portkey-admin-mcp
Full MCP server for the https://portkey.ai AI Gateway Admin API with 151 tools across 18 domains.
Portkey Admin MCP Server
MCP server for the Portkey Admin API. Manage prompts, configs, analytics, API keys, and more from any MCP client.
Quick Start
You need a Portkey API key with appropriate scopes. Get one from your Portkey dashboard under API Keys.
Claude Code
claude mcp add -e PORTKEY_API_KEY=your_key portkey-admin -- npx -y portkey-admin-mcp
Cursor / Windsurf / VS Code
Add to your MCP config (.cursor/mcp.json, .windsurf/mcp.json, or .vscode/mcp.json):
{
"mcpServers": {
"portkey-admin": {
"command": "npx",
"args": ["-y", "portkey-admin-mcp"],
"env": {
"PORTKEY_API_KEY": "your_api_key"
}
}
}
}
Run directly
PORTKEY_API_KEY=your_key npx -y portkey-admin-mcp
To expose only a focused subset of tools in stdio clients, set PORTKEY_TOOL_DOMAINS:
PORTKEY_API_KEY=your_key \
PORTKEY_TOOL_DOMAINS=prompts,analytics \
npx -y portkey-admin-mcp
Build from source
git clone https://github.com/s-b-e-n-s-o-n/portkey-admin-mcp.git
cd portkey-admin-mcp
npm install && npm run build
Then use this config:
{
"mcpServers": {
"portkey-admin": {
"command": "node",
"args": ["/path/to/portkey-admin-mcp/build/index.js"],
"env": {
"PORTKEY_API_KEY": "your_api_key"
}
}
}
}
What You Can Do
| Category | Tools | Examples |
|---|---|---|
| Prompts | 14 | Create, version, render, execute, migrate, promote prompts |
| Prompt Partials | 7 | Reusable prompt fragments with versioning |
| Prompt Labels | 5 | Organize prompt versions (production, staging, dev) |
| Configs | 6 | Gateway routing, caching, retry, loadbalancing |
| API Keys | 5 | Create and manage scoped API keys |
| Virtual Keys | 5 | Manage provider access keys |
| Collections | 5 | Group prompts by app or project |
| Providers | 5 | Manage AI provider configurations |
| Integrations | 10 | Provider integrations, models, workspace access |
| MCP Integrations | 10 | External MCP tool integrations |
| MCP Servers | 10 | MCP server registry and capabilities |
| Guardrails | 5 | Content safety policies |
| Usage Limits | 7 | Cost and token consumption limits |
| Rate Limits | 5 | Request frequency controls |
| Analytics | 20 | Cost, latency, errors, tokens, cache, feedback |
| Logging | 8 | Log ingestion and export |
| Tracing | 2 | Feedback creation and updates on traces |
| Users & Workspaces | 20 | User management, invites, workspace members |
| Audit | 1 | Audit log access |
150 tools total. See ENDPOINTS.md for the full list with descriptions.
API Key Scopes
Most tools work with a workspace-scoped service key that has Select All permissions enabled. That covers prompts, configs, virtual/API keys, providers, guardrails, workspace integrations, MCP servers, rate/usage limits, logs, prompt completions, and workspace user management.
Enterprise-gated tools (28)
The following tools require an organisation-level scope that is only available on Portkey Enterprise plans. They return 403 You do not have enough permissions to execute this request on workspace plans. Their descriptions include an Enterprise-gated. Returns 403 on non-Enterprise Portkey plans. suffix so MCP clients know upfront.
| Area | Tools | Required scope |
|---|---|---|
| Analytics (20) | get_cost_analytics, get_request_analytics, get_token_analytics, get_latency_analytics, get_error_analytics, get_error_rate_analytics, get_cache_hit_latency, get_cache_hit_rate, get_users_analytics, get_error_stacks_analytics, get_error_status_codes_analytics, get_user_requests_analytics, get_rescued_requests_analytics, get_feedback_analytics, get_feedback_models_analytics, get_feedback_scores_analytics, get_feedback_weighted_analytics, get_analytics_group_users, get_analytics_group_models, get_analytics_group_metadata | org-level analytics.view |
| Audit | list_audit_logs | audit_logs.list |
| Org-level integrations | get_integration, list_integration_models, list_integration_workspaces | organisation_integrations.read |
| Org-level users | list_all_users, get_user, get_user_stats, list_user_invites | organisation_users.list / organisation_users.read |
Other scope requirements
| Feature | Required |
|---|---|
Prompt completions (run_prompt_completion) | completions.write scope + billing metadata (app, env) |
Org-level service API key creation via create_api_key | organisation_service_api_keys.create (Enterprise) |
If a tool returns a 403 with Portkey error AB03, it means missing scopes — not a broken endpoint.
HTTP Server (Experimental)
Status: The HTTP transport works but hosted deployment is not fully validated for production. Use stdio (npx) for reliable operation.
