The Service Marketing Guys Audit MCP server
com.theservicemarketingguys/audittheservicemarketingguys.comstreamable-httpv0.1.0Scanned
Read-only audit of any local service business, Open Service Profile conformance first.
7 tools: 5 change things and 2 only read.
- Reads private data · 0
- Reads text others write · 7
- Can send data out · 4
- 4 findings
Tools listed without sign-in. Remote posture
With Anlyon
5 tools here change things. Govern them.
- Anlyon lists the tools and adopts none.
- Each tool you adopt gets approvals and receipts.
- Your agent never holds the key.
A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.
What the The Service Marketing Guys Audit MCP server can do
The The Service Marketing Guys Audit MCP server is published by theservicemarketingguys.com, a domain the MCP Registry verified. It has 7 tools. It can create or change data (5 tools: check_agent_readiness, check_site_speed, check_ai_visibility, check_local_rank and 1 more), but cannot delete data. 2 tools only read.
7 tools bring in text other people can write (check_agent_readiness, check_site_speed, check_ai_visibility and 4 more); 4 tools can send data out of your system (check_agent_readiness, check_site_speed, check_ai_visibility and 1 more).
The fixed checks matched 4 findings (annotation-conflict). Each one comes with the text it matched.
Its remote endpoint lists its tools without sign-in.
Last scanned Nov 11, 2026, version 0.1.0.
Tools
Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.
7 tools
Changes things 5Claude Code: ask
check_agent_readinessCheck whether a local service business is legible to AI agents.Reads text others writeCan send data outNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Description, as the server wrote it Check whether a local service business is legible to AI agents. Headline: Open Service Profile conformance (manifest at https://<host>/.well-known/open-service-profile validated against the spec, level claimed versus automated Level 1 checks, LocalBusiness and ScheduleAction JSON-LD on the home page). Secondary: the isitagentready.com signal, which degrades to unavailable when that service is down. Synchronous. Returns the final result, usually within about 30 seconds. Reuses a check from the last hour.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
check_ai_visibilityStart an AI visibility check: does the business appear when AI assistants are asked for local providers in its city?Reads text others writeCan send data out1 finding
Why it is in this group
- The description's first verb is "start": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Findings
- Warn
The server marks "check_ai_visibility" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The description's first verb is "start": a word for a change.
Description, as the server wrote it Start an AI visibility check: does the business appear when AI assistants are asked for local providers in its city? It uses up to five prompts to the configured OpenAI model. Paid, drawn from a shared daily budget; when the budget is used up the result says quota_reached with the UTC reset time. For a running result, wait pollAfterSeconds, then call get_audit_report with runId. Repeat while status is running. Cached completed results need no polling.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
check_local_rankStart a Google Maps rank grid (49 points, 8 miles) for a business by Google Place id, or by business name and city.Reads text others write1 finding
Why it is in this group
- The description's first verb is "start": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Findings
- Warn
The server marks "check_local_rank" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The description's first verb is "start": a word for a change.
Description, as the server wrote it Start a Google Maps rank grid (49 points, 8 miles) for a business by Google Place id, or by business name and city. Paid, drawn from a shared daily budget; when the budget is used up the result says quota_reached with the UTC reset time. For a running result, wait pollAfterSeconds, then call get_audit_report with runId. Repeat while status is running. Cached completed results need no polling.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
check_site_speedStart a Google PageSpeed run (mobile and desktop) for a website.Reads text others writeCan send data out1 finding
Why it is in this group
- The description's first verb is "start": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Findings
- Warn
The server marks "check_site_speed" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The description's first verb is "start": a word for a change.
Description, as the server wrote it Start a Google PageSpeed run (mobile and desktop) for a website. Free. For a running result, wait pollAfterSeconds, then call get_audit_report with runId. Repeat while status is running. Cached completed results need no polling.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
start_auditStart the full visibility audit: site speed, agent readiness, and Open Service Profile conformance, plus the paid engines when their inputs are given.Reads text others writeCan send data out1 finding
Why it is in this group
- The name "start_audit" says "start": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Findings
- Warn
The server marks "start_audit" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The name "start_audit" says "start": a word for a change.
