# cocoindex MCP

> Use this tool when you need to incrementally index large repositories and documents for efficient semantic search. It solves problems of slow and inaccurate search by leveraging CocoIndex and pgvector to enable fast and relevant query results. The tool takes in repository and document data as input and outputs searchable indexes, ideal for use cases requiring intelligent information retrieval.

Canonical page: https://skillsregistry.net/skills/datarian-mcp-coco  
JSON: https://api.skillsregistry.net/v1/skills/datarian-mcp-coco

## Description

An MCP server that incrementally indexes repositories and documents into a Postgres + pgvector store using CocoIndex, and exposes semantic search over them.

## Trust

- **Trust score (0–1):** 0.68
- **Verification tier:** scanned
- **Last scanned:** 2026-08-30

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** database
- **Updated:** 2026-08-30

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/vozxsvstjz)
- **Repository:** <https://github.com/datarian/mcp-coco>

## 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": "datarian-mcp-coco"
    }
  }
}
```

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