Before you start
- A DevTune project on a plan that includes API access. No account yet? Let your agent set one up.
- Claude Code 2.1.275 or later for the plugin install command below. Run
claude --versionto check. - 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
Install the DevTune plugin. It adds the DevTune server and the DevTune skills:- Confirm the marketplace when Claude Code asks, then choose where to install the plugin.
- Run
/mcpand choose devtune. - Sign in to DevTune in the browser, select the project, choose the scopes the connection may use, and approve.
claude mcp add --transport http devtune https://devtune.ai/api/mcp, then run /mcp and sign in.
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 the server. The single quotes keep the key out of the file. Claude Code saves the variable name and reads the key when it connects.--scope project writes .mcp.json in the current folder, which you can commit. Leave it out to keep the server to yourself in this folder, or use --scope user for every project.
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
Runclaude mcp list. A working connection shows devtune with ✔ Connected. ! Needs authentication means you still need to run /mcp and sign in. A project-scoped server shows ⏸ Pending approval until you start claude in that folder and approve it.
Then ask Claude Code:
devtune_get_connection_context. If it names the wrong project, connect again and select the right one.
Measure
Ask Claude Code what AI platforms say and what AI systems fetch from your site: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: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.- Claude 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. devtune_change_action_statuswithmark_liveand 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 Claude Code runs DevTune tools
Claude Code names the toolsmcp__devtune__<tool>, for example mcp__devtune__devtune_get_visibility_summary. Tools from the plugin are named mcp__plugin_devtune_devtune__<tool>. Claude Code asks before it runs a tool unless you have allowed it.
For a scripted run, allow the tools you need by name:
Skills
The DevTune skills tell the agent which DevTune tool answers which question and how to report the numbers the way DevTune measures them. The plugin includes the DevTune skills. Without the plugin, add them yourself:Limits
claude -pcannot open the browser sign-in. Sign in from an interactive session first, or use an API key.- Claude Code cuts a tool result off at 25,000 tokens by default. Ask for a narrower window or fewer rows, or raise
MAX_MCP_OUTPUT_TOKENS. - 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
- Claude Code documentation: how Anthropic 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