# io.github.roshunsunder/filesift

> Use this tool when you need to efficiently search and retrieve files from your local codebase using semantic and keyword indexing. It solves problems of file discovery and navigation, especially in large projects, by providing accurate and relevant search results. The tool takes in file directories and search queries as inputs and outputs relevant file paths and contents.

Canonical page: https://skillsregistry.net/skills/io-github-roshunsunder-filesift  
JSON: https://api.skillsregistry.net/v1/skills/io-github-roshunsunder-filesift

## Description

Local file search for AI agents — semantic + keyword indexing over your codebase.

## Trust

- **Trust score (0–1):** 0.55
- **Verification tier:** scanned
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-09-28

## Source

- **Source listing:** [MCP Registry](https://registry.modelcontextprotocol.io/v0/servers/io.github.roshunsunder%2Ffilesift)
- **Repository:** <https://github.com/roshunsunder/filesift>

## 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": "io-github-roshunsunder-filesift"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/io-github-roshunsunder-filesift` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/io-github-roshunsunder-filesift/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