Postgres MCP Pro is a self-hosted MCP server that gives AI assistants access to PostgreSQL alongside tools for diagnosing slow queries and testing index recommendations. It's for developers and database maintainers who want their assistant to work with the database's actual schema, query statistics and execution plans. It runs through Docker or Python and is open source under the MIT license.
Its tuning tools use established search algorithms and PostgreSQL's query planner to evaluate candidate indexes. With hypopg, it can estimate how an index would affect a query before creating it. Workload analysis uses pg_stat_statements to identify queries that consume the most execution time; it can also recommend indexes for specific queries. These performance capabilities depend on the database extensions.
Access is configurable. Read/write mode lets an agent change data and schema, while restricted mode limits it to read-only transactions with execution time constraints. Schema inspection exposes tables, columns, constraints and existing indexes so an assistant has concrete context for writing SQL.
Health checks adapted from PgHero examine unused or invalid indexes, connection usage, buffer cache performance, vacuum health and sequence limits. The server works with Claude Desktop, Cursor, Windsurf and other MCP clients. It can run locally alongside a client or on a server shared by multiple clients through SSE.
Claim this page and we'll verify you by hand. Postgres MCP Pro gets the verified badge, and you can upgrade the listing to be featured on localhosted. Proud to be listed? Put our badge on your site.
Want more people to find Postgres MCP Pro?Promote it
Something wrong or outdated on this page?
2.4KUpdated 3 days agoAGPL-3.0
macOS · Windows · Web#Code execution#MCP#Multimodal input
PenEcho is an open-source workspace that puts handwritten notes, diagrams and AI-generated widgets on an infinite canvas. It runs on your computer as a macOS or Windows app, or through Node.js with a browser interface. It's for people who want to work through technical ideas visually and give AI feedback by drawing directly on the result.
17.8KUpdated 1 day ago
Web#Git integration#Guardrails#LLM tracing
Wren AI is a self-hosted data agent for teams and agent builders who need answers based on agreed business definitions. It turns plain-language questions into SQL and interactive dashboards, using the same definitions when someone asks directly or through Claude, ChatGPT or Gemini over MCP.
42Updated 12 hours ago
macOS · Windows · Linux · Docker#Agent Skills#Code execution#Distributed execution
27.3KUpdated 20 hours agoMIT
macOS · Windows · Linux#Code execution#MCP#Tool calling
37.7KUpdated 2 days agoApache-2.0
macOS · Windows · Linux · Docker#Code execution#LM Studio integration#MCP
2.8KUpdated 2 weeks agoApache-2.0
macOS · Windows · Linux · Docker · Web#Code execution#Git integration#Human approval
Code Buddy is an AI coding assistant for developers who want a terminal agent running on their own machine, with a choice of local or cloud models. It reads repositories, edits code and runs commands on Linux, macOS and Windows. Ollama keeps model inference local without an API key or account; cloud providers send model requests off the machine. Routing includes automatic provider failover.
Cua gives AI agents access to computers they can inspect and operate, with tools for desktop automation, local virtual machines, and hosted fleets. It's for developers building agents that work across native apps and browsers, or evaluating how well those agents complete computer tasks. You bring the agent and model.
Playwright MCP lets AI agents control a browser by reading structured page information rather than interpreting screenshots. It's for developers building browser automation, exploratory tests or agent workflows that need to keep a browser session open across repeated actions. The server runs locally on macOS, Windows and Linux, or as a self-hosted service.
Vexa is a meeting bot and transcription API for developers building meeting features and teams feeding calls into AI agents. Bots join Google Meet, Microsoft Teams and Zoom, then send live transcripts with speaker labels to your application or agent. You can host the full platform on your own infrastructure or use Vexa's cloud service.