About Hypertune MCP by usefulapi
Hypertune MCP by usefulapi is a hosted MCP server for inspecting and evaluating Hypertune feature flags. It is intended for users of Hypertune who need flag logic and GraphQL schema details through MCP clients.
Key features
- 01Evaluate feature flags
- 02Inspect unreduced flag logic
- 03Run raw GraphQL queries
- 04Introspect the GraphQL schema
- 05List feature flags
Use cases
- 01Check a feature flag result
- 02Inspect the logic behind a flag
- 03Explore Hypertune's GraphQL schema
MCP support
Exposes read-only Hypertune tools to MCP clients through a hosted remote MCP server. Connection uses a Hypertune API token.
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://hypertune.usefulapi.io/mcpclaude mcp add --transport http io-usefulapi-hypertune https://hypertune.usefulapi.io/mcp{"mcpServers":{"io-usefulapi-hypertune":{"type":"http","url":"https://hypertune.usefulapi.io/mcp"}}}Open in Cursor{"servers":{"io-usefulapi-hypertune":{"type":"http","url":"https://hypertune.usefulapi.io/mcp"}}}Open in VS Code{"mcpServers":{"io-usefulapi-hypertune":{"type":"http","url":"https://hypertune.usefulapi.io/mcp"}}}{"mcpServers":{"io-usefulapi-hypertune":{"serverUrl":"https://hypertune.usefulapi.io/mcp"}}}Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.
Tools
5| Parameter | Type | Required | Description |
|---|---|---|---|
| context | object | No | Evaluation context object, inlined as the `context` arg. e.g. {"environment":"production","user":{"id":"u_123","email":"[email protected]"}}. Omit to return the flag LOGIC instead of a reduced value. |
| selection | string | Yes | GraphQL selection of flag fields under root, e.g. `exampleFlag` or `homePage { showBanner } exampleFlag`. |
Details
From the project READMEHypertune MCP by usefulapi
Evaluate feature flags, inspect flag logic, and introspect your Hypertune schema from Claude, Cursor, or any MCP client. Hosted, no local install — connect with your Hypertune API token.
Live endpoint: https://hypertune.usefulapi.io/mcp · Homepage: https://usefulapi.io/hypertune
Connect
- Claude (claude.ai, Desktop): open Customize → Connectors, click + Add → Add custom connector, and paste
https://hypertune.usefulapi.io/mcp. - Claude Code:
claude mcp add --transport http hypertune https://hypertune.usefulapi.io/mcp, then run/mcpto log in. - VS Code: Add to VS Code.
- Cursor and other clients: add the URL as a remote MCP server:
{
"mcpServers": {
"hypertune": {
"url": "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, and the login page asks for your Hypertune credentials.
Step-by-step setup, where to find your credentials, and FAQ: https://usefulapi.io/hypertune/
On first connect you'll paste your Hypertune API token. It's validated, stored per-user, and scoped to you.
Tools
| Tool | Type | What it does |
|---|---|---|
hypertune_evaluate | read | Evaluate feature flags |
hypertune_get_logic | read | Get flag logic (unreduced) |
hypertune_query | read | Run a raw GraphQL query |
hypertune_introspect | read | Introspect the GraphQL schema |
hypertune_list_flags | read | List feature flags |
hypertune_usage_status | meta | Usage status (free-tier meter) |
hypertune_request_feature | meta | Request a missing feature |
hypertune_upgrade | meta | Upgrade to Pro (unlimited*) |
hypertune_cancel_subscription | meta | Cancel the Pro subscription |
read tools are read-only; write tools mutate data (clients should confirm them); meta tools report usage, manage your subscription or send a feature request.
Pricing
| Plan | Price | Limit |
|---|---|---|
| Free | $0 | 50 tool calls / month |
| Pro | $9/mo or $90/yr (2 months free) | Unlimited* |
*Pro has a fair use limit of 10,000 tool calls a month on this server. For more, write to [email protected].
Pro covers this server only. Subscribe with hypertune_upgrade (it returns a Stripe Checkout link). Cancel any time with hypertune_cancel_subscription: Pro continues to the end of the paid period, with no refund for the current period, and running hypertune_upgrade before then undoes the cancel. Or write to [email protected].
License
MIT — see LICENSE. Documentation only; the server is hosted.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.