MCP Integration for Claude, Cursor and ChatGPT

Connect your AI visibility data directly to Claude Desktop, Cursor, ChatGPT and any MCP-compatible agent. Ask your AI what LLMs say about you, surface backlink opportunities, and manage competitors from your chat, not a dashboard.

Curious if AI mentions your brand?

Run a free scan and see where you stand on ChatGPT.

Free AI Scan

Key Takeaways

  • Native MCP server exposes your AI visibility data to any MCP-compatible client: Claude Desktop, Cursor, ChatGPT, Claude Code and others.
  • 7 tools available on day one: list projects, list prompts with mention stats, list LLM-cited sources (visible + hidden + fan-out), list backlink opportunities with marketplace offers, list competitors, list competitor sources, bulk update competitor status.
  • Bring-your-own-agent architecture: the data lives in Mentionable, the reasoning lives in your AI. You ask Claude a question, Claude pulls the data it needs through MCP, answers in context. No copy-paste, no dashboard tabs.
  • Per-user API keys scoped to your tenant membership. Keys inherit your project permissions, can be restricted further per project, and are revokable with one click. Writes (competitor moderation) respect role gating.
  • The only AI visibility tracker with a public MCP server. Otterly, Peec AI, Profound and competitors still force you to read dashboards. Mentionable makes your data callable from the tool you already use.

You open Claude Desktop. You ask: "How did my AI visibility move this week, and which sources should I pitch?". Claude pulls the data from Mentionable through MCP, looks at your tracked prompts, sees which domains cite your top two competitors but not you, ranks them by impact score and marketplace price, and gives you a four-line outreach shortlist.

No tab switching. No copy-pasting dashboard screenshots into a chat. No "let me check that in Mentionable and come back". Your AI has the data, because the data goes where AI lives.

What is MCP and why is it in a GEO product

The Model Context Protocol is an open standard introduced by Anthropic in late 2024 that lets AI agents call external tools and data through a common interface. A client (Claude Desktop, Cursor, Claude Code, ChatGPT with custom connectors, Zed) implements the client side. A vendor (Mentionable, in this case) implements a server that exposes tools and resources. The agent discovers the tools, invokes them when relevant to the user's request, reads the response, and incorporates the data into its answer.

For an AI visibility tracker, this is not a nice-to-have. It is the natural distribution channel.

Most marketing tools built in the last decade assumed the dashboard was the product. You pay, you log in, you read charts, you export CSVs. The model made sense when marketers read reports in the morning and took decisions in a UI.

The model does not make sense when the marketer's daily tool is an AI agent. A consultant drafting a blog post inside Cursor, an agency operator using Claude Desktop to run 5 client projects, a founder asking ChatGPT to summarize their weekly metrics: they do not want to leave their AI to check a dashboard. They want the dashboard's answer inside the AI.

MCP is the protocol that makes this work. Mentionable's server makes it real.

The 7 tools, and what they unlock

The MCP server exposes 7 tools on launch, aligned with the highest-signal data Mentionable already tracks.

list_projects

Your workspace's projects, with tenant scoping applied automatically. The entry point for any agent workflow. Every other tool takes a projectId, so this is the first call the agent makes when you ask "what is happening across my brands".

list_prompts

Every tracked prompt for a project, with its full stats: total runs, mention rate, visibility per LLM (ChatGPT, Perplexity, Gemini, Grok, Copilot, Google AI Mode, Google AI Overview), latest result per LLM with brand position and sentiment. An agent can answer "which prompts am I losing visibility on this month" in one call.

list_llm_sources

The most valuable tool for content strategy. Returns every domain that appeared in LLM responses for your tracked prompts, broken down into three types of appearance:

  • Visible citations: the LLM cited this domain in its answer, the user saw the link
  • Hidden citations: the LLM read this domain in its context but did not cite it in the final answer (available on LLMs that expose this signal, typically Perplexity and Gemini)
  • Fan-out searches: the LLM ran a background search and found this domain in the results, whether it cited it or not

The fan-out data is a GEO goldmine. It tells you which domains the LLM considers when answering prompts in your niche, even if no citation was ever shown to the user. Those domains are the real influence map. An agent can ask the tool for domains with high fan-out count but low visible-citation count, and you immediately see the sites LLMs consult but do not credit: prime candidates for content collaboration or backlink outreach.

list_backlink_opportunities

Domains where placing a backlink could lift your GEO visibility, ranked by a composite impact score that weights citation count, fan-out frequency, number of distinct LLMs that cite the domain, and number of your tracked prompts where the domain appears. Each domain comes with its current marketplace offers (price, provider) from Mentionable's aggregated backlink data. An agent can answer "what is my best backlink opportunity under €500" with a single tool call and return a sorted shortlist, not a wall of noise.

