Set up PandaCrawl MCP

PandaCrawl MCP lets compatible AI clients call PandaCrawl tools for keyword research, SERP inspection, local business research, competitive search intelligence, domain research, backlink overview, saved keywords, rank tracking, AI visibility tracking across ChatGPT, Claude, Gemini and Perplexity, shared project context, Google Search Console performance and URL inspection, Google Analytics, and Bing Webmaster Tools.

The hosted MCP server URL is:

https://app.pandacrawl.app/mcp

The first connection sends you through PandaCrawl login. After authorization, your MCP client can call PandaCrawl tools with the project context and account scopes you approved. For headless environments and CI, connect with an API key instead.

For the most current setup UI and a copyable endpoint, open AI & MCP in PandaCrawl.

Claude Code

Use user scope to make PandaCrawl available across projects. Use local scope for the current repository.

claude mcp add --transport http --scope user pandacrawl https://app.pandacrawl.app/mcp

After adding the server, approve the PandaCrawl login when prompted.

Claude (web and desktop app)

Custom connectors work on every Claude plan. The Free plan allows one custom connector.

1. Open Customize -> Connectors (in older versions, Settings -> Connectors).
2. Click +, then Add custom connector.
3. Name it PandaCrawl and paste https://app.pandacrawl.app/mcp.
4. Click Add, then Connect, and approve the PandaCrawl login.

On Team and Enterprise plans an owner adds the connector once, and each member connects with their own PandaCrawl login. See Claude for SEO for what to ask once it's connected.

ChatGPT

ChatGPT connects through custom MCP apps in developer mode, on ChatGPT for the web. Full use (reading data and starting actions such as crawls) needs ChatGPT Business, Enterprise or Edu. Pro can connect with read and fetch access only. Plus and Free can't add custom MCP apps yet.

1. Turn on developer mode: Settings -> Apps -> Advanced settings -> Developer mode. On Business, a workspace admin or owner does this for themselves.
2. Go to Apps -> Create, name it PandaCrawl and paste https://app.pandacrawl.app/mcp.
3. Choose OAuth, click Scan Tools, and approve the PandaCrawl login.
4. Click Create, then pick PandaCrawl from the tools menu in a new chat.

See ChatGPT for SEO for plan details and workflows.

Cursor

1. Open Cursor Settings -> Tools & Integrations -> MCP Tools.
2. Click New MCP Server. Cursor opens mcp.json.
3. Add:

{
  "mcpServers": {
    "pandacrawl": {
      "url": "https://app.pandacrawl.app/mcp"
    }
  }
}

4. Approve the PandaCrawl login when prompted.

Codex CLI

Run this in your terminal:

codex mcp add pandacrawl --url https://app.pandacrawl.app/mcp

Approve the login when prompted.

Codex Desktop

1. Open Settings -> Integrations & MCP.
2. Click Add your own.
3. Paste https://app.pandacrawl.app/mcp.
4. Approve the PandaCrawl login when prompted.

Connect with an API key

Use an API key in headless environments, CI, or clients where OAuth is inconvenient. API keys are personal: anything an agent does with your key acts as you in your workspace.

In the PandaCrawl app, open Settings -> API keys, create a key, and copy it when it appears. It won't be shown again.

For Claude Code, run:

claude mcp add --transport http --scope user pandacrawl https://app.pandacrawl.app/mcp --header "Authorization: Bearer pcrawl_YOUR_KEY"

For Cursor, add headers to the server entry in mcp.json:

{
  "mcpServers": {
    "pandacrawl": {
      "url": "https://app.pandacrawl.app/mcp",
      "headers": {
        "Authorization": "Bearer pcrawl_YOUR_KEY"
      }
    }
  }
}

For Codex CLI, put the key in an environment variable and reference it:

export PANDACRAWL_API_KEY=pcrawl_YOUR_KEY
codex mcp add pandacrawl --url https://app.pandacrawl.app/mcp --bearer-token-env-var PANDACRAWL_API_KEY

Any other client that supports custom HTTP headers can send Authorization: Bearer pcrawl_YOUR_KEY or x-api-key: pcrawl_YOUR_KEY.

