Server definition
- Hash
- sha256:b2958b47abf46ef42a4aee04ea31179546aca08683bcc6b311ae53dc3e903776
- What it is
- What a remote MCP server returned when asked what it offers: 34 tools
The blob, as servednamed by its sha256
{
"instructions": null,
"tools": [
{
"description": "Agent readiness report for a domain. Use when a task needs to know what an AI agent can actually do on a domain: llms.txt, robots rules for AI crawlers, sitemap, OpenAPI, an MCP endpoint, x402 or MPP offers, agent-commerce manifests (UCP, ACP, A2A) and structured data, with a score and a specific fix for each gap. Cost: 3 credits per call.",
"inputSchema": {
"properties": {
"domain": {
"description": "The domain to check. A URL is accepted and its host is used.",
"type": "string"
}
},
"required": [
"domain"
],
"type": "object"
},
"name": "agent_readiness",
"outputSchema": null
},
{
"description": "Airport reference data. Use when a task needs the static facts about an airport: what an IATA or ICAO code means, where the airport is (city, region, country, coordinates, elevation), whether it has scheduled airline service, which airports a country has, or the straight-line distance and initial bearing between two of them. Cost: 1 credit per call.",
"inputSchema": {
"properties": {
"code": {
"description": "One IATA (LHR) or ICAO (EGLL) code. Returns that single airport. Cannot be combined with q, country or from/to.",
"type": "string"
},
"country": {
"description": "ISO 3166-1 alpha-2 country code. Returns that country's airports as a list.",
"type": "string"
},
"from": {
"description": "Origin IATA or ICAO code for a distance query. Must be sent with to.",
"type": "string"
},
"limit": {
"description": "Page size for a q or country list.",
"type": "integer"
},
"offset": {
"description": "Rows to skip for a q or country list.",
"type": "integer"
},
"q": {
"description": "Free-text search over airport, city and code. Returns a list.",
"type": "string"
},
"to": {
"description": "Destination IATA or ICAO code. Must be sent with from.",
"type": "string"
},
"type": {
"description": "Filters a q or country list by airport size. Refused on a code or from/to query, which have no list to shape.",
"type": "string"
}
},
"required": [],
"type": "object"
},
"name": "airports",
"outputSchema": null
},
{
"description": "Capture a public HTTP(S) page as PNG, PDF or rendered HTML. Records what the PageVerified renderer saw; not a forensic chain of custody. PNG and HTML cost 1 credit; PDF costs 2 credits. Captures run in a shared browser pool, with a limit on the browser time used in one day and in any 31 days. If the pool is used up, a capture call answers 503 capture_capacity_reached and costs nothing until capacity returns. One key cannot use the whole pool: a key that has used its share, or has had too many failed captures today, gets 429 capture_share_reached, also at no cost. Other tools are not affected.",
"inputSchema": {
"properties": {
"format": {
"default": "png",
"enum": [
"png",
"pdf",
"html"
],
"type": "string"
},
"full_page": {
"default": false,
"type": "boolean"
},
"public_receipt": {
"default": true,
"description": "Publish a readable capture receipt",
"type": "boolean"
},
"url": {
"description": "Public HTTP or HTTPS page to render",
"format": "uri",
"type": "string"
},
"viewport": {
"properties": {
"height": {
"maximum": 2000,
"minimum": 240,
"type": "integer"
},
"width": {
"maximum": 2560,
"minimum": 320,
"type": "integer"
}
},
"type": "object"
}
},
"required": [
"url"
],
"type": "object"
},
"name": "capture_url",
"outputSchema": null
},
{
"description": "Company open roles. Use when a task needs the roles one named company is hiring for right now: the live list from that company's own Greenhouse, Lever or Ashby job board, with title, location, department, team, employment type, remote flag, posted date and a link to apply, and optionally the description as plain text. Give a board token or the careers-page URL; the provider is detected either way. Cost: 2 credits per call.",
"inputSchema": {
"properties": {
"careers_url": {
"description": "The company's Greenhouse, Lever or Ashby careers page. The provider and board token are derived from it.",
"type": "string"
},
"company": {
