
```
to rebuild config + index after tool upgrades
Keep file watching on via
```
MCP_ENABLE_FILE_WATCHING=true
```

开发环境安装使用
```
uv
```
：
```
uv sync --dev
```
工具升级后使用
```
setup --force
```
命令重建配置和索引
通过设置
```
MCP_ENABLE_FILE_WATCHING=true
```
开启文件监听功能

vector-search-workflows

Original

Translation

Vector Search Workflows (MCP Vector Search)

向量搜索工作流（MCP Vector Search）

Overview

概述

Quick Start

快速开始

Core Commands

核心命令

Indexing

索引管理

Auto-Index Strategies

自动索引策略

Search

搜索功能

Status + Doctor

状态与健康检查

MCP Integration Pattern

MCP集成模式

Reindex Triggers

重建索引触发场景

Local Patterns

本地使用最佳实践

Related Skills

相关技能