Hypertune MCP server

Evaluate and inspect your Hypertune feature flags from your AI assistant. Hosted by usefulapi: connect it to Claude, ChatGPT, Cursor or any MCP client.

Connect HypertuneFree 50 tool calls / monthPro $9/mo · $90/yr · pricing9 tools

What can I ask?

Turn on the Hypertune connector, then ask in plain words. The AI picks the tools.

Which feature flags exist in my project?
Is the new checkout flag on for a user in the UK?
What would the pricing flag return for a user on the pro plan?
Show me the underlying rules behind my beta access flag.

What you can do with Hypertune in Claude and ChatGPT

For developers who manage feature flags with Hypertune.

List the feature flags of a project

The AI lists the top-level flags with their return types and descriptions. It helps you see what exists before you test anything.

Check what a flag returns for a given user

The AI evaluates one or more flags for a context you give, such as environment and user attributes. You get the resolved values.

Inspect the rules behind a flag

The AI fetches the unreduced logic of a flag, with its conditional expression and rules instead of one value. It explains how the flag is set up.

Compare a flag for a UK and a US user

The AI evaluates the same flag for several contexts, such as a UK user and a US user, and shows the differences.

Run a custom query for a special flag shape

The AI runs your own GraphQL query with variables against the Hypertune endpoint. Use it for nested selections that the other tools cannot express.

How do I connect Hypertune?

Before you connect

The login page asks for your Hypertune API token.

Find it in Hypertune → your project → Settings (the "main token"; it's also the token embedded by the SDK setup wizard). Your token is used only to call the API on your behalf and to derive a private account id; it is never shown to anyone.

Claude claude.ai · Desktop

Open Customize → Connectors, then click + Add → Add custom connector.
Enter the name Hypertune and this URL, then click Add:
https://hypertune.usefulapi.io/mcp
Claude opens the login page: enter your Hypertune API token.
In a chat, click + → Connectors and turn on Hypertune.

Team and Enterprise: an Owner adds the connector for the organization first.

ChatGPT chatgpt.com

Open Plugins, click +, then Add custom MCP server.
Enter the name Hypertune and this URL, choose OAuth as the authentication, confirm the warning and create it:
https://hypertune.usefulapi.io/mcp
ChatGPT opens the login page: enter your Hypertune API token.
In Plugins, install Hypertune, then choose it in a chat.

No Add custom MCP server option? It depends on your account or workspace settings: see OpenAI's guide.

Claude Code

Run this command, then run /mcp in Claude Code to log in:

claude mcp add --transport http hypertune https://hypertune.usefulapi.io/mcp

Cursor

Add to Cursor or add this to ~/.cursor/mcp.json:

{
  "mcpServers": {
    "hypertune": {
      "url": "https://hypertune.usefulapi.io/mcp"
    }
  }
}

VS Code

Add to VS Code or add this to .vscode/mcp.json:

{
  "servers": {
    "hypertune": {
      "type": "http",
      "url": "https://hypertune.usefulapi.io/mcp"
    }
  }
}

Codex

Run these commands. The second one opens the login page:

codex mcp add hypertune --url https://hypertune.usefulapi.io/mcp

codex mcp login hypertune

Other clients

Windsurf, Cline, Zed and other MCP clients: add this URL as a remote MCP server (Streamable HTTP). The client then opens the login page in your browser.

https://hypertune.usefulapi.io/mcp

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 Hypertune API token. 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.

Pricing

Plan	Price	Limit
Free	$0	50 tool calls / month
Pro	$9/mo · $90/yr	10,000 tool calls / month
Pro+	$39/mo · $390/yr	100,000 tool calls / month

Each paid plan covers this Hypertune server only. Ask your AI to run hypertune_upgrade and choose Pro or Pro+, billed monthly or yearly (it returns a Stripe Checkout link). If you already have Pro, ask to change it to Pro+. The change requires your confirmation, keeps your billing interval and charges the price difference for the rest of the period immediately. Cancel any time with hypertune_cancel_subscription: your paid plan continues to the end of the paid period, with no refund for the current period, and asking to resume the same plan with hypertune_upgrade before then undoes the cancel. Or write to [email protected].

Tools 9

Show all 9 tools (the AI picks them for you)

