
Convex
Convex’s MCP server lets you introspect tables, call functions, and read/write data seamlessly. Agents can generate one-off queries safely—thanks to Convex’s sandboxed queries, ensuring data integrity. Perfect for AI automation, real-time apps, and dynamic data access.
get-convex
README
<p align="center"> <picture> <source media="(prefers-color-scheme: dark)" srcset="https://static-http.s3.amazonaws.com/logo/convex-logo-light.svg" width="600"> <source media="(prefers-color-scheme: light)" srcset="https://static-http.s3.amazonaws.com/logo/convex-logo.svg" width="600"> <img alt="Convex logo" src="https://static-http.s3.amazonaws.com/logo/convex-logo.svg" width="600"> </picture> </p>
Convex is the open-source reactive database designed to make life easy for web app developers, whether human or LLM. Fetch data and perform business logic with strong consistency by writing pure TypeScript.
Convex provides a database, a place to write your server functions, and client libraries. It makes it easy to build and scale dynamic live-updating apps. Read the docs to learn more.
Development of the Convex backend is led by the Convex team. We welcome bug fixes and love receiving feedback. We keep this repository synced with any internal development work within a handful of days.
Getting Started
Visit our documentation to learn more about Convex and follow our getting started guides.
The easiest way to build with Convex is through our cloud platform, which includes a generous free tier and lets you focus on building your application without worrying about infrastructure. Many small applications and side-projects can operate entirely on the free tier with zero cost and zero maintenance.
Self Hosting
The self-hosted product includes most features of the cloud product, including the dashboard and CLI. Self-hosted Convex works well with a variety of tools including Neon, Fly.io, Vercel, Netlify, RDS, Sqlite, Postgres, and more.
You can either use Docker (recommended) or a prebuilt binary to self host
Convex. Check out our self-hosting guide for detailed
instructions. Community support for self-hosting is available in the
#self-hosted
channel on Discord.
Community & Support
- Join our Discord community for help and discussions.
- Report issues when building and using the open source Convex backend through GitHub Issues
Building from source
See BUILD.md.
Disclaimers
- If you choose to self-host, we recommend following the self-hosting guide. If you are instead building from source, make sure to change your instance secret and admin key from the defaults in the repo.
- Convex is battle tested most thoroughly on Linux and Mac. On Windows, it has
less experience. If you run into issues, please message us on
Discord in the
#self-hosted
channel. - Convex self-hosted builds contain a beacon to help Convex improve the improve
the product. The information is minimal and anonymous and helpful to Convex,
but if you really want to disable it, you can set the
--disable-beacon
flag on the backend binary. The beacon's messages print in the log and only include- A random identifier for your deployment (not used elsewhere)
- Migration version of your database
- Git rev of the backend
- Uptime of the backend
Repository layout
-
crates/
contains Rust code- Main binary
local_backend/
is an application server on top of theRuntime
. This is the serving edge for the Convex cloud.
- Main binary
-
npm-packages/
contains both our public and internal TypeScript packages.- Internal packages
udf-runtime/
sets up the user-defined functions JS environment for queries and mutationsudf-tests/
is a collection of functions used in testing the isolate layersystem-udfs/
contains functions used by the Convex system e.g. the CLI
- Internal packages
Recommended Servers

VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
AIO-MCP Server
🚀 All-in-one MCP server with AI search, RAG, and multi-service integrations (GitLab/Jira/Confluence/YouTube) for AI-enhanced development workflows. Folk from
Persistent Knowledge Graph
An implementation of persistent memory for Claude using a local knowledge graph, allowing the AI to remember information about users across conversations with customizable storage location.
Hyperbrowser MCP Server
Welcome to Hyperbrowser, the Internet for AI. Hyperbrowser is the next-generation platform empowering AI agents and enabling effortless, scalable browser automation. Built specifically for AI developers, it eliminates the headaches of local infrastructure and performance bottlenecks, allowing you to

Any OpenAI Compatible API Integrations
Integrate Claude with Any OpenAI SDK Compatible Chat Completion API - OpenAI, Perplexity, Groq, xAI, PyroPrompts and more.
Exa MCP
A Model Context Protocol server that enables AI assistants like Claude to perform real-time web searches using the Exa AI Search API in a safe and controlled manner.
BigQuery
This is a server that lets your LLMs (like Claude) talk directly to your BigQuery data! Think of it as a friendly translator that sits between your AI assistant and your database, making sure they can chat securely and efficiently.
Web Research Server
A Model Context Protocol server that enables Claude to perform web research by integrating Google search, extracting webpage content, and capturing screenshots.