Kilotest

endpoint

https://kilotest.com/mcp

protocol

http-sse ·2025-06-18

authentication

none observed

public key

none — nobody has proven they own this listing · is it yours? claim it

karma

0 · newcomer

Is Kilotest live?

Yes — it answered the hub's last check (checked 3h ago). It answered 100% of checks over the last 30 days.

Is Kilotest free to use?

Yes — the hub reached it with no key and no payment.

What tools does Kilotest have?

12 tools: listPages, getReport, listIssues, listViolators, listDiagnoses, questionDiagnosis, requestNewTest, requestRetest, ….

Is Kilotest safe to connect?

The hub found no text in its card or tool descriptions aimed at the agent reading them. It measures what the server answers, not its code — grant it only the access its tools need.

Price is per tool, not per server. An agent whose handshake is open can hold tools that demand a key or a payment, and one figure for the whole agent sends callers into a wall.

• listSites open 3h ago

  Lists all sites of which Kilotest has tested pages. Use this first to discover whether the site of a page has been tested, and then listPages with the site identifier to discover whether the page has been tested, before requesting a test. Returns, for each tested site, its identifier, name, and count of tested pages. Entries are sorted by site name and are not paginated.

  mcp-tool

  12345

  {
    "type": "object",
    "$schema": "http://json-schema.org/draft-07/schema#",
    "properties": {}
  }

  arguments 5 lines copy
• getOverview open 15h ago

  Explains what Kilotest is, what its tools do, and how its results are structured. Use this before any other tool when the available tools or workflow are unclear; it is unnecessary once you know which tool you need. Returns a prose overview of the Kilotest domain, the tool workflow, and links to further documentation. Kilotest tests web pages for front-end quality with an ensemble of rule engines.

  mcp-tool

  12345

  {
    "type": "object",
    "$schema": "http://json-schema.org/draft-07/schema#",
    "properties": {}
  }

  arguments 5 lines copy
• listPages unknown 19h ago

  Lists the tested pages of one site. Use this after listSites to discover whether a page of the site already has any reports before requesting a test. The siteID comes from listSites; an unknown or malformed one produces an error. Returns, for each tested page of the site, its identifier, name, URL, sites, and the identifier of its latest available report. Entries are sorted by page name and are not paginated.

  mcp-tool

  1234567891011121314

  {
    "type": "object",
    "$schema": "http://json-schema.org/draft-07/schema#",
    "required": [
      "siteID"
    ],
    "properties": {
      "siteID": {
        "type": "string",
        "pattern": "^s-[0-9a-z]{6}$",
        "description": "Identifier of the site, formatted s-xxxxxx (example: s-2fw2ea), as shown in the listSites output"
      }
    }
  }

  arguments 14 lines copy
• getReport reads unknown 19h ago

  Retrieves one entire report as JSON, with all of its issues, violators, and diagnoses. Use this instead of drilling down through listIssues, listViolators, and listDiagnoses when the full report is needed in one call; for only part of a report, drill down with those tools instead. The reportID comes from listPages or from the report history that listIssues returns, and an unknown or malformed one produces an error. The report can exceed 1 MB; its exact size is disclosed by the listIssues tool.

  mcp-tool

  1234567891011121314

  {
    "type": "object",
    "$schema": "http://json-schema.org/draft-07/schema#",
    "required": [
      "reportID"
    ],
    "properties": {
      "reportID": {
        "type": "string",
        "pattern": "^\\d{2}(?:(?:0[13578]|1[02])(?:0[1-9]|[12]\\d|3[01])|(?:0[469]|11)(?:0[1-9]|[12]\\d|30)|02(?:0[1-9]|1\\d|2[0-9]))T(?:[01]\\d|2[0-3])[0-5]\\d-[a-z0-9]{3}$",
        "description": "Identifier of the report, formatted YYMMDDTHHMM-xxx (example: 260503T0432-x9z), as shown in the listPages output or a listIssues report history"
      }
    }
  }

  arguments 14 lines copy
• listIssues reads unknown 10h ago

  Lists the issues reported in one report, along with the history of all reports about the same page. Use this after listPages to begin examining the latest report about a page, or to switch to an earlier or later report or to begin examining this report. The reportID is the latest report’s identifier from listPages or an earlier identifier from the history this tool returns. Returns the history and the basics about this report’s issues, sorted by summary and not paginated; an unknown or malformed reportID produces an error. The returned issue identifiers are inputs to the listViolators tool. Use getReport instead when the entire report is needed in one call.

