← The evidence ledger
Evidence row 2042359
Observed , by probe.mcp/1.
- Kind
- mcp.tools
- About
- endpoint e72182de-b503-4bd8-99a4-70f9e533b0c7
- Recorded
- Previous row
- #1767131
- Body SHA-256
- 6b90188f4dd24d3173d72a09f6cda65036a03638af2ebc5cd1786993d338c0a9
- Leaf
- 0xce33a4de92927b886ebb6fbf75adf3e079bfdeff1f7d027a9095986392a967f8
What was observed
{
"count": 17,
"tools": [
{
"description": "Gets a site's fixes as a work order: what to fix, in what order, how, why and on which pages.\nWhen: at the start of work on a site, and after clickd_changes says a read is done.\nInstead: clickd_site for the score to tell a person; clickd_todo for the next fix across all the person's sites.\nInputs: `site` is a domain, like example.com. `format` is markdown (the default), the whole list, or steps: the four fixes worth the most as steps with pages and points, and words to hand another agent.\nReturns: with markdown, the Markdown text alone; with steps, JSON with steps, prompt, report and caveat.\nFails: a site never read, or a draft, answers not found; clickd_rescan reads it. Works with no key.",
"inputSchema": {
"properties": {
"format": {
"description": "markdown (the default) or steps.",
"enum": [
"markdown",
"steps"
],
"type": "string"
},
"site": {
"description": "The site, as a domain such as example.com.",
"type": "string"
}
},
"required": [
"site"
],
"type": "object"
},
"name": "clickd_brief"
},
{
"description": "Says what a site's latest read changed against the one before: score, rules fixed and newly failing, pages added and removed.\nWhen: after clickd_rescan, every minute or two with its job until the read is done.\nInstead: clickd_rescan to ask for the read; clickd_site for the report as it now stands.\nInputs: `site` is a domain, like example.com. `job` is the id clickd_rescan returned: the reply then says where that read stands, with changes only once it is done.\nReturns: host, run, changes (null for a first read) and visits; with job, job ({ id, state, ahead }), changes null until done.\nFails: a site never read, or a job for another site, answers not found; a failed read says so in job. Needs a key.",
"inputSchema": {
"properties": {
"job": {
"description": "The job id that clickd_rescan returned.",
"type": "number"
},
"site": {
"description": "The site, as a domain such as example.com.",
"type": "string"
}
},
"required": [
"site"
],
"type": "object"
},
"name": "clickd_changes"
},
{
"description": "Checks one live address now, as the free tools do: product data, a page as an agent reads it, an X card, a certificate, or location pages.\nWhen: before and after a fix to one page, link or host.\nInstead: clickd_rescan and clickd_changes for every page of a site; clickd_pages for a page as last read.\nInputs: `kind` is product, agent, x_card, ssl or locations. `url` is the page's full address; for ssl, only its host is used; for locations, the brand's site.\nReturns: the findings, each with its state in a word and what to do when it is wrong.\nFails: a private address is refused, and robots.txt is obeyed; the free tools' hourly allowance applies. Works with no key.",
"inputSchema": {
"properties": {
"kind": {
"description": "Which check.",
"enum": [
"product",
"agent",
"x_card",
"ssl",
"locations"
],
"type": "string"
},
"url": {
"description": "The address to check, such as https://example.com/products/linen-shirt.",
"type": "string"
}
},
"required": [
"kind",
"url"
],
"type": "object"
},
"name": "clickd_check"
},
{
"description": "Lists what assistants were found to cite for a site, question by question, from lookups already made, and the credits left.\nWhen: to tell a person whether assistants cite their site, at no cost.\nInstead: clickd_site for how well formed the pages are, which is not whether they are cited.\nInputs: `site` is a domain, like example.com.\nReturns: host, rows, credits, price, perDay and note.\nFails: rows is empty until a lookup is made. Needs a key and a claim.",
"inputSchema": {
"properties": {
"site": {
"description": "The site, as a domain such as example.com.",
"type": "string"
}
},
"required": [
"site"
],
"type": "object"
},
"name": "clickd_citations"
},
{
"description": "Claims a site for the person: the TXT record or file that proves it is theirs, then the check that finds it.\nWhen: to open a site's private parts, such as rivals, citations and proposals.\nInstead: clickd_signup first for a key; clickd_site for a public report, which needs no claim.\nInputs: `site` is a domain, like example.com. `step` is start (the default), for the record and file, or check, to look for either and add the site.\nReturns: with start, site, record, dns, file and note; with check, site, claimed and how.\nFails: check before the proof is up answers claimed false; a new DNS record can take minutes to be seen. Needs a person's key.",
"inputSchema": {
