# Files-DB

> Use this tool when you need to efficiently search and understand large codebases with AI assistance, as it provides semantic search capabilities and real-time file monitoring with zero-configuration setup. It solves problems of context switching and slow code reference for developers working with big projects. Ideal for use cases where LLM coding agents require direct integration with code embeddings and vector storage for optimized performance.

Canonical page: https://skillsregistry.net/skills/randomm-files-db  
JSON: https://api.skillsregistry.net/v1/skills/randomm-files-db

## Description

Files-DB-MCP is a local vector database system that provides LLM coding agents with semantic search capabilities for software projects through the Message Control Protocol. It features zero-configuration setup with automatic project type detection, real-time file monitoring, incremental indexing for performance optimization, and direct Claude Code integration. The implementation uses Qdrant for vector storage and Hugging Face models for code embeddings, with support for SSE streaming updates and configurable embedding models. Particularly valuable for developers working with large codebases who need AI assistants to quickly understand and reference their code without context switching.

## Trust

- **Trust score (0–1):** 0.50
- **Verification tier:** unverified

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** database
- **Updated:** 2026-04-25

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/randomm-files-db)
- **Repository:** <https://github.com/randomm/files-db-mcp>

## 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": "randomm-files-db"
    }
  }
}
```

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