Endpoints: 76,849MCP servers: 32,730Payout addresses: 3,825Paid calls: 6,160Letters: 84Defects: 3,898counted just now
teppi

Server definition

Hash
sha256:2208dae289368ed95a5628fe568077e4f823b17e67a852e6697d303e2e131883
What it is
What a remote MCP server returned when asked what it offers: 3 tools

The blob, as servednamed by its sha256

{ "instructions": "You did not send an API key. If your base URL still starts with https://ai.topxea.com, replace that part with https://api.topxai.xyz: HTTP clients drop the key when a redirect leads to another domain. TopxAI Desktop users: download the new version from https://api.topxai.xyz/downloads, drag it into Applications to replace the old app, then open it and sign in again. Otherwise, sign up and create a key at https://api.topxai.xyz/mcp/connect, then send it in the Authorization header. Each ask_model call is billed to the API key's wallet at the model's normal token price plus a flat call fee of $0.001. The reply's structuredContent reports the exact charge. Pass max_cost_usd to refuse calls whose estimated cost would exceed a budget; the estimate is approximate, the recorded charge is exact.", "tools": [ { "description": "Send a prompt to one text model of the TopxAI catalogue and return its reply. The models reason before they answer and the reasoning counts toward max_output_tokens, so leave at least 4096 tokens for a full answer or pass a lower reasoning_effort. Billed at the model's token price, reasoning included, plus a $0.001 call fee; the reply reports the exact charge.", "inputSchema": { "additionalProperties": false, "properties": { "max_cost_usd": { "description": "Refuse the call, before anything is billed, when its estimated cost (prompt, max_output_tokens and the call fee) exceeds this amount.", "minimum": 0, "type": "number" }, "max_output_tokens": { "default": 8192, "description": "Upper bound on the reply, reasoning included; the reasoning itself is not returned. Below 4096 a model may stop before writing any text, and that call is still charged.", "maximum": 65536, "minimum": 1, "type": "integer" }, "model": { "description": "Model to ask; list_models shows the choices and prices.", "type": "string" }, "prompt": { "description": "The user message sent to the model. Include every piece of context the model needs; it sees nothing else.", "type": "string" }, "reasoning_effort": { "description": "Optional thinking effort. Each model takes its own set and list_models shows them with the default, which applies when this is omitted. A lower effort answers sooner and costs less; the reasoning is billed as output and counts toward max_output_tokens.", "type": "string" }, "system": { "description": "Optional system prompt.", "type": "string" }, "temperature": { "description": "Optional sampling temperature.", "maximum": 2, "minimum": 0, "type": "number" } }, "required": [ "model", "prompt" ], "type": "object" }, "name": "ask_model", "outputSchema": { "properties": { "call_fee_usd": { "type": "number" }, "charged": { "description": "Whether the wallet was debited for this call.", "type": "boolean" }, "charged_usd": { "description": "The recorded wallet debit in USD, model price and call fee included.", "type": "number" }, "error": { "description": "Present on a failed call: category (client, wallet, topxai, upstream, budget), message, charged, charged_usd.", "type": "object" }, "finish_reason": { "type": "string" }, "model": { "type": "string" }, "reasoning_effort": { "description": "The effort the call asked for; the model's default when it named none.", "type": "string" }, "request_id": { "description": "The relay request id; the same id appears in the usage log.", "type": "string" }, "route": { "type": "string" }, "usage": { "properties": { "completion_tokens": { "type": "integer" }, "prompt_tokens": { "type": "integer" } }, "type": "object" } }, "type": "object" } }, { "description": "Ask TypeSafe's Jev (a System One model) typed questions about a piece of text and get calibrated numbers back, not prose: a probability for a yes/no question (type noul), one option with a probability per option (type choice, with criteria), or a value on a scale with a probability per anchor (type score, with anchors). Billed at Jev's input-token price plus a $0.001 call fee.", "inputSchema": { "additionalProperties": false, "properties": { "model": { "description": "System One model.", "type": "string" }, "questions": { "additionalProperties": { "properties": { "instructions": { "type": "string" }, "type": { "enum": [ "noul", "choice", "score" ], "type": "string" } }, "required": [ "type", "instructions" ], "type": "object" }, "description": "Question id to typed question. Each question is {\"type\": \"noul\" | \"choice\" | \"score\", \"instructions\": \"one question a careful reader could answer from the state alone\"}. noul may add \"criteria\": {\"true\": ..., \"false\": ...}; choice adds \"criteria\": {option: description or null, ...} (a plain list of option names is accepted too); score adds \"criteria\": [level description, ...] with 2 to 10 ordered levels.", "minProperties": 1, "type": "object" }, "state": { "description": "The text the questions are about: a ticket, a log excerpt, a document, a transcript.", "type": "string" } }, "required": [ "state", "questions" ], "type": "object" }, "name": "judge", "outputSchema": { "properties": { "answers": { "additionalProperties": { "type": "object" }, "description": "Question id to answer: {type, noul} for a probability, {type, choice, confidence, probabilities} for a choice, {type, score, confidence, probabilities} for a score.", "type": "object" }, "call_fee_usd": { "type": "number" }, "charged": { "description": "Whether the wallet was debited for this call.", "type": "boolean" }, "charged_usd": { "description": "The recorded wallet debit in USD, model price and call fee included.", "type": "number" }, "error": { "description": "Present on a failed call: category (client, wallet, topxai, upstream, budget), message, charged, charged_usd.", "type": "object" }, "model": { "type": "string" }, "request_id": { "description": "The relay request id; the same id appears in the usage log.", "type": "string" }, "route": { "type": "string" }, "usage": { "properties": { "input_tokens": { "type": "integer" } }, "type": "object" } }, "type": "object" } }, { "description": "List the text models this API key can ask, with their USD prices per million tokens, the reasoning efforts each takes and the call fee.", "inputSchema": { "additionalProperties": false, "properties": {}, "type": "object" }, "name": "list_models", "outputSchema": { "properties": { "call_fee_usd": { "type": "number" }, "models": { "items": { "properties": { "backup_cache_read_usd_per_million_tokens": { "description": "The cache-read price of a call the backup deployment answers.", "type": "number" }, "backup_cache_write_usd_per_million_tokens": { "description": "Only when the backup deployment bills cache writes: the cache-write price of a call it answers.", "type": "number" }, "backup_input_usd_per_million_tokens": { "description": "Only on a model with a backup deployment: the input price of a call the backup deployment answers, which happens only if the main deployment fails before answering.", "type": "number" }, "backup_output_usd_per_million_tokens": { "description": "The output price of a call the backup deployment answers.", "type": "number" }, "cache_read_usd_per_million_tokens": { "type": "number" }, "default_reasoning_effort": { "description": "The effort a call without reasoning_effort runs at.", "type": "string" }, "input_usd_per_million_tokens": { "type": "number" }, "model": { "type": "string" }, "output_usd_per_million_tokens": { "type": "number" }, "reasoning_efforts": { "description": "The reasoning_effort values ask_model accepts for this model.", "items": { "type": "string" }, "type": "array" }, "route": { "type": "string" }, "unit": { "type": "string" } }, "type": "object" }, "type": "array" } }, "type": "object" } } ] }
Verify it yourselfcurl -s https://api.teppi.xyz/v1/evidence/sha256:2208dae289368ed95a5628fe568077e4f823b17e67a852e6697d303e2e131883 | sha256sum