# Prominara MCP server > Your AI visibility data, in the assistant you already use. URL: https://mcp.prominara.com. Page: https://prominara.com/mcp. Updated: 2026-09-02. The Prominara MCP server is a remote Model Context Protocol server that connects your own AI assistant to your Prominara workspace, a GEO platform that tracks brand visibility across AI answers. It is included in every Prominara plan and in the 14-day trial, so any customer can connect Claude, ChatGPT, Cursor or Codex today. Ask what you are cited for, run a check, log the page you shipped, read the verdict. Same data, same quotas, no new dashboard to learn. Author: Nicolás Rodriguez Seara, Founder, Prominara. Profile: https://prominara.com/authors/nicolas-rodriguez-seara. ## What is Prominara Prominara is a Generative Engine Optimization (GEO) platform: track how ChatGPT, Perplexity, and Google AI answer your buyers’ questions, then fix what keeps your brand out of the answer. ## What can my agent do? 14 tools, namespaced `prominara_`. Read tools need the `read` permission; act tools need `write`, which you can leave ungranted. ### Read - **List sites** (`prominara_list_sites`, read permission, No quota): Lists the sites (brands) in the connected Prominara organization with domain, brand name, latest audit score, last scan date and active prompt count. Call this first to learn which site identifiers to use with the other tools; sites can be addressed by domain or id. - **Visibility overview** (`prominara_visibility_overview`, read permission, No quota): Returns AI-search visibility for one site over a window (default 30 days): citation and mention rates with confidence intervals, per-platform breakdown, trend versus the previous window, and the competitor ranking. Rates use earned prompts and successful checks only. Use concise for headline numbers, detailed for per-prompt rows. - **List tracked prompts** (`prominara_list_prompts`, read permission, No quota): Lists the prompts tracked for a site with category, panel (organic, branded, competitive), active state and the latest result per platform. Filter by status or search text. Use it to find prompt ids before calling get_answers, run_check or set_prompt_active. - **Get latest AI answers** (`prominara_get_answers`, read permission, No quota): Returns the latest recorded AI answers for one prompt: per platform whether the brand was mentioned or cited, the sources the answer used, position and sentiment, plus check history. Detailed mode includes the answer text, returned as untrusted third-party content. - **List missions** (`prominara_list_missions`, read permission, No quota): Lists the prioritized missions for a site: for each tracked prompt, the current visibility, the page that should own the answer (or the gap), the source gap and the next best action, ranked by priority. Filter by priority, status or intent. - **Sources intelligence** (`prominara_sources`, read permission, No quota): Returns the off-site sources behind AI answers for a site. Views: domains (which sites AI answers cite and whether they mention the brand), citations (individual cited pages), opportunities (ranked places to earn a citation) and accuracy (factual issues found in answers about the brand). - **Measurement verdicts** (`prominara_measurement`, read permission, No quota): Returns the impact measurement for content changes logged on a site: per change, the observation window status and the verdict (likely lift, no effect, still collecting) with its probability, plus the program-level before/after comparison when enough data exists. Pass a change id for the detail of one change. Verdict wording is the product's own and does not claim causation beyond what the design supports. - **Suggest prompts to track** (`prominara_suggest_prompts`, read permission, Uses AI suggestion allowance): Returns suggested prompts for a site from the coverage matrix (organic, branded and competitive panels across buyer-journey stages), with a recommended set for the plan's slots. Uses the cached set when one exists; generating a fresh set counts against the AI suggestion allowance. - **Plan and usage** (`prominara_usage`, read permission, No quota): Returns the organization's plan, monthly check quota used and remaining with the reset date, tracked prompt slots used, platform slots and trial state. Call it before running checks or creating prompts to know what fits. ### Act - **Create tracked prompts** (`prominara_create_prompts`, write permission, Uses prompt slots): Adds up to 20 prompts to track for a site and triggers their first checks. Duplicates of existing prompts are skipped, prompts beyond the plan's slots are skipped and reported, and platforms are clamped to the plan. Returns what was created, what was skipped and why. - **Run a check now** (`prominara_run_check`, write permission, Uses check quota): Runs a fresh visibility check for up to 10 prompts across the site's enabled AI platforms, exactly like "Run now" in the app. Each check counts against the monthly quota. Prompts with a check already in progress are skipped and reported. Results arrive asynchronously; read them with get_answers after