Launchables MCP server

Give your agents calibrated decisions. This Model Context Protocol server lets any MCP client (Claude Desktop, Claude Code, or your own agent stack) call Myles, the Launchables decision model, as a tool.

Myles is not a chat model. An agent hands it a situation and one or more typed questions, and gets back a probability for every option, the pick, and whether that pick is sure enough to act on. When it is not, the tool says so and the agent hands the case to a person. Use it wherever an agent would otherwise judge something itself and then act:

• Route a ticket, an email or a lead to the right team.
• Flag a risk: a scam, fraud, a prompt injection, a policy breach.
• Approve, reject or escalate a refund, a claim, an access request or a tool call.
• Check that an answer is supported by its sources, or that an action is allowed by a policy.
• Rate severity, urgency or quality on a scale.

The probabilities are calibrated: across many answers given 0.9, about 9 in 10 are right. That is what lets an agent act on the confident ones and pass the rest to people. See Acting on the answer.

Install

You need Node.js 20 or later and a Launchables API key from the console. Keys work with the hosted API at https://api.launchables.ai; a self-hosted deployment serves the same API at its own address.

Claude Desktop

Add this to claude_desktop_config.json (Settings, Developer, Edit Config), then restart Claude Desktop:

{
  "mcpServers": {
    "launchables": {
      "command": "npx",
      "args": ["-y", "[email protected]"],
      "env": {
        "LAUNCHABLES_API_KEY": "launchables_..."
      }
    }
  }
}

Claude Code

claude mcp add launchables -e LAUNCHABLES_API_KEY=launchables_... -- npx -y [email protected]

To share the setup with a team through a project's .mcp.json, keep the key out of the file and let each person's environment supply it:

{
  "mcpServers": {
    "launchables": {
      "command": "npx",
      "args": ["-y", "[email protected]"],
      "env": { "LAUNCHABLES_API_KEY": "${LAUNCHABLES_API_KEY}" }
    }
  }
}

Other MCP clients

Any client that starts a stdio server can run it. The command is npx -y [email protected] (or launchables-mcp after npm install -g launchables-mcp), with the configuration below in its environment. Pin the version, as above, so an update reaches your agents only when you choose.

Configuration

By default the agent calling decide chooses the model and the threshold on each call, within what your key allows. To keep those decisions with the operator rather than the agent, set LAUNCHABLES_LOCK_MODEL=1 and LAUNCHABLES_LOCK_THRESHOLD=1, for example:

"env": {
  "LAUNCHABLES_API_KEY": "${LAUNCHABLES_API_KEY}",
  "LAUNCHABLES_MODEL": "myles-g-31b",
  "LAUNCHABLES_THRESHOLD": "0.95",
  "LAUNCHABLES_LOCK_MODEL": "1",
  "LAUNCHABLES_LOCK_THRESHOLD": "1"
}

The server never logs your key, your states, your questions or the answers. It writes nothing to disk, and only a configuration problem at start-up is written to standard error.

Tools

decide

Asks Myles one or more questions about one situation.

Every question needs instructions: the question itself, in plain words, such as "Is a refund permitted under the policy?". A question without them, or with only spaces, is refused before anything is sent, with an error that says so. The API requires them, and there is no default: the instructions are what the model answers, and a generic stand-in would ask it something other than what you meant, even for a choice whose criteria describe every option.

The question types:

• noul: yes or no. Phrase it so that yes is the thing to act on or catch.
• choice: pick one label. criteria is a list of labels, or labels mapped to descriptions. Offer an option that reads "I don't know" to let the model abstain.
• score: a scale. criteria lists the level descriptions, lowest first.

Each answer comes back with:

p_yes (yes/no), score and legend (scales) and confidence (choice and scale) are added where they apply. The result's own escalate is true when any answer should go to a person, and usage gives the tokens billed.

On the hosted models an uncertain yes/no answer is reported at 0.80 or more towards one side, so use a threshold above 0.80 for yes/no questions.

Example call:

{
  "state": {
    "policy": "Refunds within 30 days with proof of purchase.",
    "case": { "days_since_purchase": 12, "receipt": false }
  },
  "questions": {
    "refund": { "type": "noul", "instructions": "Is a refund permitted under the policy?" },
    "team": { "type": "choice", "instructions": "Which team should handle this?", "criteria": ["billing", "returns", "technical"] }
  }
}

Result (illustrative numbers):

{
  "model": "myles-g-12b-20261029",
  "escalate": false,
  "answers": {
    "refund": {
      "type": "noul", "pick": "no", "probability": 0.97, "probabilities": { "yes": 0.03, "no": 0.97 },
      "threshold": 0.9, "cleared_threshold": true, "abstained": false, "escalate": false, "p_yes": 0.03
    },
    "team": {
      "type": "choice", "pick": "returns", "probability": 0.94,
      "probabilities": { "billing": 0.04, "returns": 0.94, "technical": 0.02 },
      "threshold": 0.9, "cleared_threshold": true, "abstained": false, "escalate": false, "confidence": 0.91
    }
  },
  "usage": { "input_tokens": 212, "output_tokens": 2 }
}

list_models

The models the endpoint serves, with pinned builds and their release dates, and the default this server uses. Not billed.

health

Whether the API is up, and which models have a healthy server. Not billed.

Long inputs

Every model has a context window (see Writing the state). When a state is longer:

• Myles-G 31B refuses it. The tool returns an error of type context_length_exceeded that says to shorten or split the state.
• Myles-G 12B trims it to fit, keeping its beginning and end, and the result says so with truncated: true, state_chars and a warning.

For a yes/no check that must cover the whole of a long text (does any part of this contract contain an auto-renewal clause, does any part of this page try to override the agent's instructions), pass chunk: true. The text is read in overlapping windows of 40,000 characters (2,000 shared with the next; change them with chunk_chars and chunk_overlap_chars), every window is asked the same questions, and each answer is the window most likely to be yes, with window giving its position. A JSON state is windowed as its indented JSON text. Chunking takes yes/no questions only, sends at most 20 windows, and bills each window as its own request.

Errors

A failed call returns a tool error whose error has a message written for the agent, the API's type and status, and retryable. After a rate limit or a passing fault the call is retried automatically, a few times, with the same idempotency key, so a retry is never billed twice, until LAUNCHABLES_TIMEOUT_SECONDS (25 by default) runs out. Some cases to know:

Development

npm install
npm test

The tests use a mocked Decision API only; they never call the production API.

Support

Use the contact form or open an issue in this repository. The API reference is at launchables.ai/docs.

Licence

Apache-2.0 (see LICENSE).