Add Screpy as a custom MCP app, complete browser-based OAuth, and use project-scoped tools inside ChatGPT conversations.
SEO MCP Server for AI Assistants
Connect a compatible AI client to Screpy’s hosted Model Context Protocol server with browser-based OAuth—no local server or REST API key required. Use 44 structured tools to investigate project-scoped crawl evidence, pages, links, images, Quick Wins, Rank Tracker, stored AI Visibility, Core Web Vitals, and uptime, with explicit intent and confirmation protecting high-impact actions.
TL;DR
Too Long; Didn't Read
Show summary Hide summary
TL;DR
Too Long; Didn't Read
What Is an SEO MCP Server?
Screpy SEO MCP is a hosted remote MCP server that exposes 44 structured Screpy tools to compatible AI clients. Add https://mcp.screpy.com, complete browser-based OAuth, and the client can work only with projects available to that member. Read tools support investigation; supported write tools require clear user intent, and capacity-consuming or destructive actions require confirmation.
Connection and project access
- Add the hosted remote server URL https://mcp.screpy.com to a client that supports remote HTTP MCP servers and browser-based OAuth.
- Screpy provides setup guides for ChatGPT, Claude, Codex, Cursor, VS Code with GitHub Copilot, and Gemini CLI.
- MCP uses its own OAuth connection; a Screpy REST API key cannot be used for the MCP sign-in flow.
- Every tool call is scoped to projects owned by or shared with the authenticated member, and project access is checked again when the tool runs.
- The connection can be revoked from Connected Apps, after which the client must be authorized again before it can use Screpy tools.
Read and investigate
- Account context and plan usage show available project access and capacity before an assistant starts a larger workflow.
- Project, crawl, on-page, and comparison tools move from website-level context to one completed crawl and one exact URL.
- Page, link, and image tools support structured filters and source-page tracing so findings remain tied to crawl evidence.
- AI Visibility tools read stored overview, mention, answer, citation, prompt, and source evidence without starting a new analysis.
- Quick Wins, Core Web Vitals, and uptime tools add existing opportunity, field-performance, and availability context without mixing those sources into crawl records.
Manage supported workflows safely
- Rank Tracker tools read options, overview metrics, keywords, stored analyses, results, segments, previews, and unmatched-keyword context.
- AI Visibility tools add prompts only after explicit intent and delete a project prompt only after confirmation.
- Keyword additions, keyword deletion, and destructive segment actions require explicit user intent and the required confirmation before execution.
- Project creation, settings changes, project deletion, and starting a crawl are available only through their dedicated tools and controlled action rules.
- Available data and actions still depend on the member’s plan, remaining allowance, project state, feature access, and connected sources.
- MCP does not provide Rank Tracker exports, live SERP lookup, or manual reanalysis of an existing tracked keyword.
- MCP does not provide AI Visibility CSV or Excel exports, prompt suggestions, or manual prompt reanalysis.
Connect the hosted SEO MCP server in four steps.
Screpy keeps setup short: add one remote endpoint, authorize the correct account, and verify project access before asking for deeper analysis or an approved change.
- 01
Choose a compatible AI client
Use one of Screpy’s current setup guides or another client that supports remote HTTP MCP servers and browser-based OAuth.
- 02
Add the hosted Screpy endpoint
Enter https://mcp.screpy.com in the client. You do not need to install a local server or copy a Screpy REST API key.
- 03
Complete browser-based OAuth
Sign in with the Screpy account that can access the projects you want to investigate, then approve the connection.
- 04
Verify the project scope
Ask the client to “List my Screpy projects” before a larger workflow so you can confirm the account and available project access.
Connect the AI client you already use.
Screpy provides current setup guides for these six clients. Another client may also work when it supports remote HTTP MCP servers and browser-based OAuth, but verify its current transport and authorization support before connecting.
Bring crawl, URL, Rank Tracker, and monitoring context into Codex before planning or implementing a code-level SEO change.
Connect Screpy through Claude’s remote connector support and investigate completed crawls, exact URLs, and project health.
Authorize Screpy through OAuth in Gemini CLI and use authenticated SEO tools from a terminal-based agent workflow.
Add Screpy as a remote HTTP MCP server and keep crawl evidence beside the code that controls the affected website.
Connect Screpy through VS Code MCP support and use project data from GitHub Copilot Chat while reviewing implementation work.
Connect once, then keep every answer tied to the right Screpy account.
Add the hosted remote endpoint, complete browser-based OAuth, and verify access by listing projects. The AI client discovers structured Screpy tools without a local package, copied REST key, or manual dashboard export.