Available tools

PandaCrawl MCP exposes tools for SEO research workflows:

• Research keywords with volume, difficulty, and CPC.
• Fetch live Google organic SERP results for keywords.
• Find exact keyword, page, rank, volume, CPC, intent, and traffic rows for a domain or page.
• Compare SERP competitors across a supplied keyword set.
• Search local businesses near a coordinate, filtering by rating, review count, or claimed status.
• Fetch one Maps or Local Finder SERP, and read Google Business Q&A when needed.
• Audit a Google Business Profile: categories, rating, hours, photos, and claim status.
• Collect Google reviews (including reviews from other sites) and Google Business posts.
• Look up valid Google Business category slugs.
• Check Google Maps rank at each point of a grid around a business.
• Hydrate keywords with search volume, difficulty, intent, CPC, and trends.
• List saved keywords from a PandaCrawl project.
• Save useful keywords back to PandaCrawl.
• Remove saved keywords you no longer need.
• Read rank tracker configs and latest keyword positions.
• Summarize a domain's organic footprint.
• Find keywords a domain already ranks for.
• Check backlink and referring-domain overview data.
• Read first-party Google Search Console performance (clicks, impressions, CTR, position).
• Inspect index status, crawl, and canonical for specific URLs (up to 10 per call).
• Run site audits, read their issues and pages, list past audits, and delete old ones.
• Track AI visibility: set up prompt tracking, add or remove tracked prompts, run it within an approved budget, and read how often each model names your brand, what it cites, and how that changes. See AI Visibility.
• Read Bing search performance and index health, research keywords with Bing's own search data (free), inspect a URL in Bing, and submit new pages for crawling, through Bing or IndexNow (Bing, Yandex, Seznam, Naver and Yep at once). See Bing Webmaster Tools and IndexNow.
• Connect Google Search Console or Google Analytics from a single-use link (connect_url), then choose the site or property for a project.
• Suggest a project's key pages (from Search Console, Google Analytics and the latest site audit, free) and its search competitors (sites ranking alongside it for its top searches), so you confirm a list instead of writing one.
• Read and update a project's shared context: business, goal, positioning, writing preferences, competitors, key pages, and a research log (free — it never queries a paid provider).

What to do after setup

Once PandaCrawl MCP is connected, set up PandaCrawl Agent Skills. MCP gives your agent access to PandaCrawl data. Skills are separate SKILL.md files that tell your agent how to use that data for specific SEO jobs.

Start with one focused workflow instead of asking your agent to "do SEO" broadly. SEO prompts for Claude and ChatGPT has copy-and-paste prompts for each job.

• Use SEO project setup to save your goals, positioning, competitors, and key pages to your project context, so every other skill reuses them.
• Use SEO coach if you are new to SEO or are not sure which workflow to run first.
• Use keyword research to discover keyword opportunities.
• Use competitive landscape to map a market before choosing competitors or pages.
• Use competitor analysis to study one competitor.
• Use keyword clustering to turn keywords into page groups.
• Use link prospecting to find outreach prospects for a linkable asset.

Troubleshooting

If your client cannot connect, check that the server URL is exactly https://app.pandacrawl.app/mcp.

If Codex reports Authorization server response missing required issuer: expected https://app.pandacrawl.app, upgrade Codex CLI or the Codex desktop app to 0.147.0 or later. Codex 0.143 through 0.146 drop the issuer from the OAuth callback. You can also connect with an API key instead of OAuth.

If authorization fails, disconnect the PandaCrawl server in your client, add it again, and repeat the login flow.

If your agent cannot find a project, ask it to list PandaCrawl projects first and use the returned project ID in later tool calls.