$ loading_
Route prompts across LLM providers with policy-based orchestration and verification.
Copy the install command and let the AI configure it · recommended for beginners
No copy-paste install info for "llm-gateway-mcp" yet — see the docs or source repo.
Design a declarative routing policy for llm-gateway-mcp: send everyday Q&A to a low-cost model, code generation to a high-quality model, and require verification for sensitive tasks. Include example configuration.
A clear routing policy and sample configuration covering model selection, triggers, and verification rules.
I want to self-host llm-gateway-mcp. Give me deployment steps, required environment variables, common LLM provider integration methods, and production security recommendations.
An actionable deployment guide with integration setup, operational notes, and security hardening advice.
Design a multi-role workflow for llm-gateway-mcp: one model drafts the answer, another independently reviews and corrects it. Provide the workflow description and prompt templates.
A multi-role orchestration plan with role responsibilities, execution order, and reusable prompt templates.
Route LLM requests across providers and orchestrate MCP tools with local privacy.
Route LLM completion requests to OpenAI-compatible providers through MCP tools.
Access multiple LLM providers through one encrypted OpenAI-compatible gateway.
Turn multiple LLMs into MCP tools with JSON, no Python required.
Connect multiple MCP servers through one gateway for unified tool access.
Turn OpenAPI specs into MCP servers for LLM access to REST APIs.