- Use https://mcp.screpy.com as the remote server URL
- Authorize the intended Screpy account in the browser
- List accessible projects before selecting a project UID
- Revoke the client later from Connected Apps when needed
Create a focused review of hosted mcp connection.
Add the hosted remote endpoint, complete browser-based OAuth, and verify access by listing projects. The AI client discovers structured Screpy tools without a local package, copied REST key, or manual dashboard export.
Move from website health to the exact crawl record behind a finding.
Start with the selected project and completed crawl, then narrow the investigation through crawl summaries, on-page metrics, structured page filters, exact URL details, and source relationships.
- List completed crawls and check whether a current crawl is ready to investigate
- Review crawl-level health indicators, issue counts, and changes between completed crawls
- Filter the page inventory, then retrieve detailed data for one exact crawl URL
- Trace link and image findings to the pages where they appear
Create a focused review of crawl investigation.
Start with the selected project and completed crawl, then narrow the investigation through crawl summaries, on-page metrics, structured page filters, exact URL details, and source relationships.
Investigate ranking movement before changing tracked keywords or segments.
Read visibility, position distribution, keyword details, stored history and results, and segment matches. Preview a grouping first; save, add, or delete only when the user explicitly asks for that exact action.
- Read overview metrics and current plan usage
- Filter keyword records and open one keyword’s stored history
- Preview segment rules and overlap before saving them
- Require explicit intent for capacity-consuming or destructive changes
Create a focused review of rank tracker workflow.
Read visibility, position distribution, keyword details, stored history and results, and segment matches. Preview a grouping first; save, add, or delete only when the user explicitly asks for that exact action.
Trace stored AI visibility from overview to source evidence.
Read visibility trends, mentions, answers, citations, prompts, and source activity. Add prompts only with explicit user intent and require confirmation before deleting one.
- Read stored overview and answer evidence
- Follow prompt, citation, domain, and page activity
- Use opaque cursors for longer result sets
- Keep exports, suggestions, and manual reanalysis outside MCP
Create a focused review of ai visibility workflow.
Read visibility trends, mentions, answers, citations, prompts, and source activity. Add prompts only with explicit user intent and require confirmation before deleting one.
Add existing opportunities, field performance, and availability to the investigation.
Quick Wins, Core Web Vitals, and uptime tools provide separate project-scoped evidence. Use them beside crawl and page findings while preserving the meaning and availability limits of each source.
- Retrieve existing Search Console Quick Wins by category and range
- Review available Core Web Vitals results separately from crawl data
- Check current uptime status and recent incidents
- Treat missing monitoring data as unavailable, not as a healthy result
Create a focused review of opportunities and health.
Quick Wins, Core Web Vitals, and uptime tools provide separate project-scoped evidence. Use them beside crawl and page findings while preserving the meaning and availability limits of each source.
44 project-scoped tools for investigation and controlled action.
The current member MCP server groups 44 tools into account, project, crawl, on-page, opportunity, health, Rank Tracker, and AI Visibility workflows. Availability still depends on account access, project state, connected data, and plan allowance.
Account context and usage
Read the authenticated member’s product access, available project count, current usage, and remaining allowance before a workflow consumes capacity.
Project discovery and overview
List accessible projects, open one project’s high-level SEO context, or compare summary metrics across two to five available projects.
Controlled project management
Create a project, update allowed settings, or delete a selected project only through the dedicated tool and the required user-intent or confirmation flow.
Crawl selection and status
List crawl runs for one project, select the exact crawl UID, and check progress or state before treating results as complete.
Controlled crawl start
Start a new crawl only for the selected project and only after explicit confirmation because the action may consume plan allowance.
Crawl summary and comparison
Read crawl totals, health indicators, issue counts, and on-page metrics, then compare two completed crawls to inspect metric changes.
Page inventory and exact URL
Filter pages within one crawl and retrieve detailed crawl data for one exact URL after the relevant record has been identified.
Links and source pages
List link records with structured filters and trace one destination back to the crawl pages that contain it.
Images and source pages
List image records from one crawl and return the pages that reference a selected image for contextual investigation.
Search Console Quick Wins
Retrieve existing project Quick Wins by supported category, reporting range, and cursor without presenting them as a full Search Console replacement.
Core Web Vitals and uptime
Read available field-performance results, current uptime status, and recent incidents as separate health signals for the selected project.
Rank Tracker setup and overview
Read supported countries, languages, devices, frequencies, segment-rule options, overview metrics, visibility, distribution, and plan usage.
Keyword inventory and detail
Filter and paginate tracked keywords, then open one keyword with up to 30 stored analyses and the results from the selected or latest analysis.
Controlled keyword changes
Add or delete up to 100 project-scoped keyword IDs per action only with explicit confirmation, including the requested device variants.
