SEOBlogBot MCP server
Commit Nov 1, 2026Performs SEO audits for Next.js App Router blogs by validating sitemaps, meta tags, Core Web Vitals, and Google Search Console indexing status.
Also known as Citability/SEOBlogBot
- Stars
- 0
- Tools
- 8
- Downloads, 30 days
- —
- Latest version
- —
- Last commit
- Nov 1, 2026
- License
- MIT
What is SEOBlogBot MCP?
SEOBlogBot performs SEO audits for Next.js App Router blogs by validating sitemaps, meta tags, Core Web Vitals, and Google Search Console indexing status. It exposes 8 tools, such as audit-sitemap, check-robots-txt, validate-meta-tags.
Summary generated from the project's README
About SEOBlogBot MCP server
SEOBlogBot provides a suite of eight specialized tools designed for auditing Next.js App Router blogs directly through Claude Code or Claude Desktop. It allows developers to perform technical SEO tasks by communicating naturally with their AI assistant. The server handles the underlying HTTP requests and API interactions, making it easy to verify site structures and performance metrics without leaving the chat interface.
Users can perform various checks including sitemap validation, robots.txt verification, and meta tag inspection. For deeper analysis, the server utilizes the PageSpeed API to evaluate Core Web Vitals and run Lighthouse checklists. While many tools function without authentication, inspecting Google Search Console indexing status requires a Google Cloud service account and specific credentials. The server supports batch URL inspection for up to 20 URLs at a time. It is built to work locally via a stdio connection after being cloned and built with npm.
What you can do with it
- 1Verify sitemap and robots configurationAsk the AI to validate the accessibility and structure of your sitemap or check your robots.txt settings.
- 2Analyze page performance metricsRequest an analysis of Core Web Vitals or a Lighthouse checklist for specific mobile URLs.
- 3Inspect Google Search Console indexingCheck the indexing status of individual URLs or perform batch inspections for up to 20 links.
- 4Generate structured data suggestionsHave the assistant provide JSON-LD schema recommendations for specific pages on your site.
Written from the project's README. Every use case is checked against a quote from it.
SEOBlogBot MCP tools 8
Detected from the READMEaudit-sitemapcheck-robots-txtvalidate-meta-tagsanalyze-core-web-vitalscheck-indexing-statuscheck-indexing-status-batchgenerate-schema-recommendationaudit-lighthouse
Configuration
GOOGLE_APPLICATION_CREDENTIALSPAGESPEED_API_KEY
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 reachablecitability/seoblogbot is public and reachablegithub.com/citability/seoblogbot ↗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 2026-11-01github.com/citability/seoblogbot ↗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 model8 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 GitHubSEOBlogBot
An MCP server that brings 8 SEO audit tools directly into Claude Code and Claude Desktop. Audit sitemaps, validate meta tags, analyze Core Web Vitals, and inspect Google Search Console indexing — all from your AI assistant, without leaving your workflow.
What It Is
SEOBlogBot is a Model Context Protocol (MCP) server built for SEO auditing of Next.js App Router blogs. Install it once and call its tools naturally from any Claude session — ask Claude to audit your sitemap, check your robots.txt, or run a Lighthouse checklist, and SEOBlogBot handles the HTTP requests, parsing, and Google API calls in the background.
Tools
8 SEO tools available as MCP tools inside Claude:
| Tool | Description | Auth Required |
|---|---|---|
audit-sitemap |
Validate sitemap accessibility and structure | No |
check-robots-txt |
Verify robots.txt configuration | No |
validate-meta-tags |
Check title, description, OG, Twitter, X-Robots-Tag | No |
analyze-core-web-vitals |
LCP, INP, CLS via PageSpeed API | No |
check-indexing-status |
Google Search Console URL inspection | Yes |
check-indexing-status-batch |
Batch URL inspection (max 20) | Yes |
generate-schema-recommendation |
JSON-LD schema suggestions | No |
audit-lighthouse |
Lighthouse checklist via PageSpeed Insights | No |
Install
1. Clone and build
git clone https://github.com/ChudiNnorukam/SEOBlogBot.git
cd SEOBlogBot
npm install
npm run build
2. Add to Claude Code
Create or update ~/.mcp.json (applies to all Claude Code sessions) or .mcp.json in your project root:
{
"mcpServers": {
"seoblogbot": {
"type": "stdio",
"command": "node",
"args": ["/absolute/path/to/SEOBlogBot/dist/index.js"]
}
}
}
Replace /absolute/path/to/SEOBlogBot with the directory where you cloned the repo. Example: if you cloned to ~/Projects/SEOBlogBot, use ~/Projects/SEOBlogBot/dist/index.js.
