Read AI-gateway analytics, configs, virtual keys, workspaces and users; log request feedback. Hosted by usefulapi — connect from Claude, Cursor, or any MCP client.
Team and Enterprise: an Owner adds the connector for the organization first.
Run this command, then run /mcp in Claude Code to log in:
Add to Cursor or add this to ~/.cursor/mcp.json:
{
"mcpServers": {
"portkey": {
"url": "https://portkey.usefulapi.io/mcp"
}
}
}Add to VS Code or add this to .vscode/mcp.json:
{
"servers": {
"portkey": {
"type": "http",
"url": "https://portkey.usefulapi.io/mcp"
}
}
}Other MCP clients (Windsurf, Cline, Zed and more): add the URL as a remote MCP server (Streamable HTTP). The client then opens the login page in your browser. Do not add an Authorization header: see Before you connect.
The login page asks for your Portkey API key.
Find it in the Portkey app → API Keys (an organization-level key is needed for admin/analytics endpoints). Your key is used only to call the API on your behalf and to derive a private account id; it is never shown to anyone.
Add only the URL. Do not add an Authorization header or an API key to the client config. The server signs you in with OAuth: the login page asks for your Portkey API key. If the config has such a header, remove it: some clients then send that header instead of the login token, and every call fails with 401.
Turn on the Portkey connector, then ask in plain words. The AI picks the tools.
| Tool | Type | What it does |
|---|---|---|
portkey_get_analytics_graph | read | Get analytics graph Get a time-series analytics graph for a single metric (cost, requests, tokens, latency, error-rate, cache-hit-rate, …) over a time window. Optionally scope by virtual keys, configs, or metadata. Portkey: GET /analytics/graphs/{metric}. |
portkey_get_analytics_group | read | Get analytics group Get grouped analytics (aggregated by models, users, or metadata) over a time window. Portkey: GET /analytics/groups/{group}. |
portkey_list_configs | read | List configs List gateway configs (routing/fallback/retry/cache rulesets applied to requests). Portkey: GET /configs. |
portkey_get_config | read | Get config Get a single gateway config by slug (or id), including its routing rules. Portkey: GET /configs/{slug}. |
portkey_list_api_keys | read | List API keys List API keys in the organization/workspace (metadata only — secrets are never returned). Portkey: GET /api-keys. |
portkey_get_api_key | read | Get API key Get a single API key's metadata by id (the secret is never returned). Portkey: GET /api-keys/{id}. |
portkey_list_virtual_keys | read | List virtual keys List virtual keys (the aliases that map to provider credentials + budget/rate limits used in requests). Portkey: GET /virtual-keys. |
portkey_get_virtual_key | read | Get virtual key Get a single virtual key by slug, including its provider + limits. Portkey: GET /virtual-keys/{slug}. |
portkey_list_workspaces | read | List workspaces List workspaces in the organization. Portkey: GET /workspaces. |
portkey_get_workspace | read | Get workspace Get a single workspace by slug/id. Portkey: GET /workspaces/{id}. |
portkey_list_workspace_members | read | List workspace members List members of a workspace (users + their roles). Portkey: GET /workspaces/{id}/members. |
portkey_list_users | read | List users List users in the organization. Filter by role or email. Portkey: GET /users. |
portkey_get_user | read | Get user Get a single user by id. Portkey: GET /users/{id}. |
portkey_list_user_invites | read | List user invites List pending user invitations to the organization. Portkey: GET /user-invites. |
portkey_list_audit_logs | read | List audit logs List audit log entries (admin actions across the organization). Portkey: GET /audit-logs. |
portkey_create_feedback | write | Create feedback WRITES a feedback record into the Portkey account, attached to a request/trace by trace_id. Use for logging a quality score (typically -10..10) with an optional weight (0..1) and metadata. Portkey: POST /feedback. |
portkey_usage_status | Usage status (free-tier meter) Report the caller's current free-tier usage this month: calls used, monthly limit, remaining, and whether the cap is reached. Read-only; does not count against the meter. | |
portkey_request_feature | Request a missing feature Tell usefulapi that the user needs something the Portkey tools cannot do yet (a missing tool, field or filter). Call it only when the user asks for something none of the tools can do, and tell the user that you send the request. Do not call it for errors or for normal requests. Do not include personal data, credentials or customer records. Stored with the product name and the client type (for example Claude or Cursor), without the user's account. At most 5 requests per day. Does not count against the meter. | |
portkey_upgrade | Upgrade to Pro (unlimited) Subscribe to the Pro plan for UNLIMITED Portkey tool calls (the free tier caps monthly usage). Choose monthly ($9/month) or yearly ($90/year — 2 months free) billing. Returns a Stripe Checkout link to open in your browser; after payment your account upgrades automatically. Does not count against the meter. | |
portkey_cancel_subscription | Cancel the Pro subscription Cancel the caller's Portkey Pro subscription at the end of the paid period (no refund for the current period; unlimited calls continue until then, then the free tier applies). Requires confirm: true. Run portkey_upgrade later to undo the cancel before the period ends. Does not count against the meter. |
| Plan | Price | Limit |
|---|---|---|
| Free | $0 | 100 tool calls / month |
| Proper user | $9/mo · $90/yr | Unlimited |
Pro covers this Portkey server only. Subscribe with portkey_upgrade (it returns a Stripe Checkout link). Cancel any time with portkey_cancel_subscription: Pro continues to the end of the paid period, with no refund for the current period, and running portkey_upgrade before then undoes the cancel. Or write to [email protected].
No. usefulapi is an independent service. It is not affiliated with or endorsed by Portkey. The server calls the Portkey API with your own Portkey access, so it sees only the data that your account can see.
The login page asks for your Portkey API key. See Before you connect for where to find it.
No. Add only the URL. Do not add an Authorization header or an API key to the client config. The server signs you in with OAuth: the login page asks for your Portkey API key. If the config has such a header, remove it: some clients then send that header instead of the login token, and every call fails with 401.
The login stores them encrypted in the authorization grant of your connection. The server uses them to call the Portkey API for you and to derive a private account id for usage metering. usefulapi does not show them on any page or in any reply. To stop all access, remove the connector and change or delete these credentials in Portkey.
Yes, if you approve it. 1 of the 16 Portkey tools can create or change data. The other 15 are marked read-only. Most MCP clients ask you to approve a tool call before it runs.
The Free plan gives 100 tool calls / month. Pro costs $9/mo or $90/yr, with unlimited tool calls, for this Portkey server only. Run portkey_usage_status to see how many calls you used.
Ask the AI to run portkey_upgrade: it returns a Stripe Checkout link. To cancel, run portkey_cancel_subscription. Pro continues to the end of the paid period.
Tell the AI what you wanted to do. It can send the request with portkey_request_feature. We store the text with the server name, the type of AI client and the tool you tried, not with your account, and read every request when we plan new tools. You can send up to 5 requests per day.
Any client that supports remote MCP servers (Streamable HTTP) with OAuth login: Claude (web and desktop), Claude Code, Cursor, VS Code, Windsurf and others.
This is a Model Context Protocol endpoint — meant to be connected from an AI client, not opened in a browser. An invalid_token response at the URL is the auth gate working as designed; clients authenticate automatically.