"description": "The company's board token, as it appears in its job-board URL. Required unless careers_url is sent.",
"type": "string"
},
"include_description": {
"description": "Include each role's description as plain text. Off by default, because it makes the response much larger.",
"type": "boolean"
},
"provider": {
"description": "auto (default), greenhouse, lever or ashby. Refused if it disagrees with careers_url.",
"type": "string"
}
},
"required": [],
"type": "object"
},
"name": "company_jobs",
"outputSchema": null
},
{
"description": "Currency conversion (reference rates). Use when a task needs an indicative conversion of an amount between two of about 30 major currencies (AUD, USD, GBP, JPY, NZD, CAD, CNY and others) at the latest European Central Bank reference rates, for estimates or reports, not for transactions. The ECB publishes the euro rates free of charge on its website. Cost: 1 credit per call.",
"inputSchema": {
"properties": {
"amount": {
"description": "The amount to convert, as a JSON number. A numeric string is refused rather than guessed at.",
"type": "number"
},
"from": {
"description": "Three-letter code of the currency the amount is in.",
"type": "string"
},
"to": {
"description": "Three-letter code to convert to.",
"type": "string"
}
},
"required": [
"amount",
"from",
"to"
],
"type": "object"
},
"name": "currency_convert",
"outputSchema": null
},
{
"description": "Currency reference rates. Use when a task needs today's European Central Bank reference exchange rates for about 30 major currencies (AUD, USD, GBP, JPY, NZD, CAD, CNY and others) against any of them as base, for information such as estimates or reports, not for transactions. The ECB publishes the euro rates free of charge on its website. Cost: 1 credit per call.",
"inputSchema": {
"properties": {
"base": {
"description": "Three-letter code to quote the rates against. Defaults to EUR, the currency the ECB publishes.",
"type": "string"
}
},
"required": [],
"type": "object"
},
"name": "currency_rates",
"outputSchema": null
},
{
"description": "Developer utilities: cron, regex, UUID, slug and JSON. Use when a task needs one of the small developer answers that would otherwise cost a round trip to a web tool: the next times a cron expression fires (in a named time zone and in UTC, with a plain-English reading and a note on which non-standard extensions it uses), what a regular expression matches in a piece of text (run on RE2, so no pattern can backtrack its way into exponential time, and a pattern whose compiled program is too large for the input it was given is refused rather than run), fresh UUIDs (version 4, or time-ordered version 7), a URL slug for a title, or JSON pretty-printed, minified or key-sorted with the line and column of a syntax error. Free, and no data is kept. Free to call.",
"inputSchema": {
"properties": {
"count": {
"description": "How many cron runs, or how many UUIDs, to return.",
"type": "integer"
},
"expression": {
"description": "The cron expression, for cron_next_runs.",
"type": "string"
},
"flags": {
"description": "Distinct letters from i, m, s and u, for regex_test.",
"type": "string"
},
"indent": {
"description": "Spaces per level for json_format; 0 minifies.",
"type": "integer"
},
"input": {
"description": "The text to run the pattern over, for regex_test.",
"type": "string"
},
"limit": {
"description": "Maximum matches to return, for regex_test.",
"type": "integer"
},
"max_length": {
"description": "Cap on the slug length, for slugify.",
"type": "integer"
},
"operation": {
"description": "One of cron_next_runs, regex_test, uuid, slugify, json_format. Each one reads its own further fields.",
"type": "string"
},
"pattern": {
"description": "The regular expression, for regex_test. Run on RE2.",
"type": "string"
},
"separator": {
"description": "The slug separator. Defaults to a hyphen.",
"type": "string"
},
"sort_keys": {
"description": "Sort object keys, for json_format.",
"type": "boolean"
},
"start": {
"description": "ISO instant to start the cron walk from, for cron_next_runs.",
"type": "string"
},
"text": {
"description": "The title to slugify, or the JSON document to format.",
"type": "string"
},
"timezone": {
"description": "IANA time zone name for cron_next_runs, such as Europe/London. Defaults to UTC.",