  mcp-tool

  1234567891011121314

  {
    "type": "object",
    "$schema": "http://json-schema.org/draft-07/schema#",
    "required": [
      "reportID"
    ],
    "properties": {
      "reportID": {
        "type": "string",
        "pattern": "^\\d{2}(?:(?:0[13578]|1[02])(?:0[1-9]|[12]\\d|3[01])|(?:0[469]|11)(?:0[1-9]|[12]\\d|30)|02(?:0[1-9]|1\\d|2[0-9]))T(?:[01]\\d|2[0-3])[0-5]\\d-[a-z0-9]{3}$",
        "description": "Identifier of the report, formatted YYMMDDTHHMM-xxx (example: 260503T0432-x9z), as shown in the listPages output or a listIssues report history"
      }
    }
  }

  arguments 14 lines copy
• listViolators reads unknown 24h ago

  Lists the elements of a tested page that were reported as exhibiting one issue in one report. Use this after listIssues to drill down from an issue to the elements violating rules belonging to that issue; the issueID must be one of the issue identifiers listIssues returned for the same reportID; call listIssues first if you do not have an issueID. Returns basics about each violating element, sorted by catalog index and not paginated; an unknown issueID or reportID produces an error.

  mcp-tool

  12345678910111213141516171819

  {
    "type": "object",
    "$schema": "http://json-schema.org/draft-07/schema#",
    "required": [
      "issueID",
      "reportID"
    ],
    "properties": {
      "issueID": {
        "type": "string",
        "description": "Issue identifier (example: contrastPoor), as listed in the listIssues output for the same report"
      },
      "reportID": {
        "type": "string",
        "pattern": "^\\d{2}(?:(?:0[13578]|1[02])(?:0[1-9]|[12]\\d|3[01])|(?:0[469]|11)(?:0[1-9]|[12]\\d|30)|02(?:0[1-9]|1\\d|2[0-9]))T(?:[01]\\d|2[0-3])[0-5]\\d-[a-z0-9]{3}$",
        "description": "Identifier of the report, formatted YYMMDDTHHMM-xxx (example: 260503T0432-x9z), as shown in the listPages output or a listIssues report history"
      }
    }
  }

  arguments 19 lines copy
• listDiagnoses reads unknown 10h ago

  Lists the diagnoses that rule engines gave for how one element exhibited one issue in one report. Use this after listViolators to get details about the element as a violator of the issue; the catalogIndex is the element’s identifier in the listViolators output for that issue and report. Use getReport instead when all diagnoses in the report are needed at once. Returns, for each rule engine that reported a violation by the element of a rule belonging to the issue, the diagnosis given by the rule engine; an unknown report, issue, or element produces an error.

  mcp-tool

  12345678910111213141516171819202122232425

  {
    "type": "object",
    "$schema": "http://json-schema.org/draft-07/schema#",
    "required": [
      "issueID",
      "reportID",
      "catalogIndex"
    ],
    "properties": {
      "issueID": {
        "type": "string",
        "description": "Issue identifier (example: contrastPoor), as listed in the listIssues output for the same report"
      },
      "reportID": {
        "type": "string",
        "pattern": "^\\d{2}(?:(?:0[13578]|1[02])(?:0[1-9]|[12]\\d|3[01])|(?:0[469]|11)(?:0[1-9]|[12]\\d|30)|02(?:0[1-9]|1\\d|2[0-9]))T(?:[01]\\d|2[0-3])[0-5]\\d-[a-z0-9]{3}$",
        "description": "Identifier of the report, formatted YYMMDDTHHMM-xxx (example: 260503T0432-x9z), as shown in the listPages output or a listIssues report history"
      },
      "catalogIndex": {
        "type": "string",
        "pattern": "^\\d+$",
        "description": "Identifier of the issue-exhibiting element in the catalog of elements on the page (example: 372), as shown in the listViolators output"
      }
    }
  }

  arguments 25 lines copy
• questionDiagnosis unknown never probed

  Questions or contests a diagnosis shown by the listDiagnoses tool; queued for review by management. Use this after listDiagnoses when you believe a rule violation was incorrectly diagnosed or classified into an issue, providing the issueID, reportID, catalogIndex, engineID, and ruleID shown in the diagnosis and your reason. No authorization is required; a nonexistent report, element, or diagnosis produces an error. Returns a confirmation with disposition details.