a minute or two. - **Log a shipped content change** (`prominara_log_content_change`, write permission, Opens a measurement window): Records that a page on the site was changed (edited, published, structured data added) with the release date and a summary, so Prominara can measure its impact on AI visibility. Creates the before/after experiment and freezes the affected prompts. Logging the same page and date twice returns the existing change. - **Update mission status** (`prominara_update_mission`, write permission, No quota): Sets the status of one mission (per prompt) on a site: new, in_progress, shipped, snoozed (with a date) or dismissed. Use shipped after the page work is live, or log_content_change which does it automatically. - **Enable or disable prompts** (`prominara_set_prompt_active`, write permission, Uses prompt slots): Activates or deactivates up to 50 tracked prompts. Deactivated prompts stop being checked and free a slot; activating re-checks the plan's prompt slots and reports any that do not fit. ## What does that look like in a conversation? - "Which of my tracked prompts lost citations this month, and which page should I fix first?" Reads the visibility overview for the window, pulls the ranked missions, and answers with the prompts that moved and the page that should own each answer. - "Add five prompts about serverless database pricing and check them now." Creates the prompts against your plan slots, skipping duplicates, then runs the first checks. It tells you what was created, what was skipped and how much quota is left. - "I published the new comparison page today. Log it against the prompts it targets." Records the content change with its release date, freezes the affected prompts and opens the before-and-after observation window. - "Did the page I shipped three weeks ago move anything yet?" Returns the measurement verdict for that change with its probability, range and evidence grade, in Prominara’s own wording. - "Which domains does ChatGPT cite in my category, and do any of them mention us?" Reads the sources view for the site and lists the cited domains, whether each one names your brand, and the ranked places to earn a citation. ## How do I connect? 1. **Add the server to your client.** In Claude, ChatGPT, Cursor, Codex or any other MCP client, add https://mcp.prominara.com as a remote MCP server. 2. **Sign in and choose what the agent may do.** Your client opens a Prominara consent page. Pick the organization and grant read, or read and write. 3. **Ask your agent about your AI visibility.** Ask what you are cited for, run a check, log a page you shipped, or read the measurement verdict. ### Claude (web and desktop) Add Prominara as a custom connector, then sign in once. 1. Open Settings, then Connectors. 2. Choose Add custom connector. 3. Paste https://mcp.prominara.com as the server URL and save. 4. Claude opens a Prominara consent page. Pick the organization, choose read or read and write, and approve. Setup guide: https://prominara.com/docs/agents/claude ### Claude Code One command in your terminal. 1. Run the command below in any project. 2. Run /mcp inside Claude Code and choose Authenticate to sign in. ```bash claude mcp add --transport http prominara https://mcp.prominara.com ``` Setup guide: https://prominara.com/docs/agents/coding-agents ### ChatGPT Connect it as a developer-mode connector. 1. Open Settings, then Connectors, then Advanced, and turn on developer mode. 2. Choose Create, then paste the server URL. 3. Use https://mcp.prominara.com and pick OAuth as the authentication method. 4. Approve the Prominara consent screen that opens. Setup guide: https://prominara.com/docs/agents/chatgpt ### Cursor One click, or add the server to your MCP config. 1. Use the install button, or add the block below to ~/.cursor/mcp.json. 2. Open Settings, then MCP, and click Login next to Prominara. ```json { "mcpServers": { "prominara": { "url": "https://mcp.prominara.com" } } } ``` One-click install: cursor://anysphere.cursor-deeplink/mcp/install?name=prominara&config=eyJ1cmwiOiJodHRwczovL21jcC5wcm9taW5hcmEuY29tIn0= Setup guide: https://prominara.com/docs/agents/coding-agents ### Codex One command, same as Claude Code. 1. Run the command below. 2. Follow the browser prompt to sign in to Prominara. ```bash codex mcp add prominara --url https://mcp.prominara.com ``` Setup guide: https://prominara.com/docs/agents/coding-agents ### VS Code Install with one click, then sign in. 1. Use the install button below. 2. VS Code asks you to sign in to Prominara the first time a tool runs. One-click install: vscode:mcp/install?%7B%22name%22%3A%22prominara%22%2C%22type%22%3A%22http%22%2C%22url%22%3A%22https%3A%2F%2Fmcp.prominara.com%22%7D Setup guide: https://prominara.com/docs/agents/coding-agents ### Any other client Anything that speaks MCP over streamable HTTP works. 1. Run the command below to add the server to a client of your choice. 2. Or point the client at https://mcp.prominara.com by hand. Authentication is OAuth 2.1, discovered automatically. ```bash npx add-mcp https://mcp.prominara.com ``` Setup guide: https://prominara.com/docs/agents ## How is it secured? - **OAuth 2.1, not pasted keys.