"type": "string"
},
"version": {
"description": "4 (random) or 7 (time-ordered), for uuid. Defaults to 4.",
"type": "integer"
}
},
"required": [
"operation"
],
"type": "object"
},
"name": "dev_utils",
"outputSchema": null
},
{
"description": "Directory dataset. Use when an agent needs a paged export or change feed of verified PageVerified directory facts. Cost: 10 credits per call.",
"inputSchema": {
"properties": {
"category": {
"description": "A PageVerified directory category slug.",
"type": "string"
},
"cursor": {
"description": "Opaque next_cursor from the previous page. Keep category and since unchanged. If matching data changes, restart without a cursor.",
"type": "string"
},
"format": {
"description": "json (default) or csv. CSV remains inside the JSON response envelope.",
"type": "string"
},
"limit": {
"description": "1–500 rows; defaults to 500. Each successful page costs 10 credits, including an empty page.",
"type": "integer"
},
"since": {
"description": "ISO date or timestamp with timezone; includes rows verified OR updated at or after it.",
"type": "string"
}
},
"required": [],
"type": "object"
},
"name": "directory_dataset",
"outputSchema": null
},
{
"description": "Directory search. Use when a developer, tool maker, business or AI agent needs to find AI-agent tools (MCP servers, frameworks, browser automation, memory, evals, voice, coding agents and more) by keyword or category before choosing one, or wants MCP servers and pay-per-call services with how to connect and how to pay (filter by protocol mcp, x402 or mpp, or by payable or free). Free to call. Free without an API key over REST and MCP. Anonymous searches have per-IP limits of 30 calls per minute and, where the shared limiter is configured, 600 per hour; 429 responses include Retry-After. Keyed calls cost 0 credits and keep the key's existing limits.",
"inputSchema": {
"properties": {
"capability": {
"description": "A tested capability token: mcp_server_card, ard_manifest, ai_catalog, a2a_agent_card, openapi, x402_discovery or llms_txt. Returns verified tools where PageVerified found it; no indexed entries.",
"type": "string"
},
"category": {
"description": "One of the PageVerified directory category slugs.",
"type": "string"
},
"limit": {
"description": "Maximum tools to return, applied separately to tools and indexed.",
"type": "integer"
},
"payment": {
"description": "payable (machine-payable via x402 or MPP) or free (the catalog says so). Returns indexed entries only.",
"type": "string"
},
"protocol": {
"description": "mcp, x402 or mpp. Returns indexed entries only.",
"type": "string"
},
"q": {
"description": "Keyword to search over the verified tools and the indexed catalog entries.",
"type": "string"
}
},
"required": [],
"type": "object"
},
"name": "directory_search",
"outputSchema": null
},
{
"description": "DNS records for a domain. Use when a task needs a domain's live A, AAAA, MX, TXT, NS or CAA records in one structured answer, including whether the name exists at all. Cost: 1 credit per call.",
"inputSchema": {
"properties": {
"domain": {
"description": "The domain to look up. A URL is accepted and its host is used.",
"type": "string"
},
"types": {
"description": "Any of A, AAAA, MX, TXT, NS, CAA. Defaults to all six.",
"type": "array"
}
},
"required": [
"domain"
],
"type": "object"
},
"name": "dns_lookup",
"outputSchema": null
},
{
"description": "Email address check. Use when an agent needs to screen an email address before a sign-up, lead import or send: syntax, whether the domain can receive mail (MX), disposable domains, role accounts and free mailbox providers — without contacting the mail server. Cost: 1 credit per call.",
"inputSchema": {
"properties": {
"email": {
"description": "The address to screen. Nothing is sent to the mail server.",
"type": "string"
}
},
"required": [
"email"
],
"type": "object"
},
"name": "email_check",
"outputSchema": null
},
{
"description": "Email sending-domain check. Use when a task needs to know whether a domain is set up to send email that inboxes accept: MX, SPF (with the 10-lookup limit), DKIM keys, DMARC policy, MTA-STS, TLS-RPT and BIMI, with a 0-100 score and plain-English fixes. Cost: 1 credit per call.",
