geomcp MCP server
Commit Oct 23, 2026Performs technical SEO and generative engine optimization audits by inspecting HTML, structured data, sitemaps, and crawler policies.
Also known as WebDecoy/geomcp
- Stars
- 1
- Tools
- 5
- Downloads, 30 days
- —
- Latest version
- —
- Last commit
- Oct 23, 2026
- License
- MIT
What is geomcp MCP?
geomcp performs technical SEO and generative engine optimization audits by inspecting HTML, structured data, sitemaps, and crawler policies. It exposes 5 tools, such as audit_url, audit_html, inspect_robots.
Summary generated from the project's README
About geomcp MCP server
Performing technical SEO and generative engine optimization audits from within an AI assistant is what geomcp enables for developers and webmasters. By connecting this MCP server to clients like Claude Desktop, Cursor, or VS Code, you can inspect HTML, structured data, sitemaps, and crawler policies through a conversational interface. The server runs locally on your machine using Node.js 22 or newer and requires no external accounts, API keys, or paid LLM dependencies.
Users can choose between auditing live public URLs or analyzing provided HTML offline to avoid network requests. The system provides evidence-backed findings, including stable check IDs and concrete recommendations for improvements. It includes specialized tools such as audit_url, audit_html, inspect_robots, inspect_sitemap, and compare_audits to facilitate a complete workflow from initial discovery to verifying fixes. This approach allows for comparing reports to see exactly what improved or regressed after code changes.
What you can do with it
- 1Audit live web pagesRequest a technical SEO and GEO audit for a specific public URL to identify prioritized fixes.
- 2Analyze HTML before deploymentInspect generated HTML code offline to find issues before the page is actually published to the internet.
- 3Verify crawler policiesCheck how different AI and search bots are handled by inspecting the robots.txt file.
- 4Compare audit resultsEvaluate the impact of recent changes by comparing two different audit reports.
Written from the project's README. Every use case is checked against a quote from it.
geomcp MCP tools 5
Detected from the READMEaudit_urlaudit_htmlinspect_robotsinspect_sitemapcompare_audits
Automated checks
Ran Nov 14, 2026Full report →Not verified yet. A server needs a score of 80, no serious finding, and enough data for us to check. How checks work · What to fix for more points
- Source repository linked and reachablewebdecoy/geomcp is public and reachablegithub.com/webdecoy/geomcp ↗Pass
- Package names this repository as its sourceNot checked
- Build provenance (Sigstore attestation)Not checked
- Open source license (OSI)MITspdx.org/licenses/MIT.html ↗Pass
- Commit or release in the last yearLast commit or release 2026-10-23github.com/webdecoy/geomcp ↗Pass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNot checked
- No critical advisory in the package or its dependenciesNot checked
- No hidden instructions to the model5 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledNo tool named like delete, drop or execPass
- Remote endpoint answers the MCP handshakeNot checked
README
View on GitHubGEOMCP is an open-source Model Context Protocol server for technical SEO and generative engine optimization (GEO). Connect it to an MCP-capable assistant to inspect HTML, structured data, crawler policies and sitemap documents without leaving your development workflow.
Every page finding includes a stable check ID, observed evidence and a concrete recommendation. Audit reports work as structured JSON, so your assistant can turn findings into code changes and compare the result.
See it before installing: Watch the recorded audit-to-traffic workflow · Walkthrough and installation options · Run GEOMCP
The recording pairs a GEOMCP audit with WebDecoy’s own-site traffic dashboard. GEOMCP audits crawlability and page evidence; observing AI crawler visits and referral traffic requires a separate WebDecoy integration. A crawler visit does not establish an AI citation or a referred visitor.
- Evidence you can inspect. Findings point to observed metadata, elements, counts and response details.
- Works on your machine. No GEOMCP account, API key, telemetry or paid LLM dependency.
- Useful before launch. Audit supplied HTML without making network requests.
- Search and training stay distinct. Inspect declared crawler policies without treating training opt-outs as SEO failures.
