Connect Your AI via MCP (ChatGPT, Claude & More)

MCP (Model Context Protocol) is the open standard that lets AI assistants connect to external tools. LLM Pulse ships an MCP server, so you can ask ChatGPT, Claude, Gemini, Cursor, Windsurf, Zed, or any MCP-compatible client questions about your own visibility data, in your own AI tool.

With the LLM Pulse MCP connection, you can:

• Ask ChatGPT or Claude about your visibility, citations, and competitors without leaving your AI tool
• Connect once with OAuth, free on every plan, with no API key to manage
• Let your AI assistant pull live LLM Pulse data into any analysis or report it writes for you
• Use the same data from Cursor, Windsurf, Zed, Gemini, and any other MCP-compatible client

The OAuth-based connection is free on every plan and during eligible trials. Setup lives at Utilities > Integrations > MCP in the app.

What it does

• Exposes your LLM Pulse projects to your AI assistant through roughly 90 tools: visibility metrics, timeseries, share of voice, mentions, citations, sources, sentiment, prompts, responses, recommendations, and more
• Shows interactive views for metric trends, Share of Voice, top sources, detailed sentiment, reputation reports, and prioritized recommendations in supported ChatGPT and Claude chats. They follow your light or dark appearance automatically.
• Runs Technical GEO audits and reads the completed reports back into the same chat. The Agent Readiness report, sometimes called AI readiness, uses report type agent_readiness; you do not need to copy and paste it back into Claude.
• Your assistant can also act: create prompts, add competitors, create tags, launch recommendation runs (it will ask you before creating anything)
• Access is scoped to your account and respects your plan: tools for features your plan does not include are simply not offered to the client

Links back to LLM Pulse

• Responses, prompts and Technical GEO reports come back with a link to the same record in LLM Pulse, and metric results with a link to the page they come from. Ask your assistant to include these links in what it writes, so you can check every number at the source.
• Each link names its project, so it opens on that project even if you had another one selected. It only opens for people who already have access to that project.

How to set it up

1. In LLM Pulse, open Utilities > Integrations > MCP for the guided instructions per client
2. In your AI client's connector or MCP settings, add the server URL: https://api.llmpulse.ai/api/v1/mcp
3. Your client opens a browser window; sign in with your LLM Pulse account and authorize
4. Ask something like "list my LLM Pulse projects" to confirm the connection works

For headless or scripted use (CI, automations), MCP also accepts a Bearer-token API key instead of OAuth. API keys require a Scale plan or above and are created from the profile menu under API Keys.

Troubleshooting

• Connection fails or tools don't appear: remove the LLM Pulse connection from your AI client, re-add the URL, and complete the browser authorization again. A previously failed or expired authorization is the most common cause.
• Prefer OAuth over an API key for personal use; it is simpler and works on every plan
• A tool seems missing: tool availability follows your plan and, for team members, your permission role. If a feature is locked in the app, its MCP tool is filtered out too.
• Still stuck? Open a ticket from the support page with the client you are using (ChatGPT, Claude Desktop, claude.ai, Cursor) and what error you see

Tips & notes

• Your OAuth connection stays authorized for one year. After that, your AI client will ask you to authorize it again.
• ask_support stores the full question, the generated answer, your user identity, and your account plan so our support team can review conversations and improve support. Other MCP tools that query your data are not stored as support chats.
• Technical GEO audits run in the background. After starting one, your assistant should use the returned report IDs and check each report every 15 seconds until it completes or fails.
• MCP works well for ad-hoc questions, visual analysis, and cross-tool workflows; the built-in LLM Pulse Agent remains the fastest option when you are already working inside LLM Pulse
• The REST API (Scale and above) remains the right choice for building dashboards and custom integrations; see the REST API overview