"inputSchema": {
"properties": {
"dkim_selectors": {
"description": "Extra DKIM selectors to look up, on top of the common ones this service tries.",
"type": "array"
},
"domain": {
"description": "The sending domain to check. Required unless email is sent.",
"type": "string"
},
"email": {
"description": "An address to take the domain from. Refused if it disagrees with domain.",
"type": "string"
}
},
"required": [],
"type": "object"
},
"name": "email_domain_auth",
"outputSchema": null
},
{
"description": "File converter. Use when a task has a file in one format and needs it in another: a Word document (.docx) to HTML, Markdown or plain text; HTML to Markdown or plain text; Markdown to HTML; CSV to JSON; JSON to CSV; or CSV and TSV either way. Send the file as a URL or base64, or paste the text. Input is capped at 6 MB, or 1 MB when the target is Markdown, and nothing is stored. Cost: 1 credit per call.",
"inputSchema": {
"properties": {
"file_base64": {
"description": "The document as base64. Exactly one of text, url or file_base64.",
"type": "string"
},
"from": {
"description": "The input format: docx, html, markdown, csv, json or tsv.",
"type": "string"
},
"text": {
"description": "The document as text. Not accepted for docx, which is binary.",
"type": "string"
},
"to": {
"description": "The output format. Supported pairs are returned on every response and on an unsupported_conversion error.",
"type": "string"
},
"url": {
"description": "A public http(s) URL to read the document from.",
"type": "string"
}
},
"required": [
"from",
"to"
],
"type": "object"
},
"name": "file_convert",
"outputSchema": null
},
{
"description": "Hash and encode text. Use when a task needs an exact SHA or MD5 digest, or text converted to or from base64, base64url, hex or URL percent-encoding, where a language model would otherwise guess the output. Cost: 1 credit per call.",
"inputSchema": {
"properties": {
"algorithm": {
"description": "For hash: sha256 (the default), sha384, sha512, sha1 or md5.",
"type": "string"
},
"digest": {
"description": "For hash: hex (the default), base64 or base64url.",
"type": "string"
},
"format": {
"description": "For encode and decode: base64, base64url, hex or url.",
"type": "string"
},
"input_encoding": {
"description": "For hash: how to read text. utf8 (the default), base64 or hex.",
"type": "string"
},
"operation": {
"description": "hash, encode or decode.",
"type": "string"
},
"text": {
"description": "The input, up to 1 MiB.",
"type": "string"
}
},
"required": [
"operation",
"text"
],
"type": "object"
},
"name": "hash_encode",
"outputSchema": null
},
{
"description": "Validate JSON against a JSON Schema. Use when a task needs to know whether a JSON value satisfies a JSON Schema (2020-12 and draft-07 keywords, local $ref), with the path and reason for every failure, before passing the value to another system. Cost: 1 credit per call.",
"inputSchema": {
"properties": {
"instance": {
"description": "The JSON value to validate, of any type.",
"type": [
"object",
"array",
"string",
"number",
"boolean",
"null"
]
},
"schema": {
"description": "The JSON Schema, an object or a boolean. Only local $ref is followed; no network reference is fetched.",
"type": "object"
}
},
"required": [
"schema",
"instance"
],
"type": "object"
},
"name": "json_schema_validate",
"outputSchema": null
},
{
"description": "Decode a JWT (no signature check). Use when a task needs to read the header and claims of a JSON Web Token, such as its issuer, audience, scopes or expiry, while debugging. Decode only: the signature is not verified, so the claims are unproven and must not be used to authorize anything. Cost: 1 credit per call.",
"inputSchema": {
"properties": {
"token": {
"description": "The compact JWT. Prefer an expired or test token: this tool cannot tell a live credential from a sample.",
"type": "string"
}
},
"required": [
"token"
],
"type": "object"
},
"name": "jwt_decode",
"outputSchema": null
},
{
"description": "Backlink check. Use when a task needs to confirm that a page links to a site or URL: whether the link is there, whether it is followed (no nofollow, sponsored or ugc) and whether the linking page can be indexed, based on Google's published robots and link rules. Cost: 1 credit per call.",
