
AgentSiteAudit MCP server
Which MCP servers are AgentSiteAudit's own, from the official registry and from asking its own domain, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.
read 2026-10-30
- Registry namecom.agentsiteaudit/agentsiteauditverified in the MCP registry
The registry name sits under agentsiteaudit.com. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.
- Stateanswerschecked 2026-10-30
- Tools3
- Server calls itselfagentsiteaudit
- Server version1.2.0
- Protocol version2025-06-18
On 2026-10-30 the server answered initialize and tools/list without a sign-in. First answer in 415 ms.
- Its tools do every use case we checked: Audit a page for security, SEO and TLS issues; Confirm which fixes landed since the previous audit.
- Checked on 3 of the 7 days it takes to judge reliability.
Once connected
- For "Audit a page for security, SEO and TLS issues", the likely first call is audit_site.
- For "Confirm which fixes landed since the previous audit", the likely first call is verify_fixes.
Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.
- INITE MCP scoreafter a weeka score needs 7 daily checks: 3 so far
- What an agent can do with it2 of 2 use cases
- Answeredmeasuring3 of the 7 daily checks it takes to print a share
- Median first answer558 ms
- Space in an agent's context≈ 418 tokensthe definitions of all its tools (3), which an agent carries on every turn
- Tool definitionsA · 100 of 100
- Typed results0 of 3 toolsdeclared outputSchema: results come typed, read once
- Every tool passes all six checks.
What an agent can do with it
- can do · Audit a page for security, SEO and TLS issues
- can do · Confirm which fixes landed since the previous audit
- not sure · Monitor pages for stylesheets and images that fail to load
Each of the product's use cases, put to Jev against this server's tool list: can an agent do it with these tools?
Worth a look
None of the five warning signs in these definitions.
A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (25%), doing the product's job (25%), definitions (20%), context (10%), use (10%) and how readily a client connects (10%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →
audit_siteAudit one public web page with 69 checks across security, SEO, TLS, performance, transport, accessibility, links, mobile, DNS and agent readiness. Returns the score, grade and the problems found, most important first, each with an exact…
verify_fixesRun a fresh audit of the same site and compare it with an earlier audit: lists what was fixed, improved, still failing, worse or new, with the score before and after. Use after making changes suggested by audit_site. Counts as one of the…
list_checksList every check AgentSiteAudit runs: its ID, category, severity and what it looks for, plus the category weights. Free and unlimited.
How to connect
Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:
{
"mcpServers": {
"agentsiteaudit": {
"type": "http",
"url": "https://agentsiteaudit.com/mcp/"
}
}
}Add it
Claude Code, in a terminal
claude mcp add --transport http agentsiteaudit https://agentsiteaudit.com/mcp/claude.ai, ChatGPT and other clients: add https://agentsiteaudit.com/mcp/ as a custom connector in the settings.
OpenAPI spec
4 paths, read 2026-10-30. Open the spec ↗
Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.
Cookies
Before we count this visit
Analytics and ad measurement tell us which pages and which of our ads do their job: Google Analytics and Google Ads, the Meta pixel, Yandex Metrica, and one first-party id of our own. Nothing is stored until you answer, and declining changes nothing about the site.