mcpField
S
SERP Agent SEO

SERP Agent SEO

Remote
serp-agent.comBusiness & Marketing0Updated 14w ago

About SERP Agent SEO

SERP Agent SEO exposes SEO project management, technical audits, article generation, account status and plans to AI agents. This MCP server bridges stdio clients to SERP Agent’s remote HTTP service.

Key features

  1. 01Create and manage SEO projects
  2. 02Run technical audits and retrieve reports
  3. 03Generate and retrieve articles
  4. 04Check account status and plans

Use cases

  1. 01Audit a project’s technical SEO
  2. 02Generate SEO articles through an agent
  3. 03Review account status or available plans

MCP support

Exposes SERP Agent operations as MCP tools. The package bridges stdio MCP clients to the remote HTTP server; clients that support remote HTTP can connect directly.

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://serp-agent.com/mcp
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.

All endpoints
Streamable HTTPhttps://serp-agent.com/mcpAuth required
Packages
npmserpagent-mcp1.0.1

Tools

Details

From the project README

serpagent-mcp

SERP Agent — full-cycle SEO automation for AI agents — as an MCP server.

This package is a thin stdio bridge for MCP clients that cannot speak Streamable HTTP directly. It proxies stdio ⇄ HTTP to the remote server at https://serp-agent.com/mcp (via mcp-remote). If your client supports remote HTTP servers, connect directly instead — see serp-agent.com/docs/mcp.

Tools

create_project, list_projects, get_project, run_technical_audit, get_audit_report, generate_article, get_article, get_account_status, list_plans — a thin layer over the SERP Agent REST API. Long-running jobs (audits, articles) return a job id immediately; poll the matching get_* tool.

Auth

Set SERPAGENT_API_KEY to your sk_... key. No key yet? Free sandbox key in one call, no CAPTCHA:

curl -X POST https://serp-agent.com/v1/accounts \
  -H "content-type: application/json" \
  -d '{"email":"[email protected]"}'

Optional: SERPAGENT_MCP_URL overrides the server URL (default https://serp-agent.com/mcp).

Install

Claude Code

Prefer the direct HTTP transport:

claude mcp add --transport http serpagent https://serp-agent.com/mcp \
  --header "Authorization: Bearer sk_..."

Or via this stdio bridge:

claude mcp add serpagent --env SERPAGENT_API_KEY=sk_... -- npx -y serpagent-mcp
Cursor

~/.cursor/mcp.json (or project .cursor/mcp.json):

{
  "mcpServers": {
    "serpagent": {
      "command": "npx",
      "args": ["-y", "serpagent-mcp"],
      "env": { "SERPAGENT_API_KEY": "sk_..." }
    }
  }
}

Direct HTTP alternative: { "serpagent": { "url": "https://serp-agent.com/mcp", "headers": { "Authorization": "Bearer sk_..." } } }

VS Code (Copilot agent mode)

.vscode/mcp.json:

{
  "servers": {
    "serpagent": {
      "type": "stdio",
      "command": "npx",
      "args": ["-y", "serpagent-mcp"],
      "env": { "SERPAGENT_API_KEY": "sk_..." }
    }
  }
}

Links

License

MIT

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.