The server supports Streamable HTTP for remote access:
PORTKEY_API_KEY=your_key \
MCP_HOST=127.0.0.1 \
MCP_PORT=3000 \
MCP_PUBLIC_BASE_URL=https://mcp.example.com \
MCP_AUTH_MODE=bearer \
MCP_AUTH_TOKEN=your_secret \
node build/server.js
Or via npx (the portkey-admin-mcp package includes the HTTP binary):
PORTKEY_API_KEY=your_key MCP_AUTH_MODE=bearer MCP_AUTH_TOKEN=your_secret \
npx -y -p portkey-admin-mcp portkey-admin-mcp-http
For local-only HTTP use, leave MCP_HOST at its default 127.0.0.1. Set MCP_HOST=0.0.0.0 only when you intentionally need to accept connections from outside the local machine, such as Docker or a reverse proxy on another interface.
Configuration
| Variable | Default | Description |
|---|---|---|
PORTKEY_API_KEY | (required) | Your Portkey API key |
PORTKEY_TOOL_DOMAINS | — | Optional comma-separated stdio/HTTP default tool subset, e.g. prompts,analytics |
MCP_HOST | 127.0.0.1 | Bind address |
MCP_PORT | 3000 | Port |
MCP_PUBLIC_BASE_URL | — | Public absolute base URL to advertise from /auth/info and the status page; recommended for hosted deployments |
MCP_AUTH_MODE | none | none, bearer, or clerk (none is blocked for HTTP unless explicitly overridden) |
MCP_AUTH_TOKEN | — | Secret for bearer auth |
MCP_ALLOW_UNAUTHENTICATED_HTTP | — | Set to true only for intentional local unauthenticated HTTP debugging |
MCP_SESSION_MODE | stateful | stateful or stateless |
MCP_MAX_SESSIONS | 100 | Maximum concurrent stateful MCP sessions before new initialize requests are rejected |
MCP_EVENT_STORE | off | off, memory, or redis |
MCP_REDIS_URL | — | Redis URL for shared event store |
MCP_TLS_KEY_PATH | — | TLS key for native HTTPS |
MCP_TLS_CERT_PATH | — | TLS cert for native HTTPS |
ALLOWED_ORIGINS | — | CORS allow-list |
MCP_TRUST_PROXY | false | Trust proxy headers (for reverse proxies) |
RATE_LIMIT_MAX_BUCKETS | 10000 | Maximum distinct in-memory rate-limit buckets before new clients share an overflow bucket |
Vercel deployment
Experimental Vercel support is included. See docs/VERCEL_DEPLOYMENT.md for setup instructions.
Key points:
- Uses stateless mode with Redis event store
- Requires Clerk or bearer auth
- Leave
MCP_TLS_*unset (Vercel terminates HTTPS) - Set
MCP_PUBLIC_BASE_URLto your deployment URL so advertised MCP endpoints never depend on request headers - Vercel does not support WebSockets — Streamable HTTP/SSE only
Docker
docker build -t portkey-admin-mcp .
docker run \
-e PORTKEY_API_KEY=your_key \
-e MCP_HOST=0.0.0.0 \
-e MCP_PORT=3000 \
-e MCP_AUTH_MODE=bearer \
-e MCP_AUTH_TOKEN=your_secret \
-p 3000:3000 \
portkey-admin-mcp
Health Endpoints
| Path | Purpose |
|---|---|
GET /health | Server liveness |
GET /ready | Readiness (includes optional Portkey connectivity check) |
GET /auth/info | Auth configuration metadata |
Development
npm run dev # stdio with hot reload
npm run dev:http # HTTP with hot reload
npm test # unit + contract tests
npm run test:e2e # MCP protocol tests
npm run test:http # HTTP endpoint smoke test
npm run ci # full pipeline (lint + typecheck + test + build + e2e + verify)
npm run dev:http now requires MCP_AUTH_MODE=bearer or MCP_AUTH_MODE=clerk by default. For deliberate local-only unauthenticated testing, set MCP_ALLOW_UNAUTHENTICATED_HTTP=true.
MIT License · Inspired by r-huijts/portkey-admin-mcp-server
Verwandte Server
Scout Monitoring MCP
SponsorPut performance and error data directly in the hands of your AI assistant.
Alpha Vantage MCP Server
SponsorAccess financial market data: realtime & historical stock, ETF, options, forex, crypto, commodities, fundamentals, technical indicators, & more
AI Agent Playwright
An AI agent for the Playwright MCP server, enabling automated web testing and interaction.
Grafana Loki
A server for querying Loki logs from Grafana.
WebDev MCP
Provides a collection of useful web development tools.
SCMCP
A natural language interface for single-cell RNA sequencing (scRNA-Seq) analysis, supporting various modules from IO to enrichment.
mcp-pystub
Auto-detect stubbable packages for Python exe builds (PyInstaller/Nuitka) and generate minimal stub code to reduce executable size
Codex MCP Wrapper
An MCP server that wraps the OpenAI Codex CLI, exposing its functionality through the MCP API.
Figma MCP Server
Enables AI assistants to interact with Figma via WebSocket for reading data and design analysis.
Mindpilot MCP
Visualize legacy code and inspect complex flows to understand your agent's operations.
MCPShield
Security scanner for MCP servers — detects tool poisoning, prompt injection, and 90+ vulnerability patterns
Unreal-Blender MCP
A unified server to control Blender and Unreal Engine via AI agents.