"inputSchema": {
"properties": {
"page_url": {
"description": "The public page that should carry the link.",
"type": "string"
},
"target": {
"description": "The site or URL the link should point at.",
"type": "string"
}
},
"required": [
"page_url",
"target"
],
"type": "object"
},
"name": "links_verify",
"outputSchema": null
},
{
"description": "Inspect a remote MCP server. Use when an agent needs to know what a remote MCP server offers before connecting it: transport, protocol version, whether it needs auth, and the tools it lists. A GET checks the URL first; initialize and tools/list are POSTed only if that GET identifies an MCP server (or answers a bare 405 on a path ending in /mcp, as many Streamable HTTP servers do), and no tool is ever called. Remote text comes back labelled as untrusted third-party data. Cost: 2 credits per call.",
"inputSchema": {
"properties": {
"url": {
"description": "The public http(s) URL of the MCP endpoint, such as https://example.com/mcp.",
"type": "string"
}
},
"required": [
"url"
],
"type": "object"
},
"name": "mcp_inspect",
"outputSchema": null
},
{
"description": "Inspect an MPP HTTP 402 challenge without paying. Use when an agent is about to pay an HTTP 402 resource that uses Machine Payments Protocol challenges (WWW-Authenticate: Payment) and needs the method, intent, amount, currency, recipient, expiry and any malformed field first. No credential is sent. Cost: 1 credit per call.",
"inputSchema": {
"properties": {
"method": {
"description": "GET (the default) or POST. A POST is sent only when a GET of the same URL already answered with a payment challenge, or the site's own /openapi.json declares a paid POST at that path, and always with an empty body. Otherwise the GET's answer is returned and post_skipped is true.",
"type": "string"
},
"url": {
"description": "The public http(s) resource to inspect.",
"type": "string"
}
},
"required": [
"url"
],
"type": "object"
},
"name": "mpp_inspect",
"outputSchema": null
},
{
"description": "Public-domain art and media search. Use when a task needs an image or artwork that is free to use: public-domain works from The Metropolitan Museum of Art and the Art Institute of Chicago, each with title, artist, date, medium, a full-size image URL, a thumbnail, the museum's page for the work, the licence the museum publishes and a ready-made credit line. Only items the museum itself flags as public domain are returned. Cost: 1 credit per call.",
"inputSchema": {
"properties": {
"has_image": {
"description": "Only return items that have an image. On by default.",
"type": "boolean"
},
"limit": {
"description": "Maximum items to return.",
"type": "integer"
},
"q": {
"description": "What to search the museum collections for.",
"type": "string"
},
"source": {
"description": "all (default), met for The Metropolitan Museum of Art, or aic for the Art Institute of Chicago.",
"type": "string"
}
},
"required": [
"q"
],
"type": "object"
},
"name": "open_media_search",
"outputSchema": null
},
{
"description": "Page metadata from a URL. Use when a task needs a page's title, description, canonical URL, Open Graph and Twitter card tags, JSON-LD, declared language or RSS and Atom feeds without pulling in its full text. Cost: 1 credit per call.",
"inputSchema": {
"properties": {
"url": {
"description": "The public http(s) page to read.",
"type": "string"
}
},
"required": [
"url"
],
"type": "object"
},
"name": "page_meta",
"outputSchema": null
},
{
"description": "Phone number check. Use when a task needs to know whether a phone number is valid for its country, what kind of number it is (mobile, landline, toll-free, premium rate, VoIP) and its E.164, national and international formats. Formats, country and type are only returned for valid numbers; an invalid number keeps its E.164 form only when its length is possible, and e164 is null for any number longer than the 15 digits E.164 allows. The phone input may be a plain number or an RFC 3966 tel: URI, so the uri from an earlier answer can be fed straight back in. Checked offline: no carrier or live-line lookup. Cost: 1 credit per call.",
"inputSchema": {
"properties": {
"default_country": {
"description": "ISO 3166-1 alpha-2 region code to read a national-format number against.",