Read only · 5

Evaluate feature flagshypertune_evaluate
Evaluate one or more feature flags for a given context and get their resolved values. Builds `query { root(context: <context>) { <selection> } }`. Provide `selection` = the flag fields to read (e.g. `exampleFlag anotherFlag { nestedField }`) and `context` = the evaluation context (environment + user/attributes). Every field must supply all of its arguments (Hypertune reduces the flag logic to a JSON result). Use hypertune_list_flags / hypertune_introspect first if you don't know the flag names.
Get flag logic (unreduced)hypertune_get_logic
Fetch the underlying LOGIC of flags without reducing them — i.e. `query { root { <selection> } }` with no context. Returns the flag's conditional expression / rules rather than a single resolved value, useful for inspecting how a flag is configured. If the schema requires a context arg you can still pass a partial one via `context`.
Run a raw GraphQL queryhypertune_query
Run an arbitrary GraphQL query (and optional variables) against the Hypertune edge endpoint. Power-user escape hatch for full control — each Hypertune project has its own generated schema, so this handles any flag shape, nested selections, inline enum literals, or variables the convenience tools can't express. The query root field is `root(context: ...)`.
Introspect the GraphQL schemahypertune_introspect
Run a GraphQL introspection query to discover the project's schema — all types and fields, including the available flags and the shape of the evaluation context. Best-effort: some edge deployments disable introspection, in which case this returns a clear error (use hypertune_query with a known flag name instead).
List feature flagshypertune_list_flags
List the project's top-level feature flags (the fields of the query root type) with their return types and descriptions, derived from GraphQL introspection. A convenient first call to see what flags exist before evaluating. Requires introspection to be enabled on the edge endpoint.

Your usefulapi plan · 4

Usage status (free-tier meter)hypertune_usage_status
Report the caller's current usage: the plan, calls used this month, the limit of the plan (the free monthly cap or the Pro fair use limit), remaining, and whether the limit is reached. Read-only; does not count against the meter.
Request a missing featurehypertune_request_feature
Tell usefulapi that the user needs something the Hypertune 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.
Upgrade to Pro or Pro+hypertune_upgrade
Get a paid plan for Hypertune (the free tier caps monthly usage). Pro: 10,000 tool calls a month, for normal use — plan "monthly" ($9/month) or "yearly" ($90/year, 2 months free). Pro+: 100,000 tool calls a month, for automations and heavy use — plan "plus" ($39/month) or "plus_yearly" ($390/year). Without a plan it returns both Pro and Pro+, each with a payment link, for the user to choose; with a plan, one link. An existing Pro subscription changes to Pro+ in place (needs confirm: true; the price difference for the rest of the period is charged at once). Cancel any time: the plan then runs to the end of the paid period, so it also suits a one-time job. A link opens Stripe Checkout in the browser; after payment the account upgrades automatically. Does not count against the meter.
Cancel the Pro subscriptionhypertune_cancel_subscription
Cancel the caller's Hypertune Pro subscription at the end of the paid period (no refund for the current period; Pro continues until then, then the free tier applies). Requires confirm: true. Run hypertune_upgrade later to undo the cancel before the period ends. Does not count against the meter.

FAQ

What can I do with Hypertune in Claude or ChatGPT?

List the feature flags of a project. Check what a flag returns for a given user. Inspect the rules behind a flag. Compare a flag for a UK and a US user. Run a custom query for a special flag shape. See what you can do for the details.

Is this an official Hypertune product?

No. usefulapi is an independent service. It is not affiliated with or endorsed by Hypertune. The server calls the Hypertune API with your own Hypertune access, so it sees only the data that your account can see.

Can I connect Hypertune to Claude or ChatGPT?

Yes. In Claude, add this server's URL as a custom connector. In ChatGPT, add it as a custom MCP server in Plugins. Then log in once. Cursor, VS Code, Claude Code and Codex work too. See the setup steps.

What do I need to connect?

The login page asks for your Hypertune API token. See Before you connect for where to find it.

Do I put my Hypertune key or an Authorization header in the client config?

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 Hypertune API token. 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.

How do you keep my Hypertune credentials?

The login stores them encrypted in the authorization grant of your connection. The server uses them to call the Hypertune 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 Hypertune.

Can the AI change my Hypertune data?

All 5 Hypertune tools are marked read-only.

What does it cost?

The Free plan gives 50 tool calls / month. Pro costs $9/mo or $90/yr, with 10,000 tool calls / month. Pro+ costs $39/mo or $390/yr, with 100,000 tool calls / month. Each subscription covers this Hypertune server only. Cancel any time: your paid plan then runs to the end of the paid period. Run hypertune_usage_status to see how many calls you used.

How do I subscribe or cancel?

Ask the AI to run hypertune_upgrade and choose Pro or Pro+, billed monthly or yearly: it returns a Stripe Checkout link. If you already have Pro, ask to change it to Pro+. After you confirm, your existing subscription changes in place, keeps its billing interval and charges the price difference for the rest of the period immediately. To cancel, run hypertune_cancel_subscription. Your paid plan continues to the end of the paid period.

What if a Hypertune tool that I need is missing?

Tell the AI what you wanted to do. It can send the request with hypertune_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.

Which AI clients can I use?

Any client that supports remote MCP servers (Streamable HTTP) with OAuth login: Claude (web and desktop), Claude Code, ChatGPT, Codex, 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.

Need a tool this server does not have, or a connection to another system? We build custom integrations and MCP servers.

More Developer Tools & Infrastructure MCP servers

All Developer Tools & Infrastructure servers →