Skip to main content
Connect Muse Code to your DevTune project, then ask it what AI platforms say about your product, what to fix next, and whether a shipped fix moved the numbers.

Before you start

  • A DevTune project on a plan that includes API access. No account yet? Let your agent set one up.
  • For the API key route: a project API key from API Keys in the account sidebar. DevTune shows the key once, so copy it when you create it.

Connect by signing in

Add the server to ~/.config/muse/settings.json. Keep the keys the file already has, including schema_version:
Then sign in:
Sign in to DevTune in the browser, select the project, choose the scopes the connection may use, and approve. On a machine without a browser, add --headless: Muse Code prints the URL and asks you to paste the final redirect URL. The connection reaches the project you select, with your own DevTune permissions.

Connect with an API key

Use a key for scripts, scheduled runs and machines without a browser. Put the key in an environment variable and add a header that names it. Muse Code reads the variable when it connects:
Start a new session after you change the file. A key reaches the one project it was created for, with the scopes you gave it. A change made with a key acts as the member who created it.

Check the connection

Run /mcp in a Muse Code session. It lists the connected servers and their tools. Then ask Muse Code:
It answers with your project’s name, read with devtune_get_connection_context. If it names the wrong project, connect again and select the right one.

Measure

Ask Muse Code what AI platforms say and what AI systems fetch from your site:
Muse Code answers from devtune_get_visibility_summary, devtune_get_visibility_diff, devtune_get_competitive_position, devtune_get_top_citation_pages, devtune_get_content_gaps, devtune_get_traffic_summary and devtune_get_404_demand. Measurement windows are 30 or 90 days.

Fix

Ask for the ranked fixes, then work one through:
  1. devtune_get_actions lists the queue with its evidence.
  2. devtune_change_action_status accepts an action, and devtune_generate_action_brief writes its brief. Generating a brief spends credits.
  3. Muse Code reads the brief with devtune_get_action_brief. Writing and publishing the page is your work and the agent’s, in your own repository or content system. DevTune drafts and never publishes.
  4. devtune_change_action_status with mark_live and the published URL starts the before/after measurement.

Prove

devtune_get_outcomes_ledger returns each measured action as improved, mixed, no clear change, declined, still measuring or unmeasured. Results show what moved after a fix shipped, not what caused it. Results windows are 7, 30, 90 or 365 days.

What needs your approval

  • Reading never changes your project or spends credits.
  • Accepting an action, changing prompts or competitors, and every other change acts as you. Have the agent say what it will change before it does.
  • Briefs, drafts, managed-agent runs, Agent Picks tests and prompt-set analysis spend credits. Approve the spend before the agent starts one.
  • DevTune steers suggestions around locked pages and says when it did.

How Muse Code runs DevTune tools

Muse Code names the tools mcp__devtune__<tool>. A read-only DevTune tool runs without an approval prompt under on-request approvals; tools that change something ask first. Muse Code does not sandbox MCP tools.

Skills

The DevTune skills tell the agent which DevTune tool answers which question and how to report the numbers the way DevTune measures them. Muse Code loads skills from ~/.agents/skills and from .agents/skills in a project:

Limits

  • A server’s mode defaults to required, and a required server that fails to start stops the whole run. "mode": "optional" lets Muse Code start without DevTune.
  • A connection reaches one project. Connect again, or use another key, for a second project.
  • Tools your connection has no scope for do not appear in the agent. A connection never gains scopes added later. Edit the key, or disconnect and sign in again.

If something goes wrong

Next steps