Skip to content
MCP server

Hypertune MCP by usefulapi

Hosted MCP server to evaluate and inspect Hypertune feature flags from AI assistants

Install
Pricing
Freemium
Platforms
API, Web
Runs
Remotely
Version
1.40.1
Listing updated
today

About Hypertune MCP by usefulapi

Hypertune MCP by usefulapi is a freemium MCP server for developer tools. It runs as a hosted remote server, so there is nothing to install locally.

The README says this is a hosted remote server, so there is nothing to install locally. You connect an AI client such as Claude, ChatGPT or Cursor to its URL and sign in with your Hypertune API token. From there the assistant can list the flags in a project, resolve their values for a given context such as environment and user attributes, and read the logic behind a flag without reducing it to a single value.

Beyond the five read-only tools for flags, the server offers a raw GraphQL query tool and a schema introspection tool for cases the convenience tools cannot express. Four further tools cover usage status, feature requests and managing a paid plan. The server is an independent usefulapi service and is not affiliated with Hypertune.

It suits developers and product teams who already manage flags in Hypertune and want to check how a flag resolves for particular users without writing queries by hand.

Install

Run in a terminal

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

Add to Settings → Connectors → Add custom connector

https://hypertune.usefulapi.io/mcp
Install in CursorOpens Cursor, which asks you to confirm. Or add it by hand:

Add to ~/.cursor/mcp.json

{
  "mcpServers": {
    "hypertune": {
      "url": "https://hypertune.usefulapi.io/mcp"
    }
  }
}
Install in VS CodeOpens VS Code, which asks you to confirm. Or add it by hand:

Add to .vscode/mcp.json

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

Add to ~/.codeium/windsurf/mcp_config.json

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

Add to your client's MCP settings (most use this shape)

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

Using several servers? Build one config file with the MCP config generator.

Tools this server provides (9)

Taken from the project documentation; the running server may differ.

hypertune_evaluate
Evaluate one or more feature flags for a given context and get their resolved values.
hypertune_get_logic
Fetch the underlying logic of flags without reducing them.
hypertune_query
Run an arbitrary GraphQL query against the Hypertune edge endpoint.
hypertune_introspect
Run a GraphQL introspection query to discover the project's schema.
hypertune_list_flags
List the project's top-level feature flags with return types and descriptions.
hypertune_usage_status
Report the caller's current usage and plan limits.
hypertune_request_feature
Send a request to usefulapi for a capability the tools do not yet offer.
hypertune_upgrade
Get a paid Pro or Pro+ plan for Hypertune.
hypertune_cancel_subscription
Cancel the Pro subscription at the end of the paid period.

What it does

List project feature flags
Lists top-level flags with their return types and descriptions so you can see what exists.
Evaluate flags for a context
Resolves one or more flags for an environment and user attributes you supply.
Inspect unreduced flag logic
Returns the conditional expressions and rules behind a flag rather than a single value.
Raw GraphQL queries
Runs custom GraphQL queries with variables against the Hypertune endpoint.
Schema introspection
Discovers project types, fields and evaluation context shape, where introspection is enabled.
OAuth sign-in
Authenticates through a login page using your Hypertune API token instead of a key in client config.

Good for

  • Checking whether a feature flag is on for a user in a given country
  • Comparing a flag's result for UK and US users
  • Reviewing how a flag is configured before changing it
  • Discovering which flags exist in a Hypertune project
  • Running a custom GraphQL query for nested flag structures

Pricing

Freemium, from $9 a month

Free plan 50 tool calls/month; Pro $9/mo or $90/yr; Pro+ $39/mo or $390/yr

Prices change. Check usefulapi.io before you buy.

Hypertune MCP by usefulapi FAQ

Is this an official Hypertune product?

No. usefulapi is an independent service and is not affiliated with or endorsed by Hypertune.

Do I need to install anything?

No. The server is hosted. You add its URL as a remote MCP server (Streamable HTTP) in your client and log in once.

What do I need to connect?

The login page asks for your Hypertune API token, which you can find in your project's Settings.

Can the AI change my Hypertune data?

The README and site say all five Hypertune tools are read-only.

What does it cost?

The Free plan includes 50 tool calls per month. Pro is $9 per month or $90 per year for 10,000 calls, and Pro+ is $39 per month or $390 per year for 100,000 calls.

Is Hypertune MCP by usefulapi free?

Hypertune MCP by usefulapi has a free plan, with paid plans for more usage or features. Paid plans start at $9 a month.

How do I add Hypertune MCP by usefulapi to Claude Code?

Run this command in your terminal: claude mcp add --transport http hypertune https://hypertune.usefulapi.io/mcp

What are the best alternatives to Hypertune MCP by usefulapi?

The closest alternatives to Hypertune MCP by usefulapi are REA, Codebase Memory, GitHub, Serena MCP: the IDE for your agent and XERJ.

Where this comes from

  • Description: written from the project's README, the project's website and its MCP Registry entry.
  • Install steps: from the official MCP Registry entry.

How AIPoweredBot checks servers

Alternatives to Hypertune MCP by usefulapi

  1. REA

    MCP server

    CLI and MCP server that lets coding agents reverse engineer apps and binaries

    Runs locally
    • Open source
    • 467K GitHub stars
    • Developer tools
  2. Codebase Memory

    MCP server

    Local MCP server that builds a code knowledge graph for AI coding agents

    Runs locally
    • Open source
    • 48.8K GitHub stars
    • Knowledge and memory
  3. GitHub

    MCP server

    Official MCP server connecting AI assistants to GitHub repos, issues and workflows

    • Remote
    • Open source
    • 34.6K GitHub stars
    • Developer tools
  4. MCP toolkit giving coding agents symbol-level code retrieval and editing

    Runs locally
    • Open source
    • 31.5K GitHub stars
    • Developer tools
  5. XERJ

    MCP server

    Local search engine for AI agents with cited answers over your code and docs

    Runs locally
    • Open source
    • 19.2K GitHub stars
    • Knowledge and memory
  6. Ouroboros

    MCP server

    Spec-first layer that pins requirements and verifies results of AI coding agent work

    Runs locally
    • Open source
    • 6.4K GitHub stars
    • Developer tools