"Postgres" matching MCP servers:

Enables read-only SQL analytics and ALS collaborative filtering recommendations on a Postgres e-commerce database.

An AI database assistant that connects AI clients to a PostgreSQL database for schema exploration, safe querying, and LLM-powered SQL generation and reasoning.

Agentic data quality MCP server — runs structured validation rules against warehouses (DuckDB, BigQuery, Athena, Databricks, Postgres), diagnoses failures with LLM root cause analysis, and proposes SQL remediations. Full audit trail of every AI decision.

It connects an agent to a PostgreSQL database so it can inspect schemas, run validated reads and writes, resolve fuzzy names via trigram search, and perform or store pgvector embedding searches. Vector and hybrid search operate through an OpenAI-compatible embeddings endpoint, letting agents query by text without handling embedding arrays.

Enables natural language interaction with PostgreSQL databases, converting questions into safe, validated SQL queries and returning verified results.

Enables natural language interaction with PostgreSQL databases, converting questions to safe SQL queries and executing them with result validation.

The agent-native cloud: provision Postgres-compatible databases, deploy services and functions in isolated microVMs, manage storage, auth and AI inference, and read logs and billing — 50 tools behind one API key. Hosted remote server; this repository carries the connection docs.

Access control for text-to-SQL agents. Before the model sees the schema, schemagate keeps only the tables and columns the caller may read, picks the few a question needs, and refuses hidden ones at query time. Postgres, Oracle, MySQL, SQL Server, SQLite. Quantum-safe signed audit log. Try it in your browser: https://ashishsinha1602.github.io/schemagate/

Self-hosted long-term memory for AI agents on your own Postgres. Facts are dated, versioned and superseded rather than silently overwritten, every recall ships with an inspectable trace, and agents can correct wrong memories from inside the conversation.

Enables conversational management of Postgres-backed project data, off-limits rules, and hook styles, plus logging TikTok view counts and correlating performance by creative direction, hook style, or video-gen model. It also provides a sandbox to invoke Direction, Hook, and Script agents directly for prompt iteration without a full Telegram approval loop.

Exposes PostgreSQL database operations as tools for AI assistants, allowing execution of SQL queries and inspection of database schema.

MCP server for capturing and classifying daily expenses, built with Node.js and TypeScript, using Postgres and optional LLM-based classification.