Skip to main content
Connect ChatGPT 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.
  • ChatGPT on the web. If you do not see Add custom MCP server, your workspace admin controls who can add one.

Connect by signing in

  1. Open chatgpt.com/plugins.
  2. Select the plus button, then Add custom MCP server.
  3. Enter DevTune as the name.
  4. Under Connection, paste https://devtune.ai/api/mcp as the Server URL.
  5. Set the authentication to OAuth.
  6. Review the risk warning and select I understand and want to continue.
  7. Select Create as a plugin.
  8. Install the plugin. When ChatGPT asks, sign in to DevTune, select the project, choose the scopes the connection may use, and approve.
The connection reaches the project you select, with your own DevTune permissions.

Check the connection

In a chat, type @ in the prompt box and select the DevTune plugin. Then ask ChatGPT:
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 ChatGPT what AI platforms say and what AI systems fetch from your site:
ChatGPT 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. ChatGPT 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 ChatGPT runs DevTune tools

ChatGPT asks you to confirm each DevTune tool that changes something. You can expand a tool call to read exactly what it will send before you approve, and ChatGPT can remember your choice for a tool for the rest of that conversation. A new conversation asks again. In the ChatGPT desktop app, install the DevTune plugin through Codex instead. See Use DevTune with Codex.

Limits

  • ChatGPT offers sign-in or no authentication for a custom server, so a DevTune API key cannot be used here.
  • 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