list_competitors

The competitors tracked on a project, with aggregated mention totals, Share of Voice, per-LLM presence, and status (confirmed, suggested, rejected). The foundation for competitive intelligence conversations with your AI.

list_competitor_sources

The single most useful outreach endpoint. Given a specific competitor, the tool returns every domain where that competitor gets cited, with mention count, LLMs, top URLs, and sample context from the LLM response. If your competitor is cited 12 times on a specific review site and you are not, that site is a direct outreach target. An agent can prepare a full competitive outreach list in one prompt.

bulk_update_competitor_status

The write tool. Accepts up to 50 competitor updates in a single call, each either CONFIRMED, SUGGESTED (pending) or REJECTED. An agent can run the common operational workflow entirely from chat: "list the 12 competitor suggestions detected last week, keep these 8 as real competitors, reject these 4 as noise". One call, atomic results, per-item error handling when an ID is invalid.

Real workflows, not demos

The value of MCP shows up in specific workflows that collapse multi-step manual work into a single conversation.

Content briefs from AI citation data

You ask Claude: "Write a content brief for the prompt 'best gym management software'. Use the top 5 cited sources as reference material and explain why each ranks."

Claude calls list_llm_sources filtered on that prompt, gets the top 5 domains with their fan-out queries and sample URLs, reads the titles and seenAs classification, and drafts a brief that structurally mirrors what the LLMs already value. Your brief is not speculation. It is derived from real citation signals.

Outreach lists without spreadsheets

You ask ChatGPT: "Find me 15 outreach targets for this month. I want domains that cite at least two of my three top competitors but have never cited us."

ChatGPT calls list_competitor_sources on each of your three top competitors, intersects the domain lists, compares against list_llm_sources for your own citation footprint, removes domains where you already appear, and returns a ranked list with the competitor citation counts and your current absence score. A manual version of this workflow takes 90 minutes of spreadsheet work.

Operational triage in one conversation

You ask Claude Desktop: "Show me the competitor suggestions detected in the last 14 days. I will review each and confirm or reject."

Claude calls list_competitors filtered on SUGGESTED status recently created, presents them with context and mention count, you approve or reject each from chat, Claude calls bulk_update_competitor_status once with the full batch. Triage that used to eat 20 minutes of clicking in the app, done in a two-minute conversation.

Security model you can reason about

A single principle: an API key can never grant access beyond what the user already has.

Keys are scoped to your TenantMember (your user-tenant pair). If you belong to two workspaces, each workspace has its own set of your keys. You create a key in the workspace settings under Integrations, give it a name, optionally restrict it to specific projects within your scope, copy the plaintext once (shown a single time), and configure your AI client.

On every call, the server resolves the effective permissions by intersecting your current membership permissions with the key's optional restrictions. If you later get removed from the workspace, your keys stop working immediately on the next call. If your role gets downgraded to read-only (customer), your keys immediately start rejecting write operations. Nothing is cached, no stale permission grants.

Plaintext is never stored. The server stores a SHA-256 hash of the key and a visible prefix for identification in the UI. Revocation is one click and takes effect on the next call.

Rate limits are applied per key using a sliding window: 100 requests per minute by default, generous enough for normal AI agent traffic.

Setup in under 60 seconds

For Claude Desktop, add the server to your configuration:

{
  "mcpServers": {
    "mentionable": {
      "url": "https://mentionable.ai/api/mcp",
      "headers": {
        "Authorization": "Bearer mnt_sk_YOUR_KEY"
      }
    }
  }
}

For Cursor, the format is similar. For Claude Code, use the CLI to register the server. For ChatGPT, add Mentionable as a custom connector using the same URL and Bearer token.

Create a key in Mentionable → Settings → Integrations → API Keys, paste it into your client config, restart the client, and your next Claude conversation can call your Mentionable data.

Why no other AI visibility tracker offers this

The short answer: because building an MCP server correctly means committing to a stable tool contract, proper per-user authentication, membership-aware permissions, and a data model worth querying. Most AI visibility tools are dashboard shells on top of scraping. They do not have normalized, API-friendly data underneath.

Mentionable has had a proper multi-tenant data model and auth layer from day one, because the app itself is multi-user. Adding MCP was a natural extension, not a retrofit.

Otterly, Peec AI and Profound ship dashboards. Mentionable ships an AI-native data platform that also has a dashboard.

