CrakSEO SEO Site Audit MCP
पेज पर और तकनीकी SEO जाँच, Lighthouse स्कोर और Core Web Vitals अनुसंधान। OAuth या स्कोप्ड API कुंजी के साथ होस्टेड Streamable HTTP। सशुल्क कॉल से पहले उपलब्धता और मूल्य जाँचें।
होस्ट किया गया MCP सर्वर
npx add-mcp 'https://crakseo.com/mcp/site-audit'Claude Code, Codex, Cursor और अन्य में इंस्टॉल होता है
दस्तावेज़
Agent Instructions
For SEO data and indexing, start with /seo-mcp/overview.md and /seo-mcp/connect.md, then read the focused server reference. The documentation search MCP at https://docs.crakseo.com/mcp searches documentation only. Product tools use https://crakseo.com/mcp/. Check tool availability and API credit balance before paid calls. Request owner approval for paid force indexing. Never invent prices, indexing guarantees or directory approval.
SEO Site Audit MCP (On-Page and Technical SEO)
SEO site audit MCP: on-page and technical SEO checks, Lighthouse and Core Web Vitals scores.
On-page and technical SEO checks for up to 5 pages (status code, on-page score, title, meta description, H1, canonical, word count, links, load time and every failed check), plus Lighthouse scores and Core Web Vitals for a page.
| Endpoint | https://crakseo.com/mcp/site-audit |
| Transport | Streamable HTTP |
| Sign-in | OAuth, or an API key as a bearer token |
| Scopes | seo-data:read |
| Billing | Pay as you go (API credits) |
When to use
Use before publishing, after a migration, when a page drops out of the index or when page speed is in question.
Questions this MCP can answer
How do I check a page for SEO issues?
Tools: SEO site audit for pages (run_seo_site_audit).
How do I compare technical SEO issues on up to five pages?
Tools: SEO site audit for pages (run_seo_site_audit).
How do I check page speed and Core Web Vitals?
Tools: Lighthouse and Core Web Vitals (get_page_speed_scores).
Connect
claude mcp add --transport http crakseo-site-audit https://crakseo.com/mcp/site-audit
Use crakseo-site-audit as the server name and https://crakseo.com/mcp/site-audit as the URL. Run /mcp in Claude Code to authenticate. For OAuth, scoped API keys and a free test, follow Connect and test.
Other clients: ChatGPT, Cursor, Codex, VS Code, Cline, Gemini CLI, Grok and Muse.
Connect using the URL above; no registry ID or marketplace listing is required.
Verify without spending
Use CrakSEO get_api_credit_balance to report my balance and dataCallsEnabled. Do not buy credits or make a paid call.
Tools
| Tool | What it does | Price per call |
|---|---|---|
run_seo_site_audit | SEO site audit for pages | TBD (placeholder) |
get_page_speed_scores | Lighthouse and Core Web Vitals | TBD (placeholder) |
get_api_credit_balance | API credit balance | Free |
[!NOTE]
Tool names, titles and parameters on this page match the server's
tools/listresponse, which stays authoritative. Example values are placeholders, not real measurements. Prices marked TBD are set at launch on API credits.
run_seo_site_audit
SEO site audit for pages. SEO site audit: on-page and technical SEO checks for up to 5 pages, with status code, on-page score, title, meta description, H1, canonical, word count, links, load time and every failed check. Costs API credits per page.
- Price per call: TBD (placeholder)
- Annotations: read-only, idempotent
- Limits: Results are cached for 24 hours. Failed calls are free.
| Parameter | Type | Required | Description |
|---|---|---|---|
urls | string[] | Yes | Up to 5 page URLs to audit. |
javascript | boolean | No | Render JavaScript before auditing (slower, costs more). Default false. |
{
"jsonrpc": "2.0",
"id": 1,
"method": "tools/call",
"params": {
"name": "run_seo_site_audit",
"arguments": {
"urls": [
"https://example.com/"
]
}
}
}
{
"result": {
"pages": [
{
"url": "https://example.com/",
"statusCode": 200,
"onpageScore": 0,
"title": "Example home page",
"description": null,
"h1": [
"Welcome"
],
"canonical": "https://example.com/",
"wordCount": 0,
"internalLinks": 0,
"externalLinks": 0,
"loadTimeMs": 0,
"failedChecks": [
"no_description"
]
}
]
},
"billing": {
"channel": "credits",
"chargedMicros": 0,
"chargedUsd": 0,
"cacheHit": false,
"balanceMicros": 0
}
}
get_page_speed_scores
Lighthouse and Core Web Vitals. Page speed and Core Web Vitals: Lighthouse performance, SEO, accessibility and best-practices scores for a page, with LCP, CLS, TBT and FCP. Costs API credits per call.