"properties": {
"site": {
"description": "The site, as a domain such as example.com.",
"type": "string"
},
"step": {
"description": "start (the default) or check.",
"enum": [
"start",
"check"
],
"type": "string"
}
},
"required": [
"site"
],
"type": "object"
},
"name": "clickd_claim"
},
{
"description": "Lists the public leaderboard: every ranked site by its latest score, the board of one crowd, or a record.\nWhen: to show a person where a site places among every site, or sites like it.\nInstead: clickd_site for one site's own place; clickd_rivals for the sites closest to one site.\nInputs: `in` (a line of work such as trades), `state` (two letters), `city` (needs state) and `size` narrow the board, together or alone. `record` gives one record in place of the places. `limit` and `offset` page it.\nReturns: total, offset, limit, sites, tiers and note; with record, its sites and what it counted.\nFails: a crowd too small answers an empty board; drafts and closed sites are not ranked. Works with no key.",
"inputSchema": {
"properties": {
"city": {
"description": "A city in that state, such as Dallas.",
"type": "string"
},
"in": {
"description": "A line of work, such as trades.",
"type": "string"
},
"limit": {
"description": "How many to return.",
"type": "number"
},
"offset": {
"description": "How many to skip, for the next part of a long list.",
"type": "number"
},
"record": {
"description": "One record in place of the places.",
"enum": [
"fastest",
"improved",
"stages",
"answer-first",
"biggest"
],
"type": "string"
},
"size": {
"description": "By the pages a read took.",
"enum": [
"1-10",
"11-50",
"51-99",
"100-plus"
],
"type": "string"
},
"state": {
"description": "A US state by two letters, such as MO.",
"type": "string"
}
},
"required": [],
"type": "object"
},
"name": "clickd_leaderboard"
},
{
"description": "Records a step of work on a site: what you planned, changed or checked, or where you got stuck.\nWhen: after each step, including one that carries out a proposal or a queued task.\nInstead: clickd_propose before deploying to a site set to approve; clickd_todo for tasks waiting.\nInputs: `site` is a domain, like example.com. `step` is planned, changed, checked or stuck; `did` says what. `found`, `files` and `rules` (comma separated) add detail. `proposal` names the proposal carried out, `task` the queued task finished. Never send private data.\nReturns: kept, site, step and note, with proposal or task and left when given.\nFails: a proposal or task not the person's keeps nothing and says so. Needs a person's key.",
"inputSchema": {
"properties": {
"did": {
"description": "What was done, in a sentence or two.",
"type": "string"
},
"files": {
"description": "The files touched, separated by commas.",
"type": "string"
},
"found": {
"description": "What was true of the site, such as of its code.",
"type": "string"
},
"proposal": {
"description": "The proposal id, from clickd_propose, this step carried out.",
"type": "number"
},
"rules": {
"description": "The clickd rules worked on, by id, separated by commas.",
"type": "string"
},
"site": {
"description": "The site, as a domain such as example.com.",
"type": "string"
},
"step": {
"description": "Which step this was.",
"enum": [
"planned",
"changed",
"checked",
"stuck"
],
"type": "string"
},
"task": {
"description": "The queued task id this step finished.",
"type": "number"
}
},
"required": [
"site",
"step",
"did"
],
"type": "object"
},
"name": "clickd_log_work"
},
{
"description": "Lists the pages of a site's latest read with status, depth, words and failing rules, or gives one page in full.\nWhen: to find the pages behind a fix, or everything wrong with one page.\nInstead: clickd_brief for the fixes in order; clickd_check for a page as it is live now.\nInputs: `site` is a domain, like example.com. `path`, such as /pricing, gives that page in full, and the rest is then ignored. `failing` (a rule id), `q`, `kind` and `section` narrow the list, `sort` and `dir` order it, `limit` and `offset` page it.\nReturns: host, run, total and pages; one page as path, status, failing, needsAPerson, linkedFrom, linksTo and quoted.\nFails: a site or page not read answers not found. Needs a key; any key reads a public site.",
"inputSchema": {
"properties": {
"dir": {
"description": "Which way.",
"enum": [
"asc",
"desc"
],
"type": "string"
},
"failing": {
"description": "A rule id.",
"type": "string"
},
"kind": {
"description": "A kind of page.",
"enum": [
"home",
"article",
"service",
"page"
],
"type": "string"
},
"limit": {
"description": "How many to return.",
"type": "number"
},
"offset": {
"description": "How many to skip, for the next part of a long list.",
"type": "number"
},
"path": {
"description": "One page, such as /pricing.",
"type": "string"
},
"q": {
"description": "Text in the path.",
"type": "string"
},
"section": {
