Execution MCP

Connect the execution MCP to your coding assistant to work with your Millwork organization from the conversation. The assistant can connect a provider account, save a model, submit a run (one task you send to Millwork; the API calls it an execution), and read its result and receipt. It uses your organization API key. Configure your assistant to ask before each change or paid request; the stop happens in your assistant, not in Millwork. For questions about using Millwork, connect the documentation MCP, which searches and reads these docs.

Connect your assistant

Requires Node.js 20 or later and an organization API key. Add a local server to your assistant’s MCP settings:

{
  "mcpServers": {
    "millwork": {
      "command": "npx",
      "args": ["--yes", "@millwork/solver-mcp@0.1.1"],
      "env": {
        "SOLVERAPI_API_KEY": "<organization API key>",
        "SOLVERAPI_BASE_URL": "https://api.getmillwork.dev/v1"
      }
    }
  }
}

Enter your key in the assistant’s local settings, outside the conversation. Enable confirmation for write tools, then restart the MCP connection. Ask the assistant to list the models you have saved to check the connection without starting a run. The server runs locally over standard input and output. Its package is @millwork/solver-mcp on npm.

What it can do

Each tool maps to one REST endpoint (two for the proposal tools), so the assistant sees exactly what a direct API caller sees. A saved model is an option Millwork may run your task on; the API calls it an arm, which is why several tool names carry that word.

Tool	What it does	Read, or a write your host must confirm	REST endpoint
`solver_list_sources`	Lists the providers your organization can connect	Read only	`GET /v1/model-source-profiles`
`solver_start_source_handoff`	Starts a secure setup, a one-time browser step where you enter a provider key yourself; the assistant gets a link, never the key	Write; host must confirm	`POST /v1/source-credential-handoffs`
`solver_poll_source_handoff`	Checks whether that browser step is finished	Read only	`GET /v1/source-credential-handoffs/{id}`
`solver_create_source_connection`	Saves a provider connection from a finished secure setup; it starts disabled until tested	Write; host must confirm	`POST /v1/source-connections`
`solver_test_source_connection`	Tests a provider connection against the provider; a pass enables it	Write; host must confirm	`POST /v1/source-connections/{id}/test`
`solver_list_source_connections`	Lists your provider connections and their test state	Read only	`GET /v1/source-connections`
`solver_sync_source_deployments`	Refreshes the models a tested connection can reach	Write; host must confirm	`POST /v1/source-connections/{id}/deployments/sync`
`solver_list_model_deployments`	Lists the catalog models loaded from your connections	Read only	`GET /v1/model-deployments`
`solver_enable_model_arm`	Saves a catalog model as a saved model	Write; host must confirm	`POST /v1/arms`
`solver_register_arm`	Saves a model, an agent endpoint, or a skill as a saved model	Write; host must confirm	`POST /v1/arms`
`solver_list_arms`	Lists your saved models	Read only	`GET /v1/arms`
`solver_submit`	Submits a run; a live run has a platform fee, charged when Millwork accepts it	Write; host must confirm	`POST /v1/executions`
`solver_status`	Reads a run’s status	Read only	`GET /v1/executions/{id}`
`solver_cancel`	Cancels a run that has not finished; this cannot be undone	Write; host must confirm	`POST /v1/executions/{id}/cancel`
`solver_result`	Reads the result of a completed live run	Read only	`GET /v1/executions/{id}/result`
`solver_receipt`	Reads a run’s receipt; it never contains the prompt or the output	Read only	`GET /v1/receipts/{id}`
`solver_proposals`	Lists proposed changes to a saved skill (the API calls them repair proposals), or reads one	Read only	`GET /v1/proposals`, `GET /v1/proposals/{id}`
`solver_review_proposal`	Approves or rejects a proposed change; the decision is final	Write; host must confirm	`POST /v1/proposals/{id}/approve` or `/reject`

Reads need no confirmation. The nine read-only tools change nothing, and the server may retry one when the network or Millwork fails. Writes need your confirmation. The server itself sends no confirmation flag; your assistant or its host enforces the stop, so configure it to confirm every tool that is not a read. The server retries a write on its own only for solver_submit, and only with the same request key and the same request, so a retry cannot start a second run. Any other write that loses its response is a failure, and the next call is a new decision for you, not an automatic replay. The server reads your organization API key from its own environment, sends it only to Millwork as the bearer token, and never returns it in a tool result. Confirmation is a stop in the assistant, not a narrower key: your API key keeps its full permissions, so give the assistant only a key whose permissions you are willing to let it use.

Run submission through the assistant

solver_submit is the one tool that can cost money, so your assistant must ask first every time. In 0.1.0 and 0.1.1, a call must carry:

a request key, supplied by the assistant as idempotency_key and sent in the Idempotency-Key header, so a retry does not start the work twice; the server rejects a call without one before it reaches Millwork;
the task and policy, the same shape as POST /v1/executions; Millwork keeps the saved models that fit your policy limits and picks one; and
an output check, a check applied to the run’s output, as verifier_id. Both published versions require this field. If you have not created an output check, create one with POST /v1/verifiers before the first submission.

What comes back is the run record: its execution_id and status. The assistant then follows it with solver_status, reads the output with solver_result when the run completes, and reads the receipt with solver_receipt. Every one of those is read only. A test run (a run the API calls Echo, which calls no model and has no platform fee and no model cost) takes no output check, and 0.1.0 and 0.1.1 both require verifier_id on every submission, so neither can submit a test run. Make your first test run with curl (Make your first API call), then let the assistant follow it with the read-only tools. A live run submitted through a published version needs an output check and is charged the platform fee when Millwork accepts it. Read Model access and billing before approving a live run, and Errors and retries for what each error means.

Use a coding assistant

Give an assistant one page and a short set of rules so it works with you and never sees a secret.

Documentation MCP

The live, read-only server that searches and reads these docs.

Get started

Build

Build safely

SDK and MCP

Connect your assistant

What it can do

Run submission through the assistant

Use a coding assistant

Documentation MCP

​Connect your assistant

​What it can do

​Run submission through the assistant

Use a coding assistant

Documentation MCP

Connect your assistant

What it can do

Run submission through the assistant