3. Add to Claude Desktop
Open Claude Desktop, go to Settings > Developer, and add to the MCP servers config. On macOS the config file is at ~/Library/Application Support/Claude/claude_desktop_config.json:
{
"mcpServers": {
"seoblogbot": {
"type": "stdio",
"command": "node",
"args": ["/absolute/path/to/SEOBlogBot/dist/index.js"]
}
}
}
For Google Search Console tools, pass the credentials path via env:
{
"mcpServers": {
"seoblogbot": {
"type": "stdio",
"command": "node",
"args": ["/absolute/path/to/SEOBlogBot/dist/index.js"],
"env": {
"GOOGLE_APPLICATION_CREDENTIALS": "/path/to/your-service-account-key.json"
}
}
}
}
4. Restart Claude
Quit and relaunch Claude Code or Claude Desktop. The 8 SEO tools are now available in every session.
Usage
Once installed, ask Claude naturally:
Audit the sitemap at https://example.com
Check the robots.txt for https://myblog.com
Validate meta tags on https://myblog.com/my-post
Analyze Core Web Vitals for https://myblog.com (mobile)
Generate schema recommendations for https://myblog.com/about
Run Lighthouse checklist on https://myblog.com (mobile)
Google Search Console Setup
The check-indexing-status and check-indexing-status-batch tools require a Google Cloud service account with Search Console access.
Step 1: Create Google Cloud Project
- Go to Google Cloud Console
- Create a new project or select an existing one
- Enable the Search Console API
Step 2: Create Service Account
- Go to IAM & Admin > Service Accounts
- Click Create Service Account
- Name it (e.g., "seoblogbot")
- Click Create and Continue (skip optional permissions)
- Click Done
Step 3: Download JSON Key
- Click on your new service account
- Go to the Keys tab
- Click Add Key > Create new key
- Select JSON and download
Step 4: Add Service Account to Search Console
- Copy the service account email (ends with
@...iam.gserviceaccount.com) - Go to Google Search Console
- Select your property
- Go to Settings > Users and permissions
- Click Add user, paste the email, set permission to Full or Restricted
Step 5: Configure Credentials
# Option 1: environment variable
export GOOGLE_APPLICATION_CREDENTIALS=/path/to/your-service-account-key.json
# Option 2: in the MCP config (recommended for Claude Desktop)
# see the "env" block in the install section above
PageSpeed API Key (Optional)
Without a key, PageSpeed Insights allows 25,000 requests/day — usually sufficient. To raise the limit:
- Go to Google Cloud Credentials
- Click Create Credentials > API Key
- Restrict the key to PageSpeed Insights API
- Set the environment variable:
export PAGESPEED_API_KEY=your-api-key
Development
# Watch mode (auto-rebuild on changes)
npm run dev
# Type check
npm run typecheck
# Build
npm run build
API Rate Limits
| API | Limit | Notes |
|---|---|---|
| PageSpeed Insights | 25,000/day | Free, no key required |
| GSC URL Inspection | 600/day | Per property |
Troubleshooting
"Google authentication not configured"
Set the GOOGLE_APPLICATION_CREDENTIALS environment variable to your service account JSON file path.
"Access denied" on GSC Ensure the service account email is added as a user in Search Console property settings with at least Restricted permission.
"Property not found"
The siteUrl must match exactly what is in Search Console, including protocol, trailing slash, and subdomain:
https://example.com/(with trailing slash)https://www.example.com/vshttps://example.com/are different properties
License
MIT — see LICENSE
SEOBlogBot MCP questions
What tools does SEOBlogBot MCP provide?
It exposes 8 tools, including audit-sitemap, check-robots-txt, validate-meta-tags, analyze-core-web-vitals, check-indexing-status.
Do I need a Google Cloud service account for all tools?
No, only the Google Search Console tools (check-indexing-status and check-indexing-status-batch) require a service account with Search Console access.
Is a PageSpeed API key required?
It is optional. Without a key, PageSpeed Insights allows 25,000 requests per day, which is usually sufficient.
How do I fix 'Google authentication not configured' errors?
You must set the GOOGLE_APPLICATION_CREDENTIALS environment variable to the path of your service account JSON file.