Mark

List Sites

list_sites

Read-onlyIdempotent

Lists your websites with the primary site, agent-readiness score, latest audit summary, the lead-capture config save_site writes (capture), snippet (the exact pasteable snippet the Websites page shows, or null), snippetUnavailable (top level: why snippets are withheld, in the Websites page's words, or null once the PostHog reverse proxy is live), snippetNeedsRepaste: true when the snippet on the site's live pages no longer matches its settings, such as different Consent Mode defaults or a Tag Manager container or Cookiebot id that was removed, aiAssistantFile (the exact AI assistant tracking file the Websites page shows for that site, or null), and aiAssistantFileUnavailable (top level: why there is no file, in the Websites page's words, or null when the workspace has its own PostHog project). When snippetNeedsRepaste is true, give the operator that site's snippet to paste in place of the old one on every page; if snippet is null, send them to sitesUrl. aiAssistantFile is a Next.js 16+ proxy.ts that records AI assistant fetches in the workspace's PostHog project; its header comment says where to save it, or how to merge it into an existing proxy.ts. After the operator deploys it, check_ai_assistant_tracking confirms the install. Does not change anything. Related: get_site_audit, check_site_readiness, check_ai_assistant_tracking, save_site.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "list_sites"
  }
}

Input Schema

Name	Required	Description	Default
No arguments

Output Schema

Name	Required	Description	Default
`sites`	Yes
`appUrl`	Yes
`snippetUnavailable`	Yes
`aiAssistantFileUnavailable`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedNov 5, 2026

addedOutput schema / properties / aiAssistantFileUnavailable

Added value: +{
+  "type": [
+    "string",
+    "null"
+  ]
+}

changedOutput schema / required

Previous value: -[
-  "appUrl",
-  "sites",
-  "snippetUnavailable"
-]New value: +[
+  "appUrl",
+  "sites",
+  "snippetUnavailable",
+  "aiAssistantFileUnavailable"
+]

Changed2 schema fields changedNov 3, 2026

addedOutput schema / properties / snippetUnavailable

Added value: +{
+  "type": [
+    "string",
+    "null"
+  ]
+}

changedOutput schema / required

Previous value: -[
-  "appUrl",
-  "sites"
-]New value: +[
+  "appUrl",
+  "sites",
+  "snippetUnavailable"
+]

First observedOct 1, 2026

TDQS

A3.6/5.0

Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The annotations already declare readOnlyHint, idempotentHint and destructiveHint, so "Does not change anything" is redundant. The description does add genuine behavioral nuance the annotations cannot carry — null semantics for snippet/snippetUnavailable and the meaning of snippetNeedsRepaste — but the bulk of its text describes return values that the existing output schema already encodes.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness2/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The body is one enormous sentence with deeply nested parentheticals defining each returned field, which is hard to parse and front-loads the purpose only briefly. Because an output schema already exists, much of this field-by-field enumeration does not earn its place in the description.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With zero parameters, full annotation coverage and an output schema, the description more than covers what an agent needs to invoke the tool correctly, including remediation steps for the two "NeedsRepaste"/null cases. It is complete, arguably over-complete for the tool's complexity.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool takes no parameters, so there is nothing for the description to clarify and the baseline of 4 applies. The description correctly adds no parameter guidance that would be misleading.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

"Lists your websites with the primary site, agent-readiness score, latest audit summary..." gives a specific verb and resource and enumerates the payload, so the agent knows exactly what comes back. It stops short of a crisp one-line differentiator from siblings such as get_site_audit or check_site_readiness beyond a trailing "Related:" list.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives conditional next-step instructions: when snippetNeedsRepaste is true hand the operator the snippet, when snippet is null send them to sitesUrl, and after deploying aiAssistantFile use check_ai_assistant_tracking. What's missing is an explicit statement of when to call list_sites versus get_site_audit or check_site_readiness, which is left implicit.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All Mark tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?