Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.portkey.ai/docs/llms.txt

Use this file to discover all available pages before exploring further.

The MCP Gateway is Portkey’s solution for managing access to MCP servers. It acts as a proxy between MCP Clients and MCP servers, handling authentication, access control, and logging. When connecting to MCP servers directly, each agent needs its own credentials and configuration for every server. With the MCP Gateway, clients authenticate once to Portkey. The Gateway handles credential injection, permission checks, and request logging for all configured servers.

Quickstart

Add an MCP server and connect an MCP client in 5 minutes.

Integrations

Connect Claude Desktop, Cursor, VS Code, or custom agents.

​
How It Works

Portkey MCP Gateway Architecture
When an AI Agent/MCP Client calls an MCP tool, the request flows through Portkey. The Gateway authenticates the request using the agent’s API key (or IdP token), checks whether that user has access to the requested server and tool, then injects the appropriate credentials for the upstream server—OAuth tokens for services like GitHub and Slack, API keys for public servers, or identity headers for internal servers. The request is proxied to the MCP server, and the full request/response is logged. This gives platform teams complete visibility into MCP usage—who accessed what, when, and with what parameters—while developers get access to tools without managing credentials or requesting permissions for each server.

​
Capabilities

Authentication

Configure OAuth, API keys, or custom headers per server. Supports external IdPs like Okta and Auth0.

Access Control

Control which workspaces and users can access each server.

Tool Provisioning

Enable or disable specific tools per user when a server exposes tools that shouldn’t be available to everyone.

Observability

Every tool call logged with user, parameters, and response. Filter by server, user, or time range.

Guardrails

Rate limits, content filters, and approval workflows per server.

​
Usage

Add an MCP server to your organization’s registry, configure its authentication, and provision access to workspaces. Then connect any MCP client to Portkey’s endpoint: 
{
  "mcpServers": {
    "portkey": {
      "url": "https://mcp.portkey.ai/{server-slug}/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_API_KEY"
      }
    }
  }
}
The API key determines which servers and tools are accessible. See Integrations for setup guides for Claude Desktop, Cursor, VS Code, and custom agents.

​
MCP Registry

The MCP Registry is where MCP servers are configured and managed. Add servers, set up authentication, and control which workspaces can access them.

MCP Registry

Add servers, configure authentication, and manage access.
For platform teams:
  • Add MCP servers (external services, internal APIs, or public servers)
  • Configure authentication (OAuth, API keys, custom headers)
  • Provision access to specific workspaces
  • View usage across the organization
For developers:
  • Browse available servers and tools in your workspace
  • Copy connection URLs
  • Test tools directly from the UI
Last modified on January 28, 2026