Docs

MCP server

Call the gate from Claude, Cursor, and other MCP clients.

01 · Draft

Human or LLM

Paste, PR, webhook, or CLI. The gate does not care who wrote it.

MCP server

Dokeo ships an MCP server (Model Context Protocol) so Claude Desktop, Cursor, and any MCP client can score + fix content without leaving the chat.

Exposed tools

scan_content

Score inline content against 8 core + type-specific checks across SEO, AEO, and GEO, with market benchmarks.

scan_url

Fetch + score a URL. SSRF-guarded.

batch_scan

Scan every post on a blog.

suggest_fixes

Return the fix guidance for each failed check. One-click AI rewrites are available on Growth+ plans.

list_content_types

Return the 17 supported content types.

stats

Per-check pass/flag/fail counts for the audit log.

search_kb

Search the content-knowledge base (case studies, examples).

HTTP transport (cloud clients)

For Claude.ai web, Cursor cloud, and other clients that don't speak stdio, Dokeo exposes JSON-RPC 2.0 over HTTP:

curl -X POST https://dokeo-api.fly.dev/api/v1/mcp/jsonrpc   -H "Authorization: Bearer YOUR_API_KEY"   -H "Content-Type: application/json"   -d '{
    "jsonrpc": "2.0",
    "id": 1,
    "method": "tools/call",
    "params": {
      "name": "scan_content",
      "arguments": {
        "content": "your draft goes here",
        "content_type": "blog_post"
      }
    }
  }'

Discover available tools with GET /api/v1/mcp/info (no auth).

Tools exposed

scan_content

Score inline content against 8 core + type-specific checks across SEO, AEO, and GEO, with market benchmarks.

scan_url

Fetch + score a URL. SSRF-guarded.

batch_scan

Scan every post on a blog.

suggest_fixes

Return the fix guidance for each failed check. One-click AI rewrites are available on Growth+ plans.

list_content_types

Return the 17 supported content types.

stats

Per-check pass/flag/fail counts for the audit log.

search_kb

Search the content-knowledge base (case studies, examples).

Setup with Claude Desktop

Edit ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or the equivalent on your OS and add:

json
{
  "mcpServers": {
    "dokeo": {
      "command": "uvx",
      "args": ["--from", "dokeo", "dokeo-mcp-server"],
      "env": {
        "DOKEO_API_KEY": "dk_your_tenant_key",
        "DOKEO_API_URL": "https://dokeo-api.fly.dev"
      }
    }
  }
}

Restart Claude Desktop. The dokeo tools appear in the chat under "Tools".

Setup with Cursor

Edit ~/.cursor/mcp.json:

json
{
  "mcpServers": {
    "dokeo": {
      "command": "uvx",
      "args": ["--from", "dokeo", "dokeo-mcp-server"],
      "env": {
        "DOKEO_API_KEY": "dk_your_tenant_key",
        "DOKEO_API_URL": "https://dokeo-api.fly.dev"
      }
    }
  }
}

Use it

# From Claude Desktop or Cursor, just ask:
"Score my latest draft for SEO + AEO + GEO"

# Claude will call the MCP tool automatically and show you:
# - VERDICT (BLOCKER / FAIL / WARNING / OPTIMIZATION / PASS)
# - score per check
# - the offending sentences (inline_issues)
# - concrete fix suggestions
#
# Claude can then auto-rewrite the draft and re-score until it passes.