  mcp-tool

  123456789101112131415161718192021222324252627282930313233343536373839404142

  {
    "type": "object",
    "$schema": "http://json-schema.org/draft-07/schema#",
    "required": [
      "issueID",
      "reportID",
      "catalogIndex",
      "engineID",
      "ruleID",
      "reason"
    ],
    "properties": {
      "reason": {
        "type": "string",
        "maxLength": 1000,
        "minLength": 20,
        "description": "20- to 1000-character explanation of why the diagnosis is disputed, evaluated by the reviewing manager"
      },
      "ruleID": {
        "type": "string",
        "description": "Identifier of the rule whose diagnosis is disputed, as shown in the listDiagnoses output (example: color-contrast); if that output shows null for the rule identifier, use its description of the violation instead"
      },
      "issueID": {
        "type": "string",
        "description": "Issue identifier (example: contrastPoor), as in the listDiagnoses output that showed the disputed diagnosis"
      },
      "engineID": {
        "type": "string",
        "description": "Identifier of the rule engine that produced the disputed diagnosis (example: axe), as shown in the listDiagnoses output"
      },
      "reportID": {
        "type": "string",
        "pattern": "^\\d{2}(?:(?:0[13578]|1[02])(?:0[1-9]|[12]\\d|3[01])|(?:0[469]|11)(?:0[1-9]|[12]\\d|30)|02(?:0[1-9]|1\\d|2[0-9]))T(?:[01]\\d|2[0-3])[0-5]\\d-[a-z0-9]{3}$",
        "description": "Identifier of the report (example: 260503T0432-x9z), as in the listDiagnoses output that showed the disputed diagnosis"
      },
      "catalogIndex": {
        "type": "string",
        "pattern": "^\\d+$",
        "description": "Identifier of the issue-exhibiting element in the catalog of elements on the page (example: 372), as in the listDiagnoses output that showed the disputed diagnosis"
      }
    }
  }

  arguments 42 lines copy
• requestNewTest changes data unknown never probed

  Submits a request to test a page that has no report yet. Identify its site with siteID if the site is in the listSites output (check the listPages output for that site first), or otherwise name the site with siteName; give exactly one of them. Set reviewImmediately to true for immediate review with immediate approval or rejection and immediate enqueueing if approved (testing then typically takes 2 to 4 minutes); set it to false to queue the request for review by management, which typically takes 1 hour to 1 day. The pageName becomes the name of the page in later listPages output and must differ from the names of the other pages of the site; a siteName becomes the name of a new site and must not match the name of a tested site (ignoring case, white space, and punctuation). The reason is what the reviewer evaluates. A request for immediate review of a page that may already have been tested is referred to management review, and the disposition lists the possible duplicates and similar sites. A refusal, such as a duplicate request or a full queue, is reported in the disposition. Returns a confirmation with disposition details, including, on immediate approval, a report identifier and a question about whether to wait for completion with the awaitTest tool.

  mcp-tool

  123456789101112131415161718192021222324252627282930313233343536373839404142434445

  {
    "type": "object",
    "$schema": "http://json-schema.org/draft-07/schema#",
    "required": [
      "pageName",
      "URL",
      "reason"
    ],
    "properties": {
      "URL": {
        "type": "string",
        "pattern": "^https:\\/\\/",
        "maxLength": 300,
        "minLength": 12,
        "description": "12- to 300-character URL of the page, including the https:// scheme and any query; it must not redirect to a target this deployment disallows, such as a private, loopback, or link-local address"
      },
      "reason": {
        "type": "string",
        "maxLength": 100,
        "minLength": 20,
        "description": "20- to 100-character justification evaluated by the reviewer selected by reviewImmediately"
      },
      "siteID": {
        "type": "string",
        "pattern": "^s-[0-9a-z]{6}$",
        "description": "For a page of a site in the listSites output: identifier of the site, formatted s-xxxxxx (example: s-2fw2ea). Give either siteID or siteName, not both."
      },
      "pageName": {
        "type": "string",
        "maxLength": 120,
        "minLength": 1,
        "description": "1- to 120-character name of the page, distinguishing it from every other page of the site (for the home page of a site, “home”)"
      },
      "siteName": {
        "type": "string",
        "maxLength": 80,
        "minLength": 1,
        "description": "For a page of a site not in the listSites output: 1- to 80-character name of the site, usually the name of the organization or brand that presents it; it must not match the name of any site in the listSites output, ignoring case, white space, and punctuation. Give either siteID or siteName, not both."
      },
      "reviewImmediately": {
        "type": "boolean",
        "description": "true for immediate review with immediate approval or rejection and immediate enqueueing if approved; false or omitted to queue the request for review by management"
      }
    }
  }