"description": "A section, such as /guides.",
"type": "string"
},
"site": {
"description": "The site, as a domain such as example.com.",
"type": "string"
},
"sort": {
"description": "What to sort by.",
"enum": [
"path",
"kind",
"depth",
"words",
"ms",
"inlinks",
"failing"
],
"type": "string"
}
},
"required": [
"site"
],
"type": "object"
},
"name": "clickd_pages"
},
{
"description": "Lists the person's proposals and where each stands, or one by id, and whether a site is set to approve or automatic.\nWhen: before work on a claimed site, and every few minutes after clickd_propose until it is answered.\nInstead: clickd_propose to make one; clickd_todo for the work itself.\nInputs: `id` is one proposal from clickd_propose; deploy only once it says approved. `site` gives that site's proposals and its mode. Neither, every proposal; never both.\nReturns: with id, proposal and promise; otherwise proposals and promise, and with site, site and mode.\nFails: id and site together are refused; one not the person's answers not found. Needs a person's key.",
"inputSchema": {
"properties": {
"id": {
"description": "One proposal, by the id clickd_propose returned.",
"type": "number"
},
"site": {
"description": "Only proposals for this site, and its mode.",
"type": "string"
}
},
"type": "object"
},
"name": "clickd_proposals"
},
{
"description": "Proposes a change before you deploy it, emailing the person Approve and Decline links that lapse in 72 hours.\nWhen: before each deploy to a site clickd_proposals says is set to approve.\nInstead: clickd_proposals with the id to wait for the answer; clickd_log_work, naming it, once carried out.\nInputs: `site` is a domain, like example.com. `title` is the change in a few words; `summary` what it does and why; `rule` the rule id it answers; `pages` the paths it changes, comma separated; `diff` a unified diff, shown and never applied.\nReturns: proposal ({ id, state, deploy, ... }), note and promise.\nFails: a site not claimed with this key answers not found; 20 proposals a site an hour at most. Needs a person's key.",
"inputSchema": {
"properties": {
"diff": {
"description": "A unified diff, at most 20,000 characters.",
"type": "string"
},
"pages": {
"description": "Paths separated by commas, at most 20; none for the whole site.",
"type": "string"
},
"rule": {
"description": "The rule id it answers, such as answer-first.",
"type": "string"
},
"site": {
"description": "The site, as a domain such as example.com.",
"type": "string"
},
"summary": {
"description": "What it does and why, at most 2000 characters.",
"type": "string"
},
"title": {
"description": "The change in a few words, at most 120 characters.",
"type": "string"
}
},
"required": [
"site",
"title",
"summary"
],
"type": "object"
},
"name": "clickd_propose"
},
{
"description": "Puts a fresh read of a site in line and returns a job to follow.\nWhen: once a fix is deployed, or for a site clickd has never read.\nInstead: clickd_changes with the job to see what the read changed; clickd_check for one live page with no read.\nInputs: `site` is a domain, like example.com. `reason` says what was changed, in a few words.\nReturns: job, added (false when a read was already in line), allowedAt and ahead.\nFails: a site read in the last ten minutes answers allowedAt, when to ask again; a private address is refused. Needs a key.",
"inputSchema": {
"properties": {
"reason": {
"description": "What was changed, in a few words.",
"type": "string"
},
"site": {
"description": "The site, as a domain such as example.com.",
"type": "string"
}
},
"required": [
"site"
],
"type": "object"
},
"name": "clickd_rescan"
},
{
"description": "Sets a site against its rivals from kept reads: who they are, how close, and where it is behind.\nWhen: to pick the fixes that matter against the sites a buyer compares it with.\nInstead: clickd_leaderboard for places among every site; clickd_site for its own score.\nInputs: `site` is a domain, like example.com. `view` is competitors (default: rivals doing similar work), near (closest in meaning), market (rule by rule), or rules or content (two sites side by side). `with` is the other site, for rules or content; alone, it means rules. `limit` is for near, 10 if left out.\nReturns: host, then by view: local, nearby and elsewhere; sites; rules; ahead and behind; or pages.\nFails: a site with no meaning yet answers found or embedded false; rules or content with no with says to give it. Needs a key and a claim.",
"inputSchema": {
"properties": {
"limit": {
"description": "For near only: how many sites. 10 if left out.",
"type": "number"
},
"site": {
"description": "The site, as a domain such as example.com.",
"type": "string"
},
"view": {
"description": "competitors (the default), near, market, rules or content.",
"enum": [
"competitors",
"near",
"market",
"rules",
"content"
