←back to thread

Show HN: MCP Gateway – Unifying Access to MCP Servers Without N×M Integrations

(www.truefoundry.com)
10 points supreetgupta | 1 comments | 03 Dec 25 16:14 UTC | HN request time: 0.193s | source

Many teams connecting LLMs to external tools eventually encounter the same architectural issue: as more tools and agents are added, the integration pattern becomes an N×M mesh of direct connections. Each agent implements its own auth, retries, rate limiting, and logging; each tool needs credentials distributed to multiple places and observability becomes fragmented.

We built LLM gateway with this goal to provide a single place to manage authentication, authorization, routing, and observability for MCP servers, with a path toward a more general agent-gateway architecture in the future.

The system includes a central MCP registry, support for OAuth2/DCR integration, Virtual MCP Servers for curated toolsets, and a playground for experimenting with tool calls.

Resources -

Architecture Blog – Covers the N×M problem, gateway motivation, design choices, auth layers, Virtual MCP Servers, and the overall model.

https://www.truefoundry.com/blog/introducing-truefoundry-mcp...

Tutorial – Step-by-step guide to writing an MCP server, adding Okta-based OAuth, and integrating it with the Gateway.

https://docs.truefoundry.com/docs/ai-gateway/mcp-server-oaut...

Feedback on gaps and edge cases is welcome.

https://www.truefoundry.com/mcp-gateway

1. supreetgupta ◴[03 Dec 25 16:47 UTC] No.46136708[source]▶
A bit more context: this Gateway is part of a progression from an LLM Gateway - MCP Gateway - a future Agent Gateway. The intent is to provide a consistent control plane for tool access, authentication, and policies around agent execution. MCP offers a clean interoperability layer, so the Gateway focuses on security, observability, and operational consistency rather than tool-specific logic.

There are areas still evolving (more granular budget/rate controls, extended tool composition inside Virtual MCP Servers, richer audit traces). Input from people who’ve built multi-tool agent systems or worked with MCP at scale would be especially useful.

Refer to our roadmap here - https://www.truefoundry.com/roadmap