Endpoints: 28,729MCP servers: 18,413Payout addresses: 2,071Paid calls: 1,536Letters: 14Defects: 1,322counted 1 min ago
teppi

Server definition

Hash
sha256:078ba58e599368081c23277165ed1c61ade130b6a67bccfeb95fa9eae5f6bb1a
What it is
What a remote MCP server returned when asked what it offers: 4 tools

The blob, as servednamed by its sha256

{ "instructions": "Antevo Trademark watches the trademark registers for conflicts, copycats and lookalike filings. Use these tools to screen a name, read who holds a mark, see what is closing, and follow an adversary. Everything is read from public registers: it is intelligence, not legal advice, and the user's counsel acts on it. Never present a deadline as certain — always say their counsel confirms it. It does not advise whether to sue, oppose or settle — that is for their counsel. It cannot file, oppose or renew a mark on anyone's behalf: say so, and point to the office or counsel. It covers trademarks only, not share prices, company financials or other markets.", "tools": [ { "description": "Who a holder is and how they file — the read on an adversary. Free.\n\n Computed from their whole register book: how much of it they let lapse, whether\n their marks cluster where they trade or spray across unrelated classes, and the\n leverage that gives counsel. Present the evidence, not just the label — and never\n call anyone a squatter; that is a legal conclusion we do not assert.\n ", "inputSchema": { "properties": { "name": { "title": "Name", "type": "string" } }, "required": [ "name" ], "title": "holder_readArguments", "type": "object" }, "name": "holder_read", "outputSchema": null }, { "description": "How long you have to oppose a filing in a given trademark office, and from when.\n\n Twenty registers, each with the provision the window comes from. The trap this\n answers: most offices run opposition BEFORE registration, from publication of the\n application, but a minority — Switzerland, Germany, Japan, Sweden — register the\n mark first and run the window from publication of the REGISTRATION. Applying one\n office's rule to another invents a deadline that never existed.\n\n Accepts a country name, an office name or a two-letter code ('japan', 'JP', 'EU').\n ", "inputSchema": { "properties": { "office": { "title": "Office", "type": "string" } }, "required": [ "office" ], "title": "opposition_windowArguments", "type": "object" }, "name": "opposition_window", "outputSchema": null }, { "description": "Screen a brand name against the live trademark registers. Free, no account.\n\n Returns every mark near it with a similarity tier, plus which registers were\n checked. This is the first thing to run when someone asks 'is my name taken'.\n ", "inputSchema": { "properties": { "mark": { "title": "Mark", "type": "string" } }, "required": [ "mark" ], "title": "screen_markArguments", "type": "object" }, "name": "screen_mark", "outputSchema": null }, { "description": "Which Nice classes a business like this files in. Free, no account, no database.\n\n The question people cannot answer for themselves: not \"is my name taken\" but\n \"taken in WHAT\". Nice has 45 classes and the numbering is opaque — software you\n download is class 9, software you log into is class 42, and selling other people's\n goods is class 35 whatever the goods are. Filing in one and not the other is the\n most expensive routine mistake in the process.\n\n Run this BEFORE screen_mark when someone describes a business rather than naming a\n class: the classes it returns are what makes a screen mean anything. Relay the\n reasoning, not just the numbers, and keep the closing caveat — this reports how\n similar businesses file, and their counsel decides what they actually file.\n ", "inputSchema": { "properties": { "description": { "title": "Description", "type": "string" } }, "required": [ "description" ], "title": "suggest_classesArguments", "type": "object" }, "name": "suggest_classes", "outputSchema": null } ] }
Verify it yourselfcurl -s https://api.teppi.xyz/v1/evidence/sha256:078ba58e599368081c23277165ed1c61ade130b6a67bccfeb95fa9eae5f6bb1a | sha256sum