integrations tools semrush

    Semrush MCP for your AI agent

    Cogny's Semrush integration exposes 9 tools (9 read) to an AI agent over MCP. The same tools are available on every plan, from your own AI client or inside the Cogny app.

    • 9readonly reads data.
    • 0writecreates or changes something.
    • 0destructivedeletes, removes or replaces something.

    Over MCP your own AI client asks before it runs a write. To take a tool away from your agent, block it in Settings → Integrations. Plans, approvals and limits

    set it up.

    Add Cogny to your AI client once, then connect Semrush in Cogny. Every Semrush tool below appears in the client.

    • Claude CodeRun claude mcp add --transport http cogny https://app.cogny.com/mcp, then authorise in the browser.
    • Claude.aiSettings → Connectors → Add custom connector, URL https://app.cogny.com/mcp, then log in and pick your workspace.
    • ChatGPTSettings → Apps → Advanced settings → Developer mode → Create app, URL https://app.cogny.com/mcp, authentication OAuth.
    • CursorIn Cogny, Settings → Data & Integrations → Connect AI Clients shows the block to paste into .mcp.json, with an API key.
    • CodexRun codex mcp add cogny --url https://app.cogny.com/mcp.

    Full setup, and how to undo it

    what each tool does.

    Read 9 · only reads data

    • domain_overviewReadSummary metrics for a domain.
    • domain_organic_keywordsReadKeywords the domain ranks for in organic search.
    • domain_paid_keywordsReadKeywords the domain pays to advertise on.
    • domain_organic_competitorsReadTop organic competitors of a domain.
    • backlinks_overviewReadBacklinks summary. target_type: root_domain | domain | url.
    • backlinksReadList backlinks to a target.
    • keyword_overviewReadKeyword volume, CPC, competition.
    • phrase_relatedReadRelated keyword ideas.
    • phrase_organicReadTop ranking URLs for a keyword in organic results.

    Exact input schemas come from tools/list once Semrush is connected; the free plan is enough to check. Missing something? Your agent can ask for it with request_feature.