Segment list and preview
List segments with SQL-backed match counts and unmatched keywords, then preview proposed rules, overlap, average position, and example URLs without saving.
Controlled segment management
Create, update, or delete project-scoped segments only when the user explicitly asks to save or remove the exact rules.
AI Visibility evidence
Read stored overview, mention, answer, citation, prompt, source, and activity records without triggering a new analysis.
Controlled AI prompt changes
Add 1 to 20 prompts for one market only after explicit user intent, and require confirmation before soft-deleting a project prompt.
Ask bounded questions that preserve the evidence.
A strong MCP prompt names the project, source, scope, and action boundary. These examples make the requested evidence and the actions that must not run explicit.
Investigate a release regression
“List my projects, select [site], compare the two latest completed crawls, and show the metrics that changed. Do not start a new crawl.”
- Existing crawl evidence
- Comparable crawl summaries
- No capacity-consuming action
Review one exact URL
“Open the latest completed crawl for [site], find [URL], explain its page, link, and image evidence, and separate facts from hypotheses.”
- Exact URL lookup
- Source-page context
- Evidence before recommendations
Explain ranking movement
“Show visibility, falling keywords, and affected ranking URLs for [site]. Do not add, delete, or reanalyze keywords.”
- Portfolio visibility
- Stored keyword analyses
- Read-only investigation
Preview a useful segment
“Preview a Rank Tracker segment for [rules], show matches and overlap with existing segments, and do not save it.”
- Rule preview
- Matched and unmatched keywords
- No saved change
Investigate AI visibility
“Summarize stored AI Visibility for [site], then show the prompts, answers, citations, and sources behind the largest change. Do not add or delete prompts.”
- Stored answer evidence
- Prompt and source drilldowns
- Read-only investigation
Keep access and high-impact actions under user control.
MCP makes tools available to an AI client; it does not remove the need to verify the selected account, review tool calls, protect capacity, and confirm changes.
OAuth and project-scoped access
The connection uses browser-based OAuth, and every tool call checks access to the selected project instead of exposing unrelated Screpy data.
- No copied REST API key
- Member access checked per call
- Revocable from Connected Apps
Read tools for investigation
Project, crawl, page, link, image, Quick Wins, Rank Tracker, AI Visibility, Core Web Vitals, and uptime tools can collect evidence without changing project state.
- Choose an explicit project
- Use completed data when required
- Keep source limitations visible
Explicit intent for supported writes
Project, crawl, keyword, segment, and AI Visibility prompt changes use dedicated tools. The request must clearly describe the change instead of hiding it inside a broad analysis prompt.
- Clear target and action
- Dedicated management tools
- Plan and capacity checks
Confirmation for high-impact actions
Capacity-consuming or destructive actions require confirmation. The connected AI client should also let you inspect and deny tool invocations.
- Confirm before execution
- Review the tool request
- No AI Visibility export or manual reanalysis
Choose MCP, the REST API, or the dashboard for the job.
Use MCP for conversational, tool-based investigation; the REST API for deterministic product integrations; and the dashboard for direct visual review and manual control.
Connect a compatible AI client to authenticated, project-scoped Screpy tools through a hosted remote MCP server.
Build explicit application and automation flows with API credentials, documented endpoints, pagination, and rate limits.
Review projects, crawls, pages, rankings, opportunities, performance, and monitoring directly in the product interface.
Screpy documentation
Connect, authorize, and use Screpy MCP safely
Follow the MCP guides to connect a compatible AI client, complete browser-based OAuth, verify project access, write bounded prompts, and troubleshoot the connection.
Related SEO guides
Learn the concepts behind this workflow and apply them with practical SEO guidance.
What Is AI Share of Voice and How Do You Measure It?
AI share of voice measures brand visibility in AI search using consistent prompts to track mentions, citations, competitors, key trends across major models.
Read articleHow Do You Find AI Visibility Gaps?
AI visibility gaps emerge when you compare brand mentions, citations, and competitor coverage across priority prompts, AI platforms, and topic clusters.
Read articleHow Do You Compare AI Visibility Against Competitors?
AI visibility benchmarking reveals how your brand stacks up on mentions, citations, share of voice, and prompt gaps across leading AI search platforms.
Read articleHow Do You Run an AI Visibility Audit?
An AI visibility audit benchmarks brand mentions and citations across ChatGPT, Perplexity, and Google AI Overviews, then prioritizes technical and content fixes.
Read articleSEO MCP Server FAQ
Understand remote setup, OAuth access, supported clients, tool scope, confirmations, Rank Tracker limits, data privacy, revocation, and the difference between MCP and the REST API.
