Pendium Developer Docs | Pendium MCP Docs | Pendium.ai
Pendium MCP Docs

Pendium Developer Docs

Connect your AI agent or custom integration to Pendium for AI visibility monitoring, content strategy, and brand intelligence.

Two ways to connect

Pendium gives you two ways to access AI visibility data, content strategy tools, and brand intelligence:

MCP Server — The recommended path for AI coding agents. Your agent discovers tools automatically and gets structured responses with context. Works with Claude Code, Cursor, Windsurf, and any MCP-compatible client.

https://pendium.ai/api/mcp/mcp

REST API — Direct HTTP access for custom integrations, scripts, and environments that don't support MCP. Same data, standard curl/fetch interface.

https://pendium.ai/api/visibility

What you can do

18 MCP tools and 9 REST API endpoints across four categories:

  • Visibility — Trigger scans, poll results, get full reports, track score history, manage action items, and look up any brand's public score.
  • Content Strategy — Access content goals and ideas, brand voice guidelines, factsheets, and content briefs.
  • Knowledge — Search a brand's knowledge base semantically and list ingested sources.
  • Configuration — Manage topics, queries, buyer personas, and view account info.

The MCP server exposes all 18 tools. The REST API covers the core scanning, reporting, and configuration endpoints.

Quick start

1. Get an API key

Sign up at pendium.ai and generate an API key from Settings → API Keys.

2. Connect your agent

Choose your agent platform and add the Pendium MCP server:

Claude Code

npx -y mcp-remote https://pendium.ai/api/mcp/mcp --header "Authorization:Bearer YOUR_API_KEY"

Cursor (add to .cursor/mcp.json)

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

Windsurf (add to ~/.codeium/windsurf/mcp_config.json)

{
  "mcpServers": {
    "pendium": {
      "serverUrl": "https://pendium.ai/api/mcp/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_API_KEY"
      }
    }
  }
}

3. Start using it

Ask your agent something like:

"Scan the AI visibility for https://example.com and tell me how AI platforms perceive the brand."

The agent will use scan_visibility to trigger a scan, then poll with get_scan_status until results are ready.

Transport

The server uses Streamable HTTP transport, the standard MCP remote transport. Each request is stateless — no session management required. The server accepts GET, POST, and DELETE requests.

Next steps

MCP Tools:

REST API:

On this page