portkey.ai
Portkey provides infrastructure for building and operating LLM applications and agents, including an AI gateway, MCP gateway, observability, guardrails, and related management features. It sits between client applications or agents and upstream AI or MCP providers to handle routing, authentication, access control, and logging.
Portkey exposes an authenticated HTTP inference API, an HTTP admin API, a remote MCP Gateway endpoint, and an npm-distributed CLI.
- Portkey Inference APIdiscovered
- Portkey Admin APIdiscovered
- Portkey CLIdiscovered
Sign up at Portkey or log in at Portkey, then open the API keys/settings area in the dashboard at app.portkey.ai/api-keys or the account Settings page referenced in the docs. Create a key, choose the needed permissions, name it, and save it. For MCP Gateway programmatic access, the docs specifically call for a workspace user API key with mcp invoke permission enabled.
Portkey supports JWT-based authentication for some integrations. Configure JWT/IdP-based auth through Portkey's MCP Gateway or enterprise identity setup as described in MCP Advanced Configuration and Authorization. This is typically obtained by signing users into your configured identity provider and having Portkey validate the token via your configured jwksUri.
conventions · 1/8 published
- integrations.json✗
/.well-known/integrations.json - llms.txt✓https://portkey.ai/llms.txt
- API catalog✗
/.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✗
/.well-known/agent-card.json - Agent skills✗
/.well-known/agent-skills/index.json
Publish these signals → /publishing