- Price per call: TBD (placeholder)
- Annotations: read-only, idempotent
- Limits: Results are cached for 24 hours. Failed calls are free.
| Parameter | Type | Required | Description |
|---|---|---|---|
url | string | Yes | Absolute public http(s) URL of the page. |
mobile | boolean | No | Test the mobile experience (true) or desktop (false). Default true. |
{
"jsonrpc": "2.0",
"id": 1,
"method": "tools/call",
"params": {
"name": "get_page_speed_scores",
"arguments": {
"url": "https://example.com/",
"mobile": true
}
}
}
{
"result": {
"url": "https://example.com/",
"scores": {
"performance": 0,
"seo": 0,
"accessibility": 0,
"bestPractices": 0
},
"vitals": {
"lcp": "0.0 s",
"cls": "0",
"tbt": "0 ms",
"fcp": "0.0 s",
"speedIndex": "0.0 s"
}
},
"billing": {
"channel": "credits",
"chargedMicros": 0,
"chargedUsd": 0,
"cacheHit": false,
"balanceMicros": 0
}
}
get_api_credit_balance
API credit balance. API credit balance: prepaid credits left for SEO data calls, amount spent, whether spending is suspended, and the per-call pricing rule. Free; no supplier call.
- Price per call: Free
- Annotations: read-only, idempotent
- Limits: Free; reads the wallet only.
| Parameter | Type | Required | Description |
|---|
{
"jsonrpc": "2.0",
"id": 1,
"method": "tools/call",
"params": {
"name": "get_api_credit_balance",
"arguments": {}
}
}
{
"availableMicros": 0,
"availableUsd": 0,
"spentMicros": 0,
"frozen": false,
"dataCallsEnabled": true,
"pricing": {
"creditMarkup": 0,
"minimumPerCallUsd": 0
},
"creditsUrl": "https://crakseo.com/app/api/credits",
"historyUrl": "https://crakseo.com/app/api/data/seo"
}
Errors
| Code | Meaning | What to do |
|---|---|---|
insufficient_credits | The API credits wallet can't cover the call's maximum price. | Add credits at https://crakseo.com/app/indexing/credits, then retry the same call. The failed call isn't charged. |
forbidden | The connection doesn't have the scope this tool needs, for example seo-data:read or console:write. | Reconnect and grant the scope named in the message, or use an API key that has it. |
not_connected | Google Search Console or Bing Webmaster Tools isn't connected, or no connected property covers the URL. | Open the connect link in the message and sign in with the account that owns the property. |
invalid_input | A parameter is missing or out of range. | Read the message, which names the field, fix the argument and retry. |
confirmation_required | A force indexing submission doesn't have the account owner's approval for this exact quote. | submit_force_indexing returns status: "needs_confirmation" with a confirmationUrl. Send the owner there to approve, then retry with the same quoteId and idempotencyKey. The agent can't approve spend. |
wallet_frozen | API credit spending is suspended on this account after a refund or dispute. | Contact support@crakseo.com. |
budget_exceeded | The account's daily API credit spending limit, or the service's daily data budget, is used up. | Retry tomorrow. |
disabled | SEO data calls aren't switched on for this deployment yet. | Use the free Search Console and URL indexing tools meanwhile. get_api_credit_balance reports dataCallsEnabled. |
supplier_unavailable | The data supplier couldn't be reached or is rate limiting. | Retry later. Failed data calls are free. |
supplier_unknown | The data supplier didn't answer in time or sent an unreadable response. | Retry later. Failed data calls are free. |
supplier_error | The data supplier refused the request or returned no data. | Check the arguments (for example the location name) and retry. Failed data calls are free. |
Technical registry details
Intended MCP Registry ID:
com.crakseo/site-audit.The namespace
com.crakseois the reverse-domain form ofcrakseo.com, used to identify the publisher. It is not a website address, product name or connection URL. You do not need it to connect.This identifier is recorded in our publishing drafts, not a claim of registry acceptance or directory approval.
This documentation is built and hosted on Mintlify, a developer documentation platform.