# mcp-server-pgvector

> mcp-server-pgvector — mittalpk-mcp-server-pgvector. Use this tool when you need to enable large language models (LLMs) to efficiently search, manage, and update vector embeddings in PostgreSQL databases. It solves problems related to similarity search, hybrid search, and index management, providing a seamless interface for LLM agents to interact with pgvector-backed embedding tables. Ideal for use cases requiring scalable and accurate vector search capabilities, such as information retrieval, recommendation systems, and natural language processing applications.

Canonical page: https://skillsregistry.net/skills/mittalpk-mcp-server-pgvector  
JSON: https://api.skillsregistry.net/v1/skills/mittalpk-mcp-server-pgvector

## Description

An MCP server that gives LLM agents first-class access to pgvector-backed embedding tables in PostgreSQL: similarity search, hybrid (vector + full-text) search, upserts, and HNSW/IVFFlat index management.

## Trust

- **Trust score (0–1):** 0.69
- **Verification tier:** scanned
- **Last scanned:** 2026-09-03

## Facts

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

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/nkwk3igrlr)
- **Repository:** <https://github.com/mittalpk/mcp-server-pgvector>

## 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": "mittalpk-mcp-server-pgvector"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/mittalpk-mcp-server-pgvector` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/mittalpk-mcp-server-pgvector/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