Skip to main content
Glama
prompteye-mcp

prompteye-mcp

Official

Score how well bots can crawl the site

get_crawl_health
Read-only

The requests of list_bot_visits for one kind, turned into a verdict by the API: how many were errors or redirects, how fast the site answered, and the worst problems behind those numbers.

Instructions

The requests of list_bot_visits for one kind, turned into a verdict by the API: how many were errors or redirects, how fast the site answered, and the worst problems behind those numbers.

assessments holds four fixed checks — the 3xx, 4xx and 5xx rates and the average response time — each scored ok, warning or critical against a fixed threshold the API sets (unknown only for the response-time check, when nothing was ever timed). issues lists up to 20 distinct problems (a bot, a path, a status and, for a redirect, where it pointed), worst first: a 5xx before a 4xx before a 3xx, then the one hit most often, then the one hit most recently. An assistant that cannot fetch a page answers from something else, so each issue is a citation that went elsewhere.

kind is required: ai scores what AI assistants and their bots found, seo what search engines and SEO tools found, and the two are never combined into one score. Only the newest 4 000 requests of the period are read, so narrow the period on a busy project rather than trusting a score built from a partial read.

A bot visit is a machine fetching a page, not a person reading one. It is the supply side of visibility: an assistant can only quote a page its bot was able to fetch, so this says whether the site is reachable and readable to them at all. It is a different measurement from being named in an answer (list_prompts, list_competitors), from being cited as a source (list_sources), and from somebody arriving afterwards (get_ai_traffic). kind=ai is the assistants; kind=seo is classic search engines and SEO tools.

A project whose integration is not connected answers this with zeros and empty lists, which reads exactly like a site nobody visits. Call get_integrations_status before reporting a zero or an empty list as a finding: it says whether Search Console, Google Analytics, the bot tracker and the sitemap are connected, and a sync that is failing. Not connected means the figures say nothing about the site, never that it had no traffic; say the integration is missing and that it can be connected in the PromptEye app.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "projectId": "<projectId>",
      "kind": "<kind>"
    },
    "name": "get_crawl_health"
  }
}

Input Schema

NameRequiredDescriptionDefault
kindYes`ai` for AI assistants and their bots, `seo` for search engines and SEO tools. Required: there is no combined health.
vendorNoOnly bots run by this company, spelled as the API spells it: OpenAI, Anthropic, Google, Perplexity, Meta, Amazon, Apple, Microsoft, ByteDance, Yandex, DuckDuckGo, Ahrefs, Semrush, Moz, CommonCrawl, Mistral, Cohere and others. This is not the `assistant` of get_ai_traffic, which matches a referrer instead.
endDateNoLast day to report on, inclusive. Defaults to today, and must be within 31 days of startDate — these endpoints read a month at a time, not a year.
projectIdYesThe project to work on — its id from list_projects. Required on every call, so that parallel conversations never read or write each other's project.
startDateNoFirst day to report on, inclusive. Defaults to 30 days before today.

Output Schema

NameRequiredDescriptionDefault
totalYesRequests read for the period.
issuesYesUp to 20 distinct problems (status 300 or above), worst first: 5xx before 4xx before 3xx, then the most frequent, then the most recent.
successYesRequests answered with a 2xx status.
unknownYesRequests the site never answered with any status code.
redirectsYesRequests answered with a 3xx status.
assessmentsYesFour fixed checks: the 3xx, 4xx and 5xx rates, and the average response time.
clientErrorsYesRequests answered with a 4xx status.
scanRequestsYesRequests for a path that only a vulnerability scanner would ask for, counted apart from the rest.
serverErrorsYesRequests answered with a 5xx status.
averageResponseTimeMsYesAverage response time across the requests that reported one, in milliseconds. null = none reported one.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv1.0.28
    • addedInput schema / properties / projectId
      Added value: +{
      +  "description": "The project to work on — its id from list_projects. Required on every call, so that parallel conversations never read or write each other's project.",
      +  "minLength": 1,
      +  "type": "string"
      +}
    • changedInput schema / required
      Previous value: -[
      -  "kind"
      -]New value: +[
      +  "projectId",
      +  "kind"
      +]
  2. Addedv1.0.22

TDQS

A4.8/5.0
Behavior5/5

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

With readOnlyHint/openWorldHint already set, the description still adds real behavioral context: the 4 000-newest-requests read cap, the exact scoring/threshold model, the 20-item issue ordering rule, and the critical caveat that a disconnected integration returns zeros and empty lists that mimic a site nobody visits. This is substantial disclosure beyond annotations.

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

Conciseness4/5

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

It is front-loaded with the core verdict definition and the zero-state warning carries real weight, but it runs long and repeats the `kind=ai`/`kind=seo` mapping twice in close succession, which is wasted space.

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

Completeness5/5

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

For a scored, filtered read tool with an output schema, the description covers the return structure (assessments, issues), the failure mode of disconnected integrations, and correct routing to get_integrations_status. Nothing an agent needs to call or interpret it is missing.

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?

Schema coverage is 100%, so the baseline is 3, but the text adds practical meaning for the date parameters (narrow the window rather than accept a partial read) and reinforces that `kind` has no combined value. The `vendor` parameter is only covered by the schema, not the description, so it falls short of full marks.

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

Purpose5/5

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

The opening sentence states a specific transformation: the requests of list_bot_visits for one `kind`, turned into a verdict (error/redirect rates, speed, worst problems). It then names what the tool is not (list_prompts, list_competitors, list_sources, get_ai_traffic), so an agent can separate it from siblings without opening a schema.

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

Usage Guidelines5/5

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

It gives explicit when-to-use conditions (`kind` is required, `ai` vs `seo`, never combined) and an explicit when-not/alternative framing against four named siblings. It also adds an operational rule — narrow the period on a busy project instead of trusting a partial 4 000-request read — and a sequencing instruction to call get_integrations_status before reporting zeros.

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