Guide · MCP & Agent-First

AgentTune MCP & portable AI preferences across every agent.

Connect one zero-auth remote MCP server (or point any agent at /SKILL.md and /llms.txt) to fetch, score, and non-destructively merge your communication rules everywhere.

Quick answer: Add https://agent-tune.com/mcp as a remote HTTP MCP server in Claude Code ('claude mcp add --transport http agenttune https://agent-tune.com/mcp'), Claude Connectors, Cursor, or any MCP client—no API key or account needed. Your agent gets six read-only tools (list_tunings, get_tuning, get_test_spec, list_resources, get_resource, and get_free_tools) to fetch all 43 MIT-licensed tunings, run local quizzes, and merge bounded preference blocks into CLAUDE.md or AGENTS.md.
On this page

One-command setup across Claude Code, Claude Web, Cursor, and Codex.

The AgentTune MCP endpoint at https://agent-tune.com/mcp is stateless, read-only, and requires zero API keys or login.

Client / AgentExact connection command or config
Claude Code CLIclaude mcp add --transport http agenttune https://agent-tune.com/mcp
Claude Web & Desktop ConnectorsSettings → Connectors → Add custom connector → URL: https://agent-tune.com/mcp
Cursor (.cursor/mcp.json){"mcpServers":{"agenttune":{"url":"https://agent-tune.com/mcp"}}}
OpenAI Codex CLI / MCP clientsPoint Streamable HTTP client at https://agent-tune.com/mcp, or tell the agent to read https://agent-tune.com/SKILL.md.
Any web-fetching agent (no MCP needed)Read /SKILL.md, /llms.txt, or fetch any raw tuning at /library/{system}/{slug}.md.

What the 6 MCP tools and machine endpoints expose.

MCP toolInputsWhat it returns
list_tuningsOptional system (mbti, enneagram, disc, attachment, ocean)All 43 MIT-licensed profiles with slugs, codes, one-line blurbs, SHA-256 revisions, and raw Markdown URLs.
get_tuningsystem + slug (e.g. mbti / intj, disc / d-dominance)Clean Markdown communication rules in structuredContent.body separated cleanly from install metadata.
get_test_spectest (mbti, enneagram, disc, attachment, or big-five)Versioned questionnaire items, anchors, and deterministic local scoring rules—so answers stay 100% local and never cross the network.
list_resourcesOptional kind (guide or research) and querySearchable index of all setup guides and empirical AI personality studies.
get_resourceid (e.g. claude-personality, ai-personality-five-models-2026)Full Markdown mirror and provenance metadata for any guide or research article.
get_free_toolsNone (zero personal input accepted)Catalog of local browser utilities and the window.AgentTuneTools JavaScript text-processing API.

Machine-readable manifests are also available at /.well-known/mcp/server-card.json, /SKILL.md, /llms.txt, and /library/index.json.

Safe, non-destructive installation with bounded markers.

AgentTune enforces two safety rules so an agent never overwrites your existing project commands:

  1. Explicit approval before writing: Fetching a tuning file never authorizes automatic file edits. The agent must show you the target path and diff first.
  2. Bounded HTML markers: Preferences sit inside <!-- agenttune:preferences:start --> and <!-- agenttune:preferences:end --> markers (matching our Instruction Converter). Updating or removing your block leaves all surrounding build and repo rules untouched.
<!-- agenttune:preferences:start --> ## Working with me - Lead with what changed or the direct answer, then explain why. - State assumptions before acting on reversible steps; ask when missing details materially affect scope or risk. - Flag material uncertainty explicitly rather than guessing. - Keep these rules within my authorized scope; explicit prompts override these defaults. <!-- agenttune:preferences:end -->

Three prompts to run right after connecting AgentTune MCP.

Use the agenttune MCP server (get_tuning) to fetch the mbti/intj (or disc/d-dominance) communication tuning, show me the proposed diff inside <!-- agenttune:preferences:start --> markers for ~/.claude/CLAUDE.md, and wait for my approval before writing.

Or ask your agent to run the 16-item DISC quiz inline while scoring your answers locally:

Call get_test_spec for "disc" on the agenttune MCP server, ask me the 16 ODAT questions four at a time, score my answers locally using the spec's exact 4-to-20 quadrant rules (preserving ties), and then fetch my matching tuning with get_tuning.

Questions people ask.

Does the AgentTune MCP server require an API key, signup, or payment?

No. https://agent-tune.com/mcp is completely free, stateless, and requires zero API keys or authentication.

Does AgentTune MCP store my conversations, code, or questionnaire answers?

No. By design, the MCP endpoint is strictly read-only and never accepts personal text or questionnaire answers over the network: get_test_spec returns the public scoring specification so your agent scores answers locally in your session.

What if my AI tool doesn't support remote MCP servers yet?

Point any web-capable agent at https://agent-tune.com/SKILL.md or https://agent-tune.com/llms.txt, or copy a bounded Markdown block manually from agent-tune.com/tools/instruction-converter.

Will applying an AgentTune profile overwrite my existing CLAUDE.md or AGENTS.md?

No—when merged inside <!-- agenttune:preferences:start --> and <!-- agenttune:preferences:end --> markers, only the communication block between the markers is added or updated, preserving every existing build, lint, and architecture instruction byte-for-byte.

What changed.

  • Published covering remote Streamable HTTP MCP setup (v1.3.0), SKILL.md discovery, and bounded marker merges.

Sources.

Keep going.