SEO Researcher
Allows AI agents to perform live search research by querying Google, surfacing competitors, topics, entities, search questions, AI citations, content gaps, and source URLs for a given subject.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@SEO ResearcherResearch "best CRM software" before we create this article."
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
SEO Researcher
SEO Researcher gives Claude, Codex, Cursor, and other agents the live search research they are missing before they write: Google competitors, topics, entities, search questions, AI citations, content gaps, and source URLs.
The public website, REST façade, and remote MCP server run on Cloudflare. Research jobs use the existing Rankability research infrastructure behind a narrow, versioned adapter. This repository contains no SERP-provider runtime and no Rankability secrets.
Connect an agent
The help center includes platform-specific connection guides, content workflows, troubleshooting, and five downloadable starter skills.
Use the Streamable HTTP MCP endpoint:
https://mcp.seoresearcher.ai/mcpThe first connection opens OAuth. After authorization, ask your agent:
Check which SEO Researcher account is connected and list my existing jobs. Do not start research.The focused tool surface is:
seo_research_connection— connected organization, workspace, permissions, and metering modelseo_research_startseo_research_statusseo_research_getseo_research_list
Related MCP server: Web Search MCP Server
REST API
The REST façade is available at https://api.seoresearcher.ai/v1. Send the same OAuth access token or Rankability API key as a bearer token. See docs/API.md and openapi.yaml.
Local development
npm install
npm run dev
npm run dev:workerCopy .env.example to .dev.vars for local Worker secrets. Never commit .dev.vars.
Validation and deployment
npm run validate
npm run deployCloudflare serves the same Worker at seoresearcher.ai, api.seoresearcher.ai, and mcp.seoresearcher.ai. The Worker separates each host's surface, records edge analytics, and proxies only the dedicated SEO Researcher contract.
The free-sample CTA hands customers to https://app.seoresearcher.ai/start. That
branded host uses Rankability's existing account, billing, and research
infrastructure without exposing the generic Rankability pricing funnel.
Security
See SECURITY.md. OAuth is preferred. Raw access tokens are never written to analytics or logs.
License
The public integration and deployment shell is available under the MIT License. Rankability's private research engine is not part of this repository.
Read-only MCP acceptance
See the acceptance runbook. npm run test:mcp exercises the real MCP transport with mocked upstream responses, including 25 concurrent account-isolation checks. npm run acceptance:read-only runs bounded public checks; set SEO_RESEARCHER_ACCESS_TOKEN through your secret manager to also verify authenticated reads. Neither command starts research. Deploy the Rankability read-only connection repair before the companion gateway release.
This server cannot be deployed
Maintenance
Related MCP Connectors
Agent-native search engine with live web research optimized for AI agents.
- VibeSEOOAuthdev.vibeseo
SEO research, audits, backlinks, GSC, and content workflow tools for AI agents.
- MotiBlogOAuthai.motiblog
Agent-first SEO research and publishing: competitors, SERPs, internal links, and Search Console.
SEO data for AI agents: Google SERP, keyword research, backlinks, site audits, AI answer visibility.
Related MCP Servers
- AlicenseAqualityAmaintenanceEvidence-backed web research for AI agents. Real-time search with cited claims, confidence scores, and compare mode showing raw LLM hallucination vs evidence-backed answers.520Apache 2.0
- FlicenseNot gradedqualityCmaintenanceEnables AI agents to perform web searches, extract webpage content, and conduct end-to-end search-and-extract operations using multiple search providers and content extraction methods.-
- AlicenseAqualityAmaintenanceProvides AI agents live web access through scraping, multi-engine search, site mapping, crawling, SEO audits, and 31 data collectors via natural language tool calls.936 npmMIT
- AlicenseNot gradedqualityAmaintenanceEnables AI agents to perform live web searches across 9 engines, scrape web pages into clean formats, and run agentic research with citations via MCP.222 PyPI2MIT