Intelligent multi-provider agent routing MCP server — transparently switch between AI providers and models
Wellknown found it in public sources; nobody has proven control of it yet. Claiming takes one click if the repository is under your GitHub account, or a small file on your domain otherwise. Verified owners get the badge, 15-minute checks, status alerts, edits that outrank crawled data, and a ranking boost.
Agents can do it too: POST https://wellknown.network/api/v1/claims with {"agent":"switchboard-mcp","method":"well_known_file"} — machine-readable steps at claim.json, guide at /docs/claim.
Everything here was measured by our prober or read from a registry. Nothing is self-reported.
Attributed to the source that supplied each field. Treated as claims, not facts.
# Switchboard 🎛️ > Never let your AI coding agent hit a dead end again. [](https://pypi.org/project/switchboard-mcp/) [](https://www.python.org/downloads/) [](https://opensource.org/licenses/MIT) [](https://github.com/yourname/switchboard-mcp/actions) [](#cli-tester) A multi-provider AI routing layer that gives any MCP-compatible coding agent (Claude Code, Cursor, Windsurf) **unlimited flow** by transparently switching between AI providers when rate limits hit or when a better model exists for the task. --- ## The Problem It's 2am. You're deep in a coding session with Claude Code. You've got 80 messages of context, the agent is about to write the perfect solution — and then: > *"You've reached your message limit. Please upgrade your plan or wait."* The agent stops dead. Your flow is gone. You're staring at an error message instead of working code. **This shouldn't happen.** Your coding agent should never hit a wall because one provider said no. Switchboard fixes this. It sits between your coding agent and the AI providers, watching for rate limits, picking the best model for each task, and silently falling back to alternatives — all without the agent (or you) ever knowing a switch happened. --- ## How It Works ``` ┌──────────────────────────────────────────────────────────────────┐ │ YOUR WORKSTATION │ │ │ │ ┌─────────────┐ │ │ │ Your Agent │ Claude Code / Cursor / Windsurf │ │ │ (Claude etc)│ …
Mapped onto the structured taxonomy from declared text and observed tool names. Confidence shown for derived entries.
Every source is kept verbatim. Field changes are logged as events.