About AgentSEO
AgentSEO provides client integrations for an SEO intelligence API used by AI agents and developer workflows. This repository includes JavaScript and Python SDKs and an MCP server, but not the hosted API or its backend systems.
Key features
- 01JavaScript/TypeScript SDK
- 02Python SDK
- 03MCP server integration
Use cases
- 01Call SEO search from JavaScript projects
- 02Query SEO data in Python workflows
- 03Expose SEO capabilities to agents through MCP
MCP support
The repository includes an MCP server that lets clients access the AgentSEO API.
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://www.agentseo.dev/mcpclaude mcp add --transport http dev-agentseo-www-agentseo https://www.agentseo.dev/mcp{"mcpServers":{"dev-agentseo-www-agentseo":{"type":"http","url":"https://www.agentseo.dev/mcp"}}}Open in Cursor{"servers":{"dev-agentseo-www-agentseo":{"type":"http","url":"https://www.agentseo.dev/mcp"}}}Open in VS Code{"mcpServers":{"dev-agentseo-www-agentseo":{"type":"http","url":"https://www.agentseo.dev/mcp"}}}{"mcpServers":{"dev-agentseo-www-agentseo":{"serverUrl":"https://www.agentseo.dev/mcp"}}}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.
https://www.agentseo.dev/mcpAuth requiredTools
45| Parameter | Type | Required | Description |
|---|---|---|---|
| sync | boolean | No | |
| limit | integer | No | |
| query | string | Yes | The search query |
| exclude_domains | array | No | |
| include_domains | array | No |
Details
From the project READMEAgentSEO Clients
Official open-source clients for AgentSEO, the SEO intelligence API for AI agents and developer workflows.
This repository contains the integration layer only:
packages/js-sdk- JavaScript/TypeScript SDKpackages/python-sdk- Python SDKpackages/mcp-server- Model Context Protocol server
The hosted AgentSEO API, worker system, provider orchestration, billing, and transformation logic are not part of this repository.
Quick Start
Use the JavaScript SDK:
npm install @agentseo/sdk
import { AgentSEO } from "@agentseo/sdk";
const client = new AgentSEO({
apiKey: process.env.AGENTSEO_API_KEY!,
});
const result = await client.search(
{ query: "seo api", location: "United States", limit: 5 },
{ sync: true },
);
console.log(result);
Use the Python SDK:
pip install agentseo-sdk
from agentseo_sdk import AgentSEOClient
client = AgentSEOClient(api_key="sk_live_...")
result = client.search(query="seo api", sync=True)
print(result)
Use the MCP server:
export AGENTSEO_API_KEY="sk_live_your_key"
npx -y @agentseo/mcp-server
Development
Build the JavaScript SDK:
cd packages/js-sdk
npm install
npm run build
Build the MCP server:
cd packages/mcp-server
npm install
npm run build
Install the Python SDK locally:
cd packages/python-sdk
python -m pip install -e .
Security
Do not commit API keys, .env files, customer payloads, or provider credentials. See SECURITY.md.
License
MIT. See package-level LICENSE files.
Comments
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.