"type": "string"
},
"phone": {
"description": "The number, as digits or as an RFC 3966 tel: URI, so the uri from an earlier answer can be fed straight back in.",
"type": "string"
}
},
"required": [
"phone"
],
"type": "object"
},
"name": "phone_parse",
"outputSchema": null
},
{
"description": "Check before you connect or pay. Use when developers, businesses and AI agents need public endpoint facts before connecting or paying: x402 terms, signed offers, recipient and price history, MCP tool changes and domain observations. No payment is sent. Costs 5 credits or US$0.05 per call through x402 when enabled. Cost: 5 credits per call.",
"inputSchema": {
"properties": {
"domain": {
"description": "Domain to check at its HTTPS root, including any advertised MCP server.",
"type": "string"
},
"expect": {
"description": "Optional pay_to, max_amount, asset and network strings. max_amount is an integer in the asset's atomic units, compared separately for every offer.",
"type": "object"
},
"method": {
"description": "GET (default) or POST. Empty POST only after the GET shows a payment challenge or the site's OpenAPI declares a paid POST.",
"type": "string"
},
"url": {
"description": "Public paid endpoint or MCP URL. Supply url or domain. Per-call x402 requires url.",
"type": "string"
}
},
"required": [],
"type": "object"
},
"name": "prepay_check",
"outputSchema": null
},
{
"description": "Domain registration data from RDAP. Use when a task needs when a domain was registered or expires, which registrar holds it, its nameservers and registry status codes, from the registry's own RDAP service rather than a scraped WHOIS page. Contact details of people are omitted. Cost: 1 credit per call.",
"inputSchema": {
"properties": {
"domain": {
"description": "The registered domain, such as example.com. A URL is accepted and its host is used; www. is dropped, and a subdomain is reported under parent_registered.",
"type": "string"
}
},
"required": [
"domain"
],
"type": "object"
},
"name": "rdap_lookup",
"outputSchema": null
},
{
"description": "robots.txt check for a user agent and URL. Use when a task needs to know whether a given crawler or agent may fetch a given URL under the site's robots.txt, and which rule decided it. Parsed by RFC 9309 with longest-match precedence. Robots rules are a request from the site, not access control. Cost: 1 credit per call.",
"inputSchema": {
"properties": {
"url": {
"description": "The public http(s) URL the agent wants to fetch.",
"type": "string"
},
"user_agent": {
"description": "The robots.txt product token, such as GPTBot or ClaudeBot: letters, hyphen and underscore only, not a full browser string.",
"type": "string"
}
},
"required": [
"url",
"user_agent"
],
"type": "object"
},
"name": "robots_check",
"outputSchema": null
},
{
"description": "Pre-payment signals for a seller. Use when an agent is about to pay a seller it has not dealt with and wants plain signals first: domain age from RDAP, whether HTTPS works, DNS and email authentication, whether a payTo address is well formed, and whether the site publishes terms and a refund policy. Signals only: not a guarantee, not legal or financial advice. Cost: 3 credits per call.",
"inputSchema": {
"properties": {
"domain": {
"description": "The seller's domain. A URL is accepted and its host is used. Use the seller's main domain where you can: a subdomain or a shop on a shared platform gives a less complete answer, because the registry only knows its parent.",
"type": "string"
},
"network": {
"description": "The CAIP-2 network for pay_to, such as eip155:8453.",
"type": "string"
},
"pay_to": {
"description": "The address the agent has been asked to pay. Format checked only.",
"type": "string"
}
},
"required": [
"domain"
],
"type": "object"
},
"name": "seller_check",
"outputSchema": null
},
{
"description": "Spreadsheet builder. Use when a task has to hand back a real spreadsheet rather than a wall of rows: typed columns (text, number, date, currency, percent) with number formats applied, a bold header, optional frozen header row, column widths and an autofilter, returned as a base64 .xlsx or .csv. Up to 10 sheets and 50,000 cells in total (the header row counts). Values that could be read back as formulas are neutralised. Dates go in as YYYY-MM-DD or YYYY-MM-DDTHH:MM:SS; percent cells store a fraction (0.15 is 15%) unless the column sets percent_basis to \"percent\". CSV takes one sheet. Cost: 1 credit per call.",
