requesty.ai
Requesty is an AI gateway and LLM router that lets developers send requests to many model providers through one OpenAI- and Anthropic-compatible service. It also provides management, analytics, governance, and MCP gateway features for teams using AI tools and external servers.
Requesty exposes two authenticated HTTP APIs—a unified inference API and a management API—and documents an MCP Gateway for connecting AI tools to MCP servers, though its client connect endpoint/auth mechanics are not publicly specified.
- Requesty MCP Gatewaydiscovered
- Requesty Inference APIdiscovered
- Requesty Management APIdiscovered
Sign up at Requesty, then create a key on the API Keys page. Export it as REQUESTY_API_KEY for API clients, or use the same key as ANTHROPIC_AUTH_TOKEN when pointing Anthropic-compatible tools at Requesty. Service-account keys can also be created from Service Accounts via the API Keys page.
conventions · 4/8 published
- integrations.json✗
/.well-known/integrations.json - llms.txt✓https://requesty.ai/llms.txt
- API catalog✓https://requesty.ai/.well-known/api-catalog
- OpenAPI document✗
/api/schema/, /openapi.json, /swagger.json, /api/openapi.json, or /v1/openapi.json - MCP server card✗
/.well-known/mcp/server-card.json - OAuth protected resource✗
/.well-known/oauth-protected-resource - Agent card✓https://requesty.ai/.well-known/agent-card.json
- Agent skills✓https://requesty.ai/.well-known/agent-skills/index.json
Publish these signals → /publishing