About

Imported from bobmatnyc/claude-mpm-skills (toolchains/ai/techniques/vector-search-workflows/SKILL.md). Install upstream with npx skills add bobmatnyc/claude-mpm-skills --skill vector-search-workflows. Copyright stays with the author (MIT).

Vector Search Workflows (MCP Vector Search)

Name: vector-search-workflows
Author: bobmatnyc

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

Use it

Copy one of these into your project. Installing also returns the manifest and these snippets.

yaml

targets:
  - https://api.opensmartroute.ai/api/v1/registry/bobmatnyc-claude-mpm-skills-vector-search-workflows/manifest   # or paste the manifest below

Manifest

An Open Capability Manifest: the router reads it to know what this does, what it costs and when to pick it.

bobmatnyc-claude-mpm-skills-vector-search-workflows.ocm.jsonjson

{
  "ocm": "1",
  "id": "bobmatnyc-claude-mpm-skills-vector-search-workflows",
  "kind": "skill",
  "name": "vector-search-workflows",
  "description": "Vector search indexing and querying workflows using MCP Vector Search, including setup, reindexing, auto-index strategies, and MCP integration.",
  "publisher": "bobmatnyc",
  "version": "1.0.0",
  "capabilities": {
    "domains": [
      "general"
    ],
    "tags": [
      "skill-md",
      "vector-search",
      "embeddings",
      "indexing",
      "search",
      "mcp",
      "skills-sh"
    ],
    "languages": [
      "en"
    ]
  },
  "quality_prior": 0.6,
  "examples": [
    "Vector search indexing and querying workflows using MCP Vector Search, including setup, reindexing, auto-index strategies, and MCP integration."
  ],
  "primary": false,
  "metadata": {
    "source": {
      "provider": "skills.sh",
      "repository": "https://github.com/bobmatnyc/claude-mpm-skills",
      "path": "toolchains/ai/techniques/vector-search-workflows/SKILL.md",
      "ref": "HEAD",
      "url": "https://github.com/bobmatnyc/claude-mpm-skills/blob/HEAD/toolchains/ai/techniques/vector-search-workflows/SKILL.md",
      "key": "bobmatnyc/claude-mpm-skills/toolchains/ai/techniques/vector-search-workflows/SKILL.md"
    },
    "license": "MIT"
  },
  "instructions": "# Vector Search Workflows (MCP Vector Search)\n\n## Overview\n\nUse `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.\n\n## Quick Start\n\n```bash\npip install mcp-vector-search\nmcp-vector-search setup\nmcp-vector-search search \"authentication logic\"\n```\n\n`setup` detects languages, initializes config, indexes the repo, and configures MCP integrations (Claude Code, Cursor, etc.).\n\n## Core Commands\n\n### Indexing\n\n```bash\nmcp-vector-sear",
  "cost": {
    "context_tokens": 511
  }
}

Fetch it by URL: GET /api/v1/registry/bobmatnyc-claude-mpm-skills-vector-search-workflows/manifest?version=1.0.0

Reviews

Star ratings from people who tried it. One review per account; edit yours any time.

No reviews yet. Install it, try it, and be the first to rate it.