"inputSchema": {
"properties": {
"format": {
"description": "xlsx (default) or csv. CSV takes one sheet.",
"type": "string"
},
"sheets": {
"description": "Up to 10 sheets. Each has a name, a columns list and an optional rows list, plus freeze_header and autofilter flags.",
"items": {
"properties": {
"autofilter": {
"description": "Add an autofilter to the header row.",
"type": "boolean"
},
"columns": {
"description": "Each column: key, label and type (text, number, date, currency, percent), with optional width and percent_basis.",
"type": "array"
},
"freeze_header": {
"description": "Freeze the header row.",
"type": "boolean"
},
"name": {
"description": "The sheet name, up to 31 characters and unique in the workbook.",
"type": "string"
},
"rows": {
"description": "Each row is an object keyed by column key. Up to 50,000 cells in total, header row included.",
"type": "array"
}
},
"required": [
"name",
"columns"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"sheets"
],
"type": "object"
},
"name": "sheets_build",
"outputSchema": null
},
{
"description": "Read a sitemap or sitemap index. Use when a task needs the list of URLs a site publishes, from an XML, gzipped XML or plain-text sitemap or a sitemap index, with lastmod where the site gives it and hard caps so a huge file cannot flood the agent. Cost: 1 credit per call.",
"inputSchema": {
"properties": {
"expand_index": {
"description": "Also read up to 5 child sitemaps of an index on the same site, at most 2 MiB each. Off by default.",
"type": "boolean"
},
"limit": {
"description": "Most entries to return, 1 to 5000. Defaults to 200.",
"type": "integer"
},
"url": {
"description": "The sitemap URL, or a site root to find it through robots.txt and then /sitemap.xml.",
"type": "string"
}
},
"required": [
"url"
],
"type": "object"
},
"name": "sitemap_read",
"outputSchema": null
},
{
"description": "Subtitle tools: convert, retime, merge and read caption files. Use when a task involves a subtitle or caption file: converting between SubRip (.srt), WebVTT (.vtt), ASS/SSA and YouTube SBV, shifting timings or rescaling them for a frame-rate change (23.976 to 25 and back), merging several files onto one timeline, pulling a plain-text transcript out of captions, or reporting a file's cue count, duration and reading speed. The converted file comes back in result_text; the info operation leaves result_text empty and answers in the info block. Send the file as text, as a public URL, or as base64 up to 4 MB. Cost: 1 credit per call.",
"inputSchema": {
"properties": {
"file_base64": {
"description": "The caption file as base64, up to 4 MB.",
"type": "string"
},
"files": {
"description": "The files to merge onto one timeline. merge only.",
"type": "array"
},
"from_format": {
"description": "auto (default), srt, vtt, ass or sbv.",
"type": "string"
},
"merge_gap_seconds": {
"description": "Gap to leave between files, for operation merge.",
"type": "number"
},
"offset_seconds": {
"description": "Seconds to shift every cue, for operation shift.",
"type": "number"
},
"operation": {
"description": "convert (default), shift, merge, to_text or info.",
"type": "string"
},
"scale": {
"description": "Timing multiplier for a frame-rate change, for operation shift.",
"type": "number"
},
"strip_tags": {
"description": "Drop styling tags from the cue text.",
"type": "boolean"
},
"text": {
"description": "The caption file as text. Not allowed with operation merge.",
"type": "string"
},
"to_format": {
"description": "srt, vtt, ass or sbv. Required for convert; refused for info and to_text.",
"type": "string"
},
"url": {
"description": "A public http(s) URL to read the caption file from.",
"type": "string"
}
},
"required": [],
"type": "object"
},
"name": "subtitle_tools",
"outputSchema": null
},
{
"description": "Tech Stack lookup. Use when a task depends on what a website is built with: CMS, ecommerce platform, hosting, analytics, ad pixels, payments, chat or forms. Cost: 1 credit per call.",
"inputSchema": {
