#134 · Primary category: AI Gateway & API Infrastructure
gateway
Universal MCP-Server for your Databases optimized for LLMs and AI-Agents.
Project last updated:07/18/25
GitHub Stars
546
Forks
65
Contributors
11
License
Apache-2.0
Why we included this project
Most teams that want LLM agents to query their database end up hand-writing a pile of API endpoints. This project skips that: point it at a supported store such as PostgreSQL, MySQL, ClickHouse, or Snowflake, and it inspects the schema, runs one LLM pass to generate an API configuration, then serves the data over REST or the Model Context Protocol. Tools like Cursor or Claude Desktop can then call your database as a function without any custom glue code. It also handles the production concerns that usually get deferred, including PII redaction via regex or Microsoft Presidio, row-level access control, API-key and OAuth auth, OpenTelemetry tracing, and caching. If you want a controlled, auditable way to let agents touch real data, the built-in security and compliance features are worth a look before you wire agents straight to the database.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
OmniRoute
Open-source AI gateway: one endpoint, 290+ providers (90+ free), 500+ models, auto-fallback, token compression, MCP/A2A, works with Claude Code, Codex, Cursor, Cline, Copilot.
CLIProxyAPI
Wrap Antigravity, ChatGPT Codex, Claude Code, Grok Build as an OpenAI/Gemini/Claude/Codex compatible API service, allowing you to enjoy the free Gemini 3.1 Pro, GPT 5.6 Series, Grok 4.5, Claude model through API
kong
🦍 The API and AI Gateway
novu
The open-source communication infrastructure for agents and products
GPT_API_free
Free API for large models, supports GPT, DeepSeek, etc., 10k free points daily, paid plans at 10-20% of official price.