- Designed for a second pass. Compare checks after changes; unknowns remain coverage changes.
Get started
Requires Node.js 22+. Run the versioned GitHub release directly:
npx --yes --package=https://github.com/WebDecoy/geomcp/releases/download/v0.1.1/webdecoy-geomcp-0.1.1.tgz geomcp
This downloads the built release; cloning and compiling are optional. For development, use:
git clone https://github.com/WebDecoy/geomcp.git
cd geomcp
npm ci
npm run build
node dist/cli.js --help
Use the absolute path to dist/cli.js in your MCP client. The server communicates over stdio and waits for an MCP client when started without arguments.
Claude Desktop or Cursor
Add this entry to your client's MCP configuration (claude_desktop_config.json for Claude Desktop; .cursor/mcp.json for a Cursor project). Replace the example path with your actual clone location, then restart or enable the server.
{
"mcpServers": {
"geomcp": {
"command": "node",
"args": ["/absolute/path/to/geomcp/dist/cli.js"]
}
}
}
If your desktop app cannot find Node, use the absolute path returned by which node (macOS/Linux) or where node (Windows) as command.
VS Code
In .vscode/mcp.json:
{
"servers": {
"geomcp": {
"type": "stdio",
"command": "node",
"args": ["/absolute/path/to/geomcp/dist/cli.js"]
}
}
}
Start with a question
Audit https://your-site.com/guide for technical GEO issues. Show the evidence for the three most useful fixes, inspect its robots policy, and propose specific changes.
Audit this generated HTML before I deploy it. Keep unavailable HTTP checks separate from failures.
Compare these two GEOMCP reports. What improved, what regressed, and what could we not evaluate?
The included improve-page prompt guides the audit → fix plan → verification workflow. geomcp://methodology exposes scoring guidance directly to clients that support MCP resources.
Five tools, one workflow
| Tool | Input | Result |
|---|---|---|
audit_url |
url |
Fetch one public HTML page; return scored checks, evidence, coverage and up to eight prioritized fixes. |
audit_html |
html, url |
Analyze supplied HTML offline. The URL resolves relative links; no request is made. |
inspect_robots |
url |
Fetch the origin's /robots.txt; evaluate declared policies for the exact page path. |
inspect_sitemap |
url |
Inspect one XML sitemap or sitemap index for syntax, locations, dates and duplicates. |
compare_audits |
before, after |
Compare check statuses from two reports using the same rules version. |
audit_url, inspect_robots and inspect_sitemap make public GET requests. The other tools run offline. All tools are read-only: they do not edit your files or deploy changes.
What it checks
26 page checks across seven categories. Rules are readable in src/audit.ts; the complete check IDs and weights are in docs/checks.md.
| Category | Signals inspected |
|---|---|
| Discovery | Title, page description, canonical URL, index directives, Open Graph metadata |
| Structure | Document language, primary heading, heading order, main landmark, extractable HTML text |
| Semantics | JSON-LD syntax, entity types and contexts, publisher identity metadata |
| Media & interaction | Image alt attributes, table headers, form labels |
| Links | Internal links, descriptive labels, HTML navigation destinations |
| Evidence signals | Author attribution, machine-readable dates, supporting source links |
| Delivery | HTTP status, HTML Content-Type, HTTPS URL, responsive viewport |
Robots inspection reports policies for Googlebot, Bingbot, OAI-SearchBot, ChatGPT-User, Claude-SearchBot, Claude-User, PerplexityBot, GPTBot and ClaudeBot. These are declared policies, not live requests made under those identities.
An actual report
examples/audit.json is generated from the included examples/page.html fixture. It is a reproducible example, not a customer result.
{
"id": "canonical-url",
"category": "discovery",
"status": "warn",
"weight": 2,
"title": "Canonical URL",
"evidence": "0 canonical elements; resolved URL: none",
"recommendation": "Use one HTTP(S) canonical URL for the preferred version of this page."