"properties": {
"url": {
"description": "The public http(s) page to look up. A bare domain is treated as https://.",
"type": "string"
}
},
"required": [
"url"
],
"type": "object"
},
"name": "techstack",
"outputSchema": null
},
{
"description": "Text and JSON compare. Use when a task needs to know exactly what changed between two versions of a text, document, config file or JSON payload: line, word or character changes with a unified patch, or a JSON Pointer list of structural changes. Inputs are capped at 1,000,000 characters a side and 1,500,000 combined; lines and words mode handle that whole range, while chars mode on a heavily rewritten document falls back to block-level changes (coarse: true in the response) rather than taking longer. Cost: 1 credit per call.",
"inputSchema": {
"properties": {
"a": {
"description": "The first version. Up to 1,000,000 characters.",
"type": "string"
},
"b": {
"description": "The second version. a and b together are capped at 1,500,000 characters.",
"type": "string"
},
"context_lines": {
"description": "Lines of context in the unified patch, 0-20.",
"type": "integer"
},
"ignore_case": {
"description": "Compare without case.",
"type": "boolean"
},
"ignore_whitespace": {
"description": "Treat runs of whitespace as equal.",
"type": "boolean"
},
"mode": {
"description": "lines (default), words, chars or json.",
"type": "string"
}
},
"required": [
"a",
"b"
],
"type": "object"
},
"name": "text_diff",
"outputSchema": null
},
{
"description": "Text Stats: words, characters, tokens and SMS segments. Use when a task needs counts for a piece of text: words, user-perceived characters, bytes, sentences, paragraphs, lines, reading or speaking time, OpenAI token counts, SMS segments, or a check against length limits such as a character, word, SMS or prompt-token budget. Cost: 1 credit per call.",
"inputSchema": {
"properties": {
"limits": {
"description": "Up to 20 budgets to check the text against. Each is { name, max, unit } where unit is characters, words, tokens_o200k, tokens_cl100k, bytes or sms_segments.",
"type": "array"
},
"text": {
"description": "The text to count. Up to 200,000 UTF-16 code units. Whitespace-only text is valid and counts zero words.",
"type": "string"
}
},
"required": [
"text"
],
"type": "object"
},
"name": "text_stats",
"outputSchema": null
},
{
"description": "Read a page as Markdown. Use when a task needs the readable text of one web page instead of its HTML: an article, a documentation page, a changelog or a product page, returned as Markdown with its headings, lists, tables and code blocks intact, plus the page's title, byline, language and links. Cost: 1 credit per call.",
"inputSchema": {
"properties": {
"include_images": {
"description": "Return the page's images as a list. Off by default.",
"type": "boolean"
},
"include_links": {
"description": "Return the page's links as a list. On by default.",
"type": "boolean"
},
"max_chars": {
"description": "Cap on the Markdown returned, from 1,000 to 200,000 characters. Defaults to 50,000.",
"type": "integer"
},
"url": {
"description": "The public http(s) page to read.",
"type": "string"
}
},
"required": [
"url"
],
"type": "object"
},
"name": "url_markdown",
"outputSchema": null
},
{
"description": "Inspect an x402 payment offer without paying. Use when an agent is about to pay an HTTP 402 resource and needs to see the x402 offers first: network, asset, price in dollars for recognised USD stablecoins, payTo, scheme, and any malformed field. No payment is signed or sent. Cost: 1 credit per call.",
"inputSchema": {
"properties": {
"method": {
"description": "GET (the default) or POST. A POST is sent only when a GET of the same URL already answered with a payment challenge, or the site's own /openapi.json declares a paid POST at that path, and always with an empty body. Otherwise the GET's answer is returned and post_skipped is true.",
"type": "string"
},
"url": {
"description": "The public http(s) resource to inspect.",
"type": "string"
}
},
"required": [
"url"
],
"type": "object"
},
"name": "x402_inspect",
"outputSchema": null
}
]
}Verify it yourself
curl -s https://api.teppi.xyz/v1/evidence/sha256:b2958b47abf46ef42a4aee04ea31179546aca08683bcc6b311ae53dc3e903776 | sha256sum