Endpoints: 76,849MCP servers: 32,725Payout addresses: 3,825Paid calls: 6,132Letters: 84Defects: 3,888counted 2 min ago
teppi

Server definition

Hash
sha256:3c61e0933dc52cdbe46ca4c90a1853a3d7a40665bafc3b4a61689cfa48cdefcf
What it is
What a remote MCP server returned when asked what it offers: 4 tools

The blob, as servednamed by its sha256

{ "instructions": "Free daily AI pricing per right answer, for business jobs. From NL;NL Labs. Free daily AI pricing for business jobs. No paid placement or referral fees. NL;NL Labs models appear whatever their results. Use these tools for any question about NL;NL Labs' daily model tests: the jobs, which model is the pick for a job, one model's history, or every model's result on one day. Call list_jobs first for job and model names. Quote data_date and cite when you answer.", "tools": [ { "description": "Use to compare the models and systems on one job on one day. Leave date out for the newest day. Returns every model's and system's published result that day, NL;NL Labs' own models and systems marked. On a job with two tests, the answer says what they are. Extract's documents days also carry invented, missed and unreadable counts. Fields: cost_per_1000_right_usd and ipd are exact; cost_shown and ipd_shown are how the page shows them. assembled_by_us is 1 when the answer was assembled by us, else 0. A count marked \"not published for this model\" is not published for that model.", "inputSchema": { "$schema": "https://json-schema.org/draft/2020-12/schema", "additionalProperties": false, "properties": { "date": { "description": "YYYY-MM-DD. Default: newest day.", "pattern": "^\\d{4}-\\d{2}-\\d{2}$", "type": "string" }, "job": { "description": "Job id.", "enum": [ "classify", "convert", "decide", "extract", "find", "fix", "match", "resolve", "write" ], "type": "string" } }, "required": [ "job" ], "type": "object" }, "name": "get_day_results", "outputSchema": null }, { "description": "Use to follow one model on one job over time (for example, has it got cheaper or worse). Returns its published days: right answers, items, cost per 1,000 right in US dollars and IPD (right answers per dollar). On a job with two tests (Extract, Classify), every row names its test; the answer says what the two tests are and when each ran, and rows from the two tests are not comparable. Fields: cost_per_1000_right_usd and ipd are exact; cost_shown and ipd_shown are how the page shows them. assembled_by_us is 1 when the answer was assembled by us, else 0. A count marked \"not published for this model\" is not published for that model.", "inputSchema": { "$schema": "https://json-schema.org/draft/2020-12/schema", "additionalProperties": false, "properties": { "job": { "description": "Job id.", "enum": [ "classify", "convert", "decide", "extract", "find", "fix", "match", "resolve", "write" ], "type": "string" }, "model": { "description": "Model or system name for that job, e.g. GPT-6 Luna, Claude Haiku 5.5, NL;NL Desk (a system. Not open yet.).", "maxLength": 100, "type": "string" } }, "required": [ "job", "model" ], "type": "object" }, "name": "get_model_history", "outputSchema": null }, { "description": "Use it when someone asks which model to use for a job. Returns the job page's latest published pick. The pick is always an outside model: NL;NL Labs' own models and systems (NL;NL Pull, NL;NL Desk) are never the pick. When one of ours would have been the pick under the same rule, the answer adds an \"ours\" entry with its figures, marked as ours, not as the pick. Returns the model the job page shows as its pick, with the page's label and rule, the figures as the page shows them (right answers per $1, cost per 1,000 right), the pick's own date and that model's day row. Fields: cost_per_1000_right_usd and ipd are exact; cost_shown and ipd_shown are how the page shows them. assembled_by_us is 1 when the answer was assembled by us, else 0. A count marked \"not published for this model\" is not published for that model.", "inputSchema": { "$schema": "https://json-schema.org/draft/2020-12/schema", "additionalProperties": false, "properties": { "job": { "description": "Job id.", "enum": [ "classify", "convert", "decide", "extract", "find", "fix", "match", "resolve", "write" ], "type": "string" } }, "required": [ "job" ], "type": "object" }, "name": "get_pick", "outputSchema": null }, { "description": "Lists the jobs NL;NL Labs tests every day, what each one asks, what counts as right (the site's own words), the models and systems tested on each job and the dates covered. NL;NL Labs' own models are marked; NL;NL Desk is a system, not a model. Not open yet.", "inputSchema": { "properties": {}, "type": "object" }, "name": "list_jobs", "outputSchema": null } ] }
Verify it yourselfcurl -s https://api.teppi.xyz/v1/evidence/sha256:3c61e0933dc52cdbe46ca4c90a1853a3d7a40665bafc3b4a61689cfa48cdefcf | sha256sum