📡 MCP Radar

VeyraX/veyrax-platform

Open-source tool-calling platform for AI agents: 80+ integrations with OAuth, MCP server deployment, memory and agent flows.

⭐ 6 stars
⑂ 1 forks
Python
momentum ▲ 32.0
created 2026-10-12
on radar since 2026-10-13
star trend 5 → 6 since 2026-10-13
agent-infrastructureai-agentsfastapifunction-callingintegrationsllmmcpmodel-context-protocolnextjsoauthself-hostedtool-calling
View on GitHub ↗

About veyrax-platform

One API key. 80+ tools. Any AI agent. Open-source tool calling, OAuth, MCP, memory and flows for Claude, Cursor and your own LLM apps.

Quickstart · How it works · Integrations · Architecture · Contributing

VeyraX is an infrastructure layer that connects AI agents to the tools people actually use. One API key gives an agent (Claude, Cursor, your own LLM app) authenticated access to 80+ integrations and thousands of MCP servers, plus long-term memory and multi-step automation flows.

[!TIP] If VeyraX is useful to you, give it a ⭐. It helps other people find the project.

The agent calls a tool through VeyraX; VeyraX authenticates on behalf of the user, calls the underlying API and returns both structured data and a ready-to-render UI component.

- Tool calling API — a single, uniform interface (/tools, /tool-call/{tool}/{method}) over 80+ integrations: Gmail, Google Calendar/Drive/Docs/Sheets, Slack, Notion, Linear, Jira, Confluence, GitHub, Outlook, Dropbox, Asana, Trello, Figma, Airtable, Vercel, Sentry, PostgreSQL, ClickHouse, Snowflake, Perplexity, Tavily, Exa, Firecrawl, Browserbase, E2B and many more (see aciserver/integrations). - OAuth & credential management — users connect their accounts once; tokens and API keys are stored encrypted (AES) and injected into tool calls on their behalf. - MCP — expose all connected tools to MCP clients, and deploy any GitHub-hosted MCP server "in two clicks" (Dockerfile generation, build via GitHub Actions, push to Docker Hub). - Memory — retain information automatically across user requests and make it available to any agent. - Flo

From the project README.

Maintaining this server?

Add the radar badge to your README — it shows your project was picked up by MCP Radar and links to this page:

[![On MCP Radar](https://mcp.liqiwa.com/badge.svg)](https://mcp.liqiwa.com/s/VeyraX--veyrax-platform.html)

Related MCP servers

Ignitic-AI/ignitic

AI agents that run your e-commerce ops — Shopify, ads, CRM & support via 190+ MCP tools. Open-source, self-hosted, one docker compose up.

⭐ 7TypeScript
dhpradeep/aegis

Turn your Claude subscription into a multi-tenant agent API with rate limits, cost tracking, autonomous objectives, and an admin dashboard. Self-hostable, no API key.

⭐ 6Python
AdamRussak/self-doc

Self-hosted documentation RAG pipeline that serves semantic search to LLM agents over the Model Context Protocol.

⭐ 3Python
bybit-exchange/kaas

Turn scattered notes, docs and transcripts into a queryable Markdown wiki — an LLM knowledge-base compiler with MCP access, no embeddings, self-hosted.

⭐ 82Python
CTRLRun/ctrlrun

The execution safety layer for AI agents.

⭐ 14Python
batrapulkit/squidbrake

Brakes for your AI agents: every tool call is checked against your rules, held for human approval when risky, and recorded in a tamper-evident audit trail. Works with Claude Code and any MCP app.

⭐ 12Python

📬 Get the weekly radar in your inbox

The top new MCP servers of the week, every Monday. No spam, unsubscribe anytime.