πŸ—„οΈ

Pgvector

🟑Caution
Data & Storage

Provides semantic search capabilities for PostgreSQL databases using the pgvector extension, with support for multiple embedding providers.

STEP 1

Understand what it does

Tell your agent things like:

β†’β€œuse pgvector”
β†’β€œquery database”
β†’β€œstore data”
β†’β€œmanage records”
PERMISSIONS

What this capability can access

This capability requires the following permissions:

This capability can modify data or communicate externally. Review the permissions below before granting access.

πŸ”‘
Requires API Keys
Needs authentication credentials
πŸ“–
Read Files
Reads local files and directories
🌐
Read External Data
Fetches data from external sources
πŸ“€
Send Data Externally
Sends data to external services
πŸ“±
Social Media Posting
Posts publicly on social media
STEP 2

Set it up

Available on 2 platforms. Pick yours:

MCP (Model Context Protocol)Docs

Add to your MCP client configuration:

{
  "mcpServers": {
    "pgvector": {
      "command": "npx",
      "args": ["-y", "@modelcontextprotocol/server-pgvector"]
    }
  }
}
LangChainDocs
$ pip install langchain-community
from langchain_community.tools import ...
# See docs for specific import
STEP 3

Go deeper

Full documentation and source code

Add to your README

Show that your tool is listed on AgentSift

Pgvector trust score on AgentSift
[![AgentSift](https://agentsift.com/api/badge/capability/pgvector)](https://agentsift.com/capabilities/pgvector)

Options: ?style=flat-square for square corners, ?score=false for simple β€œlisted” badge

#mcp#data#agent-tool

Related capabilities