],
"type": "string"
},
"with": {
"description": "The other site, already read.",
"type": "string"
}
},
"required": [
"site"
],
"type": "object"
},
"name": "clickd_rivals"
},
{
"description": "Lists the rulebook: every rule clickd checks, with its id, stage, weight and fix.\nWhen: to explain a fix to a person, or to find a rule's id.\nInstead: clickd_brief for the rules one site fails; clickd_pages with failing for the pages failing one.\nInputs: none.\nReturns: rules, each with id, title, stage, weight and fix.\nFails: nothing to refuse. Works with no key.",
"inputSchema": {
"properties": {},
"type": "object"
},
"name": "clickd_rules"
},
{
"description": "Makes JSON-LD for one page from the fields given, ready to paste, and fetches nothing.\nWhen: to write the structured data a fix asks for; call it with only type to see the fields.\nInstead: clickd_check with kind product to check a live product page.\nInputs: `type` is one of the types offered; `as` a more exact one, such as Plumber; `fields` the values by field key, as text. Give only what the page shows.\nReturns: jsonld, script (ready to paste), missing, problems, recommended and fields.\nFails: a type not offered says which are. Works with no key.",
"inputSchema": {
"properties": {
"as": {
"description": "A more exact type, for LocalBusiness (such as Plumber, RoofingContractor, Restaurant) or Article (BlogPosting, NewsArticle).",
"type": "string"
},
"fields": {
"description": "Values by field key, as text, such as { \"name\": \"Acme Plumbing\" }. A list is one value a line.",
"type": "object"
},
"type": {
"description": "The schema type to make.",
"enum": [
"LocalBusiness",
"Organization",
"Product",
"Article",
"BreadcrumbList",
"Service",
"Event",
"WebSite"
],
"type": "string"
}
},
"required": [
"type"
],
"type": "object"
},
"name": "clickd_schema_create"
},
{
"description": "Gets a free key, shown once, with the command to connect with it: the person's by email, or a throwaway one.\nWhen: when a call needs a key and there is none.\nInstead: clickd_claim, with a person's key, to make a site theirs.\nInputs: `email` is the person's own address; leave it out for a throwaway key, which reads and asks for a few reads an hour.\nReturns: key, connect and next, with email or anonymous.\nFails: an email already signed up, or not an email, says so; three an hour from one address. Needs no key.",
"inputSchema": {
"properties": {
"email": {
"description": "The person's email address. Leave it out for a throwaway key.",
"type": "string"
}
},
"type": "object"
},
"name": "clickd_signup"
},
{
"description": "Gets a site's report from its latest read: score, grades, place among ranked sites, towns served, and every fix with its failing pages.\nWhen: to tell a person how a site stands.\nInstead: clickd_brief for the fixes as a work order; clickd_rivals for its rivals; clickd_check for one live page.\nInputs: `site` is a domain, like example.com. `view` is report (the default) or agent: the whole-site Agent View from the same read, with each AI crawler as robots.txt treats it.\nReturns: host, score, grade, stages, grades, rank, served, fixes and card, a picture to send the person; with agent, the Agent View's figures.\nFails: a site never read, a draft or one kept unnamed answers not found. Works with no key.",
"inputSchema": {
"properties": {
"site": {
"description": "The site, as a domain such as example.com.",
"type": "string"
},
"view": {
"description": "report (the default) or agent.",
"enum": [
"report",
"agent"
],
"type": "string"
}
},
"required": [
"site"
],
"type": "object"
},
"name": "clickd_site"
},
{
"description": "Gets the person's work across all their sites: the next fix and every other by worth, or the tasks they queued for you.\nWhen: when you start work for the person, and when a reply says tasks are waiting.\nInstead: clickd_brief for every fix on one site; clickd_log_work with task to finish a queued task.\nInputs: `show` is board (the default): next, every fix by worth, what slipped and what is fixed; or queue: the person's tasks for you, oldest first.\nReturns: with board, next, todo, slipped, fixed, waiting and note; with queue, tasks and note.\nFails: an account with no claimed site has an empty board. Needs a person's key.",
"inputSchema": {
"properties": {
"show": {
"description": "board (the default) or queue.",
"enum": [
"board",
"queue"
],
"type": "string"
}
},
"required": [],
"type": "object"
},
"name": "clickd_todo"
}
]
}What the leaf hashes
{"body":"6b90188f4dd24d3173d72a09f6cda65036a03638af2ebc5cd1786993d338c0a9","id":2042359,"kind":"mcp.tools","method":"probe.mcp/1","observed_us":1793588686182657,"prev":1767131,"subject":"e72182de-b503-4bd8-99a4-70f9e533b0c7","subject_kind":"endpoint"}Proof
Its day has not closed yet. A day closes ten minutes after midnight UTC; the proof appears here then.