The bigger bet

The tools that survive the LLM transition are the ones that stop assuming the human will open their UI. The product is the data. The UI is one interface. MCP is another. Tomorrow there will be more.

If you run marketing in 2026 and your AI assistant cannot access your visibility data without you copy-pasting, you are paying for the wrong tool.

Try it

Start a free trial, create an API key from Settings → Integrations, paste the Bearer token into Claude Desktop, and ask your AI your first real question about your visibility.

Related articles

Frequently Asked Questions

What is MCP and why does it matter for AI visibility tracking?
MCP stands for Model Context Protocol, an open standard that lets AI agents call external tools and data sources. With Mentionable's MCP server, Claude Desktop, Cursor, ChatGPT, Claude Code and any MCP-compatible client can query your AI visibility data directly. Instead of switching to a dashboard to check your mention rate, you ask Claude: the answer comes back with your real numbers from Mentionable in seconds.
Which AI clients support MCP today?
Claude Desktop (first-party), Claude Code, Cursor (via config), ChatGPT (via custom connectors), Zed editor, and an increasing number of third-party agents. The protocol is open so any agent vendor can add support. Mentionable's MCP server uses standard Streamable HTTP transport, which is the universal MCP deployment mode for web-hosted servers.
What tools does the Mentionable MCP server expose?
Seven tools on launch: list_projects (all projects accessible to the key), list_prompts (tracked prompts with mention rate, visibility by LLM, latest run per LLM), list_llm_sources (domains cited in LLM responses plus fan-out searches, with visible/hidden/fan-out breakdown), list_backlink_opportunities (domains where placing a backlink could lift GEO visibility, with marketplace offers and best-price sorting), list_competitors (tracked competitors with Share of Voice and per-LLM presence), list_competitor_sources (where a specific competitor gets cited, the prime outreach list), and bulk_update_competitor_status (confirm or reject competitor suggestions in batch).
How are API keys secured?
Keys are generated with 192 bits of entropy, hashed with SHA-256 before storage, and only the plaintext is shown once at creation. Each key is scoped to a single tenant membership, inherits the role and project restrictions of the user who created it, and can be further restricted to specific projects. Keys never grant broader access than the underlying user has. Revocation is one click and takes effect immediately on the next call. Write operations respect role gating: a customer-role user creating a key still cannot mutate data through it.
Can my AI agent modify data through MCP or only read?
Read and one controlled write. The read tools (list projects, prompts, sources, backlinks, competitors) cover the query use cases. The write tool, bulk_update_competitor_status, lets an agent confirm or reject up to 50 competitor suggestions in a single call, which is the most common batch operation users run in the app. Additional write tools are intentionally restricted for safety and will expand based on usage signals. Every write goes through the same permission checks as the web UI.
Do I need to be on a specific plan to use MCP?
MCP is available on every Mentionable paid plan, starting with Growth at EUR 79/month. Each plan includes API key generation from the workspace settings under the Integrations tab. Rate limits are applied per key (100 requests per minute by default) and are generous enough for normal AI agent usage. For high-volume workflows, contact us to discuss higher quotas.
Which workflows are best done through MCP instead of the app?
Three categories benefit most. Content briefs: ask Claude to pull the top-cited sources for a tracked prompt, then draft a brief that targets those sources. Outreach prep: ask your agent to list competitor citation sources where your brand does not appear, with suggested email angles. Operational triage: ask Claude to show competitors detected in the last 7 days that need moderation, review each, then confirm or reject in bulk. The app stays the best place for deep dashboards, tracking setup, scan credit management, and content generation.
How does this compare to Otterly, Peec AI or Profound?
As of April 2026, Mentionable is the only public-facing AI visibility tracker with an MCP server. Otterly and Peec AI offer dashboards and some export APIs, but no native MCP integration. Profound targets enterprise with broader analytics but no MCP either. If your team already uses Claude Desktop or Cursor for daily work, MCP collapses the round-trip between your AI assistant and your visibility data. That is not a small workflow win, it is a different product category.
Is the MCP server stable and production-ready?
The server is built on the official @modelcontextprotocol/sdk and the Vercel mcp-handler adapter, both production-grade. It runs in Next.js 16 on the same stack that serves the web app, with the same auth model, the same rate-limiter, and the same database. It is covered by unit tests and tested end-to-end in dev. The API surface is versioned through the server info metadata and tool names will be treated as a stable contract once past the 0.x phase.

Ready to check your AI visibility?

See if ChatGPT mention you on the queries that actually lead to sales. No credit card required.

Keep Reading