}
You can also use the audit engine directly after building:
import { auditHTML } from './dist/index.js';
const report = auditHTML(html, 'https://example.com/guide');
console.log(report.priorities);
Understand the score
The score is a transparent technical checklist, with rules version 0.1.0:
pass = 1 warn = 0.5 fail = 0
score = round(100 × Σ(weight × value) / Σ(evaluated weights))
unknown checks are excluded
Core checks receive weights of 2 or 3; supporting checks receive 1. Reports include coverage and category scores so a high score with sparse evidence remains visible. Compare similar page types, coverage and the same rules version.
A checklist score does not predict AI citations, rankings, factual accuracy or signups. A public product page, private dashboard and editorial article have different needs. Intentional noindex, absent bylines and missing editorial dates can all be appropriate. No recommendation requires invented content, credentials, claims or reviews.
Network behavior & privacy
- Runs locally. No telemetry, vendor API or account system. Reports are returned to the MCP client; your assistant provider's own data policies still apply.
- Public fetches identify as
GEOMCP/0.1.1 (+https://github.com/WebDecoy/geomcp). It does not impersonate AI vendors. - HTTP(S) only, ports 80/443, a 15-second total fetch deadline, four redirects maximum and a 2 MiB response limit. The same size limit applies to offline HTML input.
- Private, loopback, link-local and reserved IP ranges are blocked. DNS answers are checked and pinned to each connection; redirects are revalidated. HTTPS downgrades are blocked.
- No cookies, authentication headers, form submissions, JavaScript execution or browser automation. Requests ask for uncompressed content; unexpectedly compressed responses are rejected.
audit_urlfetches one page and does not enforce robots.txt policy automatically. Use it on pages you are authorized to inspect; useinspect_robotswhen reviewing declared crawler preferences.- Page content is untrusted data. MCP tool descriptions and server instructions tell assistants to treat it as evidence, never as instructions.
The tool does not measure Core Web Vitals, computed visibility, rendered accessibility, actual crawler identity or index inclusion. Sitemaps and outbound links are inspected without following their destinations. Supporting links are evidence signals, not fact checking.
Development
npm ci
npm run build
npm test
npm run check
npm run artwork
Tests cover audit behavior, scoring, crawler rules, XML parsing, SSRF protections and a real MCP client/server stdio exchange. GitHub Actions runs the build and tests on Node.js 22 and 24. Artwork is generated from the editable SVG designs in scripts/artwork.mjs.
A live validation of all 193 WebDecoy sitemap pages exercised all five tools through a real SDK client and stdio server. It also checked a controlled missing-title/missing-H1 fixture, blocked a metadata IP, and verified the methodology resource and prompt. Reproduce the initial 12-page validation with npm run validate:site -- /tmp/geomcp-validation. The recorded scores describe checklist results, not search visibility.
See CONTRIBUTING.md for adding checks and SECURITY.md for private vulnerability reports.
Find the installation guide, interactive demo and audit case study.
Built by WebDecoy
WebDecoy builds bot detection for websites, applications, WordPress and Shopify. GEOMCP helps developers inspect discoverability; WebDecoy helps them understand the traffic that arrives.
If GEOMCP helps you ship a better page, give it a star or share a reproducible issue. Contributions and thoughtful new checks are welcome.
MIT licensed. Made for people who want to see the work behind the score.
geomcp MCP questions
What tools does geomcp MCP provide?
It exposes 5 tools, including audit_url, audit_html, inspect_robots, inspect_sitemap, compare_audits.
Does GEOMCP require an account or API key?
No, it works locally on your machine without any GEOMCP account, API key, telemetry, or paid LLM dependency.
Can I audit HTML without making network requests?
Yes, you can use the audit_html tool to analyze supplied HTML offline, which is useful for auditing before deployment.
What kind of crawler policies does it inspect?
It reports policies for various bots including Googlebot, Bingbot, OAI-SearchBot, ChatGPT-User, Claude-SearchBot, Claude-User, PerplexityBot, GPTBot and ClaudeBot.