Description, as the server wrote it Start the full visibility audit: site speed, agent readiness, and Open Service Profile conformance, plus the paid engines when their inputs are given. city enables AI visibility. placeId enables local rank. Provide businessName and state for accurate identification. If the paid budget cannot cover this request, nothing starts; use the individual free tools. For a running result, wait pollAfterSeconds, then call get_audit_report with runId. Repeat while status is running. Cached completed results need no polling.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
Only reads 2Show 2 read-only tools
explain_checkPlain-language explanation of one check id: what it looks at, why it matters to a service business, and what to do.Reads text others writeNo findings
Why it is in this group
- The name "explain_check" says "explain": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Plain-language explanation of one check id: what it looks at, why it matters to a service business, and what to do. Explains osp-1 through osp-20 and agent-readiness check ids. Other engines' finding ids are not supported.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
get_audit_reportFetch the status and, when finished, the report for a runId returned by check_site_speed, check_ai_visibility, check_local_rank, or start_audit.Reads text others writeNo findings
Why it is in this group
- The name "get_audit_report" says "get": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Fetch the status and, when finished, the report for a runId returned by check_site_speed, check_ai_visibility, check_local_rank, or start_audit. For a running result, wait pollAfterSeconds, then call again with the same runId. Repeat while status is running.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.
Exfil surface
Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.
No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data.
- Reads private data0
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write7
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out4
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.
Remote posture
What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.
Looked at Nov 20, 2026, 18:48 UTC, unchanged since Oct 22, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- yes
- HTTP status of an anonymous initialize
- 200
- tools/list served without credentials
- yes
- Tools that change things, listed without credentials
- 5
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- https://www.theservicemarketingguys.com/.well-known/oauth-protected-resource
- Authorization servers
- https://wondrous-dress-64-staging.authkit.app
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- yes
- Client ID metadata documents
- no
- WarnThe whole server
The endpoint served tools/list without credentials, and the list has 5 tools that change things (5 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://www.theservicemarketingguys.com/api/audit-mcp: tools/list returned 7 tools to an anonymous client, including check_agent_readiness (write), check_site_speed (write), check_ai_visibility (write), check_local_rank (write), start_audit (write)
Findings
Matches of fixed checks, with the text they matched.
- Warncheck_site_speed
The server marks "check_site_speed" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The description's first verb is "start": a word for a change.
The server marks "check_ai_visibility" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The description's first verb is "start": a word for a change.
- Warncheck_local_rank
The server marks "check_local_rank" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The description's first verb is "start": a word for a change.
- Warnstart_audit
The server marks "start_audit" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The name "start_audit" says "start": a word for a change.
History
Changes to its tool definitions and to its remote endpoint, newest first.
No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.
Install
Pinned to version 0.1.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http audit https://www.theservicemarketingguys.com/api/audit-mcpclaude mcp add --transport http audit https://www.theservicemarketingguys.com/api/audit-mcpRun in a terminal.
Claude Code permissions
Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.
{
"permissions": {
"allow": [
"mcp__audit__get_audit_report",
"mcp__audit__explain_check"
],
"ask": [
"mcp__audit__check_agent_readiness",
"mcp__audit__check_site_speed",
"mcp__audit__check_ai_visibility",
"mcp__audit__check_local_rank",
"mcp__audit__start_audit"
],
"deny": []
}
}Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as audit. Review it before you use it.
Capability tags behind 7 rules
- mcp__audit__check_agent_readiness untrusted-input, outbound
- mcp__audit__check_site_speed untrusted-input, outbound
- mcp__audit__check_ai_visibility untrusted-input, outbound
- mcp__audit__check_local_rank untrusted-input
- mcp__audit__start_audit untrusted-input, outbound
- mcp__audit__get_audit_report untrusted-input
- mcp__audit__explain_check untrusted-input
Pin
Keep the decision: fail CI when the tools change, follow every change, or show a badge.
Pin in CI
Fail a build when the tools you reviewed are not the tools the server serves today.
curl -s "https://radar.anlyon.com/api/v1/servers/com.theservicemarketingguys/audit/verify?hash=307dc7328090a8cbedecc9aca8946a03859a42c5617fa5d93a3c4f79ea45a99c" | jq -e '.changed == false'Pinned hash 307dc7328090, from Nov 11, 2026, 03:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/com.theservicemarketingguys/audit/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/com.theservicemarketingguys/audit)Source: MCP Registry · repository. Synced Oct 21, 2026, 18:06 UTC.
The Service Marketing Guys Audit MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the The Service Marketing Guys Audit MCP server safe?
- No scan can promise that. What its definitions show: 7 tools, 5 of which can change, send or delete something, and 4 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the The Service Marketing Guys Audit MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the The Service Marketing Guys Audit MCP server do things that cannot be undone?
- No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.
What tools does the The Service Marketing Guys Audit MCP server have?
- 7 tools: 5 write, 2 read. check_agent_readiness, check_site_speed, check_ai_visibility, check_local_rank, start_audit, get_audit_report and explain_check.
Does the The Service Marketing Guys Audit MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the The Service Marketing Guys Audit MCP server send data to outside services?
- 4 tools can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): check_agent_readiness, check_site_speed, check_ai_visibility and start_audit.
Has the The Service Marketing Guys Audit MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 11, 2026.