Hypertune MCP server. Evaluate and inspect your Hypertune feature flags from your AI assistant.
Add to your MCP config, then reload & authorize:
{
"mcpServers": {
"hypertune": {
"url": "https://hypertune.usefulapi.io/mcp"
}
}
}| Tool | Type | What it does |
|---|---|---|
hypertune_evaluate | read | Evaluate Evaluate one or more feature flags for a given context — environment plus user and request attributes — and get their fully resolved JSON values back. |
hypertune_get_logic | read | Get logic Fetch the underlying conditional expression and targeting rules of flags without reducing them, so you can inspect exactly how a flag is configured. |
hypertune_list_flags | read | List flags List the project's top-level feature flags with their return types and descriptions — a convenient first call to discover what flags exist before evaluating. |
hypertune_introspect | read | Introspect Run a GraphQL introspection query to discover the project's full schema, including every available flag and the exact shape of the evaluation context. |
hypertune_query | read | Query Run an arbitrary GraphQL query with optional variables against the Hypertune edge endpoint — a power-user escape hatch for any flag shape or nested selection. |
hypertune_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. | |
hypertune_upgrade | Upgrade to Pro (unlimited) Subscribe to the Pro plan for UNLIMITED Hypertune 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. Read-only; does not count against the meter. |
| Plan | Price | Limit |
|---|---|---|
| Free | $0 | 100 tool calls / month |
| Pro | $9/mo · $90/yr | Unlimited |
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.