MCP

The ProteinIQ MCP server gives an MCP-compatible agent access to the same authenticated workspace resources as the public API. Use it when an agent should inspect tool contracts, run an analysis, follow a job, retrieve results, or work with published workflows on your behalf.

Connect a client

The remote MCP endpoint is https://proteiniq.io/mcp. It uses streamable HTTP and authenticates each request with a workspace API key in the Authorization header.

Create a workspace API key from an Enterprise or active legacy Lite workspace. In your MCP client's remote-server settings, provide the endpoint and bearer header.

This configuration illustrates the required values. The configuration keys and environment-variable substitution syntax depend on your client; ${PROTEINIQ_API_KEY} must be resolved by the client, not sent literally.

{
  "mcpServers": {
    "proteiniq": {
      "type": "http",
      "url": "https://proteiniq.io/mcp",
      "headers": {
        "Authorization": "Bearer ${PROTEINIQ_API_KEY}"
      }
    }
  }
}

Keep the API key in the client's secret or environment-variable system. Do not paste a live key into source control, chat messages, or a configuration file that will be shared.

When to use MCP

MCP is appropriate when an agent needs to act across a ProteinIQ workspace rather than only read public documentation. Typical uses include:

• Tool selection: List tools and inspect accepted inputs, settings, outputs, and credit models
• Job execution: Submit a job, read its status, and fetch its structured results and file links
• File work: List, inspect, or upload workspace files when the key has the required scopes. upload_file accepts a filename and either UTF-8 content or content_base64, not a local filesystem path
• Workflow execution: List workflows, start a published workflow, inspect a run, and continue a curation checkpoint

Use the REST API or Python SDK when your integration needs direct HTTP control, generated types, or application-owned orchestration. Use the browser when a person needs to review inputs and settings before execution.

Run an analysis

An agent should inspect the scientific contract before it creates work:

1. Call list_tools to find relevant tool IDs.
2. Call get_tool to read the selected tool's input, setting, output, and credit contract.
3. Prepare input that matches the returned slot definitions and preserve documented units and defaults.
4. Call submit_job with a descriptive name and an idempotency key when the request may be retried.
5. Call get_job until the job reaches a terminal state, using polling backoff.
6. Call get_result when results are available and retain the structured output and downloadable files.

Job submission can spend workspace credits. The same workspace permissions, scopes, validation, billing, and concurrency rules used by the public API apply to MCP calls.

Available resource groups

The server groups its tools and resources around stable ProteinIQ objects:

choose_tool_for_task is an MCP prompt, not a callable tool. Clients that support prompts can use it to guide tool selection.

The server also publishes readable MCP resources for tool, job, result, file, and workflow records. Available actions depend on the API key's scopes.