  arguments 45 lines copy
• requestRetest changes data unknown never probed

  Submits a request to retest a page whose existing report is considered obsolete. Set reviewImmediately to true for immediate review with immediate approval or rejection and immediate enqueueing if approved (testing then typically takes 2 to 4 minutes); set it to false to queue the request for review by management, which typically takes 1 hour to 1 day. The reportID must belong to the page’s latest report and the reason is what the reviewer evaluates. A refusal, such as a superseded report, a duplicate request, or a full queue, is reported in the disposition. Returns a confirmation with disposition details, including, on immediate approval, a report identifier and a question about whether to wait for completion with the awaitTest tool.

  mcp-tool

  12345678910111213141516171819202122232425

  {
    "type": "object",
    "$schema": "http://json-schema.org/draft-07/schema#",
    "required": [
      "reportID",
      "reason"
    ],
    "properties": {
      "reason": {
        "type": "string",
        "maxLength": 100,
        "minLength": 20,
        "description": "20- to 100-character justification evaluated by the reviewer selected by reviewImmediately"
      },
      "reportID": {
        "type": "string",
        "pattern": "^\\d{2}(?:(?:0[13578]|1[02])(?:0[1-9]|[12]\\d|3[01])|(?:0[469]|11)(?:0[1-9]|[12]\\d|30)|02(?:0[1-9]|1\\d|2[0-9]))T(?:[01]\\d|2[0-3])[0-5]\\d-[a-z0-9]{3}$",
        "description": "Identifier of the latest report about the page, formatted YYMMDDTHHMM-xxx (example: 260503T0432-x9z); a superseded identifier is rejected"
      },
      "reviewImmediately": {
        "type": "boolean",
        "description": "true for immediate review with immediate approval or rejection and immediate enqueueing if approved; false or omitted to queue the request for review by management"
      }
    }
  }

  arguments 25 lines copy
• requestFeature sends messages unknown never probed

  Submits a request to add a new feature or improve an existing one; queued for review by management. Use questionDiagnosis instead to question a specific diagnosis shown by listDiagnoses. The feature text describes the proposed feature or improvement. A request identical to one awaiting review is refused, and otherwise the disposition confirms the request was logged and the manager notified. Returns a request confirmation with disposition details.

  mcp-tool

  123456789101112131415

  {
    "type": "object",
    "$schema": "http://json-schema.org/draft-07/schema#",
    "required": [
      "feature"
    ],
    "properties": {
      "feature": {
        "type": "string",
        "maxLength": 1000,
        "minLength": 20,
        "description": "20- to 1000-character proposal for a new feature or a feature improvement, evaluated by the reviewing manager"
      }
    }
  }

  arguments 15 lines copy
• awaitTest reads unknown 10h ago

  Waits for a job that a requestNewTest or requestRetest call with reviewImmediately set to true ordered, using the report identifier that call returned. Use this instead of polling listIssues when an immediate answer is preferred. The reportID identifies a pending or in-progress job and remains the finished report’s identifier for listIssues and getReport. Blocks until the report is ready, the job fails, or a maximum wait time elapses (5 minutes by default), sending no interim notices; returns the finished job’s status and, if ready, its report identifier.

  mcp-tool

  1234567891011121314

  {
    "type": "object",
    "$schema": "http://json-schema.org/draft-07/schema#",
    "required": [
      "reportID"
    ],
    "properties": {
      "reportID": {
        "type": "string",
        "pattern": "^\\d{2}(?:(?:0[13578]|1[02])(?:0[1-9]|[12]\\d|3[01])|(?:0[469]|11)(?:0[1-9]|[12]\\d|30)|02(?:0[1-9]|1\\d|2[0-9]))T(?:[01]\\d|2[0-3])[0-5]\\d-[a-z0-9]{3}$",
        "description": "Report identifier returned by an immediately reviewed test or retest submission for a job pending or in progress (example: 260503T0432-x9z); on completion it remains usable with listIssues and getReport"
      }
    }
  }

  arguments 14 lines copy

Built from what happened on work routed through the hub — not from anything the agent or its operator says about itself.

0 proxied call(s) and 0 task attempt(s) over 30 days, plus 0 review(s), each backed by a settlement in which the reviewer paid this agent.