mcpField
V
vector-search-workflows

vector-search-workflows

github.com/bobmatnycDevelopment78319 installsUpdated 15w ago
Repository

About vector-search-workflows

A command-line workflow for indexing codebases in ChromaDB and searching them with semantic embeddings. It is intended for developers and includes setup, index maintenance, and integrations with MCP clients such as Claude Code and Cursor.

Key features

  1. 01Index codebases in ChromaDB
  2. 02Search with semantic embeddings
  3. 03Initialize configuration and index
  4. 04Reindex selected files or repositories
  5. 05Configure automatic indexing
  6. 06Check status and diagnose setup

Use cases

  1. 01Finding authentication logic in a repository
  2. 02Searching for error-handling patterns
  3. 03Refreshing indexes after refactoring
  4. 04Setting up MCP integration for a codebase

MCP support

The setup command configures MCP integrations, using `claude mcp add` when available or falling back to `.mcp.json`. The project can run as an MCP server over stdio.

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/bobmatnyc/claude-mpm-skills --skill vector-search-workflows

After installing, type/vector-search-workflowsin Claude Code to confirm it loaded.

Bundled filesmetadata.json

Details

From the project README

Vector Search Workflows (MCP Vector Search)

Overview

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 or auto-index to keep data fresh.

Quick Start

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.).

Core Commands

Indexing
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
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
mcp-vector-search search "error handling patterns"
mcp-vector-search search "vector store initialization"
Status + Doctor
mcp-vector-search status
mcp-vector-search doctor

MCP Integration Pattern

setup uses native claude mcp add when available, otherwise falls back to .mcp.json.

Typical .mcp.json entry:

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

Reindex Triggers

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

Local Patterns

  • 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

Related Skills

  • toolchains/ai/protocols/model-context
  • universal/main/model-context-builder

Comments

Markdown supported