What is an SEO MCP server?
An SEO MCP server exposes structured SEO tools to compatible AI clients through the Model Context Protocol. Screpy SEO MCP connects an authenticated member account to project-scoped tools for website crawls, page records, links, images, Quick Wins, Rank Tracker, Core Web Vitals, uptime, and controlled project actions.
How do I connect to Screpy SEO MCP?
Choose a client that supports remote HTTP MCP servers and browser-based OAuth, add https://mcp.screpy.com, complete the Screpy sign-in and approval flow, then ask the client to list your Screpy projects. Seeing the expected projects confirms that the connection is ready.
Do I need to install a local MCP server or create an API key?
No. Screpy provides a hosted remote MCP endpoint, so supported clients can connect without running a local package. MCP uses browser-based OAuth; a Screpy REST API key is a separate credential and cannot be used for the MCP connection.
Which AI clients have Screpy setup guides?
Screpy currently documents setup for ChatGPT, Claude, Codex, Cursor, VS Code with GitHub Copilot, and Gemini CLI. Other clients may work when they support compatible remote HTTP transport and OAuth, but their connection flow should be verified against the client’s current MCP implementation.
How many tools does Screpy SEO MCP provide?
The current member MCP server registers 44 tools across account context, projects, crawls, on-page records, Quick Wins, website health, Rank Tracker, and AI Visibility. The tools available in a result still depend on the member’s access, project state, connected data, plan, and remaining allowance.
How does Screpy MCP protect project access?
The client connects through OAuth and receives only the projects owned by or shared with the authenticated member. Screpy checks project access again whenever a tool runs, so a project cannot continue to be used after that member loses access.
Are Screpy MCP tools read-only?
Most investigation tools read existing data, but the server also includes controlled actions for projects, crawls, Rank Tracker keywords, and segments. A write tool should run only when the user explicitly asks for that exact change. Capacity-consuming and destructive actions require confirmation.
Which MCP actions require confirmation?
Starting a crawl, creating or deleting a project, adding or deleting Rank Tracker keywords, and destructive segment actions use explicit intent or confirmation controls appropriate to the operation. The client should show the proposed tool call so the user can approve or deny it before execution.
Can an AI assistant investigate one exact URL?
Yes. The assistant can select a completed crawl, filter its page inventory, and request detailed crawl data for one exact URL. Separate tools can list links and images and trace a selected destination or image back to its source pages.
Can Screpy MCP compare website crawls or projects?
Yes. One tool compares summary metrics across two to five accessible projects, while another compares two selected completed crawls. Use project comparison for website-level context and crawl comparison for changes between technical SEO snapshots.
Does Screpy MCP provide full live Search Console reporting?
No. The MCP tool returns existing Search Console Quick Wins for a supported category and reporting range. It does not reproduce every Search Console dashboard or expose a separate unrestricted live reporting interface.
What can Screpy MCP do with Rank Tracker?
It can read supported options, overview metrics, visibility, position distribution, keyword lists, one keyword’s stored analyses and results, segment lists, and segment previews. It can also add or delete keywords and create, update, or delete segments when explicitly requested.
What Rank Tracker actions are not available through MCP?
MCP does not export Rank Tracker data, run a live SERP lookup, or manually reanalyze an existing tracked keyword. New keywords begin their normal first analysis, and existing keywords continue on the configured schedule. Use the REST API or dashboard when a workflow requires a capability outside the MCP tool set.
What can Screpy MCP do with AI Visibility?
It can read stored options, overview metrics, mentions, answers, citations, prompts, and source activity. It can also add prompts after explicit user intent and delete a prompt after confirmation. It does not export CSV or Excel files, suggest prompts, or manually reanalyze prompts.
Can MCP include Core Web Vitals and uptime in an investigation?
Yes. Separate tools return available Core Web Vitals results, current uptime status, and recent incidents for the selected project. If monitoring data is unavailable, the assistant should report that state rather than infer that the website is fast or available.
What happens to data returned to my AI client?
Screpy returns the project data requested by the authorized client tool call. The connected AI provider or client may process or retain that result according to its own product settings and terms. Review the client’s privacy and data-control options before connecting sensitive projects.
How do I revoke an AI client’s Screpy access?
Open Connected Apps in Screpy, find the authorized AI client, and revoke the connection. The client cannot use Screpy MCP again until it completes a new browser-based OAuth approval.
How is Screpy MCP different from the Screpy REST API?
MCP is designed for compatible AI clients to discover and call a smaller agent-focused tool set during a conversation or coding workflow. The REST API is designed for custom products, dashboards, scripts, and automations that need direct HTTP requests, API keys, pagination, and programmatic control.