Use DevTune with Gemini CLI
Connect Gemini CLI 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.
- Made by
- What it is
- Coding agent for the terminal.
- Connect with
- Sign-in, API key
- How we checked
- Checked against docs
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, then sign in from a Gemini CLI session:
gemini mcp add --transport http devtune https://devtune.ai/api/mcp
/mcp auth devtune
Sign in to DevTune in the browser, select the project, choose the scopes the connection may use, and approve.
The command writes to .gemini/settings.json in the current folder. Add --scope user to write to ~/.gemini/settings.json and use the server everywhere.
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.
Add the server with the key as a header. Your shell fills in the key, and Gemini CLI saves it in the settings file, so use --scope user to keep it out of your project:
export DEVTUNE_API_KEY='dtk_live_YOUR_KEY'
gemini mcp add --scope user --transport http \
--header "Authorization: Bearer $DEVTUNE_API_KEY" \
devtune https://devtune.ai/api/mcp
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 gemini mcp list for the server and its connection status. In a session, /mcp shows the server and its tools.
Then ask Gemini CLI:
Which DevTune project are you connected to?
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 Gemini CLI what AI platforms say and what AI systems fetch from your site:
What is our share of voice across AI platforms over the last 30 days, and how has it changed?
Which pages and domains do AI platforms cite for our topics, and which competitors get cited where we are not?
What are AI systems fetching from our site, and which pages do they ask for that do not exist?
Gemini CLI 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:
List the top five actions DevTune suggests for this project, with the evidence behind each.
Accept the first action, generate its brief and show me the brief.
Mark that action live. The page is published at https://example.com/your-page.
devtune_get_actionslists the queue with its evidence.devtune_change_action_statusaccepts an action, anddevtune_generate_action_briefwrites its brief. Generating a brief spends credits.- Gemini CLI 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. devtune_change_action_statuswithmark_liveand the published URL starts the before/after measurement.
Prove
Which of our shipped actions have results, and what moved?
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 Gemini CLI runs DevTune tools
Gemini CLI names the tools mcp_devtune_<tool> and asks before it runs each one. Adding --trust to gemini mcp add skips every confirmation for DevTune, including for tools that change your project, so leave it off.
Limits
- Browser sign-in needs a browser on the same machine. Over SSH or in a container, use an API key.
- 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
| Symptom | What to do |
|---|---|
gemini mcp list shows devtune as Disabled | Gemini CLI does not start project servers in a folder you have not trusted. Trust the folder when Gemini CLI asks, then check again. |
| Gemini CLI lists no DevTune tools | Check the connection as described above. With an API key, confirm the key is active under API Keys and has not expired. |
A tool is missing, or a call is refused with 403 | The connection lacks that tool's scope, or the plan lacks the feature. Ask the agent which scopes the connection has, then edit the key or sign in again with the scope selected. |
| Changes are refused but reads work | The connection has read scopes only, or the project is paused. Add the scope to the key or sign in again with it selected; resume a paused project in DevTune. |
A figure comes back empty or as Unmeasured | DevTune has no measurement for that window. Report it as unmeasured, not as zero. |
Next steps
- Gemini CLI documentation: how Google documents connecting outside tools
- MCP server: every tool, its inputs and its scope
- Code mode: two tools in place of the full list, for agents short on context
- API authentication: keys and scopes
- Use DevTune with your agent: setup guides for other agents
Make AI describe you the way you'd describe yourself.
No card required