# VecGrep

> Use this tool when you need to efficiently search and retrieve relevant code snippets, reducing unnecessary token usage. VecGrep solves the problem of sifting through large codebases by returning top relevant code chunks, making it ideal for developers and programmers. It takes in search queries as input and outputs concise, context-specific code excerpts, streamlining the coding process.

Canonical page: https://skillsregistry.net/skills/vecgrep-vecgrep  
JSON: https://api.skillsregistry.net/v1/skills/vecgrep-vecgrep

## Description

Semantic code search MCP server that reduces token usage by ~95% by returning top relevant code chunks instead of full files.

## Trust

- **Trust score (0–1):** 0.68
- **Verification tier:** scanned
- **Last scanned:** 2026-09-03

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** search
- **Updated:** 2026-09-03

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/ajfwpofwqz)
- **Repository:** <https://github.com/VecGrep/vecgrep>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "vecgrep-vecgrep"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/vecgrep-vecgrep` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/vecgrep-vecgrep/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt