Endpoints: 28,729MCP servers: 18,413Payout addresses: 2,071Paid calls: 1,551Letters: 14Defects: 1,323counted 2 min ago
teppi

Server definition

Hash
sha256:ff4fff1236bd6901f4910c7949bac9e10b2a0fba69c785f39cca8329044bee93
What it is
What a remote MCP server returned when asked what it offers: 3 tools

The blob, as servednamed by its sha256

{ "instructions": "Ask this server why a fetch was refused and what to do about it.\n\n`access_check_url` is the main tool: it reads the origin's robots.txt, its AI-preference\ndirectives, any licence it links, and the live response to an honestly-identified request,\nand returns a verdict with the evidence behind it. The verdict that matters is\n`allowed_if_identified`: the site's written policy permits the fetch and the refusal came\nfrom bot management, which means identifying and signing as a named crawler is a documented\nroute to the content rather than a guess.\n\nEvery answer carries a `next` field, `{ what, url, why }` or null: when a tool we publish\ntoday closes the gap the verdict names — the signing library for an `allowed_if_identified`\nURL — `next` names it; on every other verdict it is null.\n\nThis server never evades anything and never impersonates another operator's crawler. The\nper-agent answers come from what the origin declared, not from testing with a borrowed\nuser-agent. If robots.txt disallows this index, it says so and does not fetch the page.", "tools": [ { "description": "Given a URL, say whether an AI agent may fetch it, on what terms, and at what price.\nReads robots.txt for a generic agent and for every AI user-agent the operators document,\nthe Content-signal and Content-Usage directives, any RSL licence the origin links, and\nthe live response to an honestly-identified request.\n\nVerdicts: `allowed` (it served us), `allowed_if_identified` (the written policy permits\nthis but bot management refused an anonymous request — signing as a named crawler is the\ndocumented route), `charged` (there is a price, quoted where the rail will show one),\n`blocked` (the site disallows the agents that would want this, with nothing to buy), and\n`unknown` (the origin did not answer, or the URL is not there).\n\nNever evades: no CAPTCHA solving, no proxies, no spoofed user-agents. Refusals come back\nas findings with the evidence attached.", "inputSchema": { "$schema": "https://json-schema.org/draft/2020-12/schema", "additionalProperties": false, "properties": { "includeEvidence": { "description": "Include every request made, with status and headers (default false: it is large)", "type": "boolean" }, "skipWellKnown": { "description": "Skip the five well-known probes; faster, and they are almost always absent", "type": "boolean" }, "url": { "description": "Absolute http(s) URL of the page to check, e.g. https://example.com/article", "format": "uri", "type": "string" } }, "required": [ "url" ], "type": "object" }, "name": "access_check_url", "outputSchema": null }, { "description": "Return the five verdicts this index can return, what each one means for an agent that has just been refused, and what the agent's next move is for each. Costs nothing and makes no request; call it once to interpret access_check_url results.", "inputSchema": { "$schema": "https://json-schema.org/draft/2020-12/schema", "additionalProperties": false, "properties": {}, "type": "object" }, "name": "access_explain_verdicts", "outputSchema": null }, { "description": "Return the AI crawler tokens this index reads robots.txt rules for — only tokens their operators document — plus the widely-written tokens that no operator sends, which make a robots rule unenforceable. Useful when writing or auditing a robots.txt.", "inputSchema": { "$schema": "https://json-schema.org/draft/2020-12/schema", "additionalProperties": false, "properties": {}, "type": "object" }, "name": "access_list_agents", "outputSchema": null } ] }
Verify it yourselfcurl -s https://api.teppi.xyz/v1/evidence/sha256:ff4fff1236bd6901f4910c7949bac9e10b2a0fba69c785f39cca8329044bee93 | sha256sum