** You sign in to Prominara in your browser with PKCE. There is no key to copy into a config file, and nothing long-lived sits on your machine. - **Consent on every connection.** Each new connection shows the client asking, where it will send you back, and the organization you are connecting. Nothing is approved silently from a previous grant. - **Read and write are separate.** Write is a scope you can leave unchecked at consent. A read-only connection can look at everything and change nothing. - **No tool deletes anything.** The catalog covers reads and safe writes. Nothing touches billing, team settings, deletion, or another organization. - **The same quotas as the app.** A check your agent runs counts exactly like pressing Run now, against the same monthly allowance. Refusals say which limit was hit and when it resets. - **Revoke whenever you want.** Every connection is listed under Settings, Connected agents, with the client, the scopes and when it was last used. Revoking takes effect on the next call. ## Choosing a GEO tool for your agent - **Sign-in, not key-pasting.** Prefer OAuth. A tool that asks you to paste a long-lived key into a config file puts a credential on disk that nobody can revoke from the product. - **Read and write, not read only.** An agent that can only report leaves you doing the work by hand. Creating prompts, running checks and logging what you shipped is where the time goes. - **Verdicts, not just counts.** A citation count answers what happened. Whether the page you shipped moved anything needs a before-and-after design with a control group. - **No separate usage units.** Agent calls should draw on the plan you already pay for, not on a second meter with its own pricing. - **Available on the cheapest plan.** Check the entry tier, not the top one. Prominara includes agent access from Starter at $29 per month and in the 14-day trial. ## What an agent can and cannot tell you - **The verdict is the product’s, not the model’s.** Measurement wording comes from Prominara and ships as a probability with a range and an evidence grade. Your agent relays it. It does not compute a verdict of its own from the numbers it reads. - **A citation rate is a measurement, not a ranking.** Rates describe the prompts you track, on the checks that succeeded, using questions that never name your brand. There is no placement to buy and none is promised. - **Answer text is third-party content.** When a tool returns what an AI engine said about you, it is marked as untrusted third-party text so your agent treats it as evidence to read, never as instructions to follow. - **No timeline is implied.** Checks run asynchronously and results land when the platforms answer. Nothing here states how long a content change takes to show up, because that is not ours to promise. Measurement protocol: https://prominara.com/methodology ## Frequently asked questions **What is the Prominara MCP server?** It is a remote Model Context Protocol server at https://mcp.prominara.com. Adding it to an MCP client such as Claude, ChatGPT, Cursor or Codex lets that assistant read your Prominara data and take a small set of safe actions on your behalf, using your own account. **Which plans include it?** Every plan, and the 14-day trial. Agent access starts at Starter, $29 per month. There is no separate purchase and no extra usage meter. **Which AI clients work with it?** Claude on web and desktop, Claude Code, ChatGPT in developer mode, Cursor, Codex and VS Code, plus any other client that supports remote MCP servers over streamable HTTP with OAuth. **Do I need to write any code?** No. You add a URL in your client’s settings and sign in to Prominara in the browser. Coding agents offer a single command instead, which does the same thing. **Can my agent delete or break something?** No tool deletes data, changes billing, edits team settings or reaches another organization. Writes are limited to creating tracked prompts, running a check, logging a content change, setting a mission status and turning prompts on or off. You can also grant read only. **Does an agent check cost more than a check in the app?** No. It draws on the same monthly check allowance as the app. If a limit is reached, the tool says which limit, what remains and when it resets, rather than silently spending. **What does the agent actually receive?** Only what the tools return for the organization you consented to: your sites, prompts, recorded answers, sources, missions, measurement verdicts and plan usage. Nothing about other customers, and nothing outside the scopes you granted. **How do I disconnect an agent?** Open Settings, then Connected agents, and revoke the connection. It stops working on the next call. You can reconnect later, which creates a fresh consent. ## Links - [Prominara MCP server](https://prominara.com/mcp) - [Connect your AI agent documentation](https://prominara.com/docs/agents) - [Tools reference](https://prominara.com/docs/agents/tools) - [Pricing](https://prominara.com/pricing) - [Measurement methodology](https://prominara.com/methodology) - [Privacy policy](https://prominara.com/privacy)