{"slug":"agentrank","domain":"web","title":"What agents call: usage from the platforms that run the tools","summary":"Calls and calling accounts per tool on Monid, MCP server use on Smithery, users and runs per tool on Apify, MCP image pulls on Docker, and which tools AI assistants recommend.","help":"agentrank: agent tool usage, as the platforms that run or route it count it.\n\nWHAT IT IS\n  A download counts an install and a visit counts a person. Neither counts an\n  agent at work. The platforms that run or route tools do:\n    monid     calls and calling accounts per provider and endpoint\n    smithery  the use count of each MCP server it lists or hosts\n    apify     users (7 and 30 days, total) and runs (30 days) per store tool\n    docker    all-time pulls of each MCP server image in Docker's catalog\n    answers   asks ChatGPT, Perplexity, Gemini, AI Mode and Copilot a question\n    answer    reads one assistant's answer, and which of your tools it names first\n\nASK, THEN READ\n  An assistant takes 20 to 60 seconds and they answer one at a time, so\n  `answers` returns at once with a task id per assistant. Read each with\n  `agentrank answer \u003ctask\u003e --tools A,B,C`: QUEUED or PROCESSING means wait and\n  read again; COMPLETED carries the answer. A task is kept for 24 hours.\n\nANSWERS ARE READINGS, AND COST\n  Each assistant asked is one agentrank_answer on the bill; reading is free.\n  An answer is what one assistant said once: ask more than once, or several\n  questions, before calling anything a pattern. The other studies are free.\n\nONE PLATFORM, NEVER A MARKET SHARE\n  Each counts only its own traffic. Monid sees only calls routed through it; a\n  provider whose customers call its own API directly reads SMALL there however\n  big it is. Smithery counts its servers, Apify runs on Apify, Docker pulls of\n  its images (installs, not calls). Say which platform a figure is from, and\n  compare platforms side by side, never by adding them up.\n\nACCOUNTS BEFORE CALLS\n  A call counts once whatever it does, so a search an agent runs thirty times\n  a task outranks a render it runs once. `accounts` is how many accounts call an\n  endpoint; 60,000 calls from 62 accounts is a few pipelines, not adoption.\n  A provider's `accounts_at_least` is its busiest endpoint's figure — a floor.\n\nWEIGHTED, AND MOSTLY FREE\n  Monid ranks by a weighted count: a free call is a fifth of a paid one. The\n  headline gives raw and paid calls, and free_share — most traffic is free.\n  `change` is against the window before, while the platform itself grows; a\n  provider growing slower than the headline is losing share.\n\nStudies:\n  monid    \u003cview\u003e\n      calls, calling accounts and change per provider or endpoint, with the free share of all traffic\n  smithery \u003cquery\u003e\n      MCP servers matching a name, with Smithery's use count for each\n  apify    \u003climit\u003e\n      Apify Store tools with users in the last 7 and 30 days and runs in the last 30 days\n  docker   \u003climit\u003e\n      MCP server images in Docker's MCP Catalog by all-time pulls\n  answers  \u003cprompt\u003e\n      ask ChatGPT, Perplexity, Gemini, AI Mode and Copilot a question; answers come back as task ids to read with `agentrank answer` — billed per assistant\n  answer   \u003ctask\u003e\n      one assistant's answer once it is done, its sources, and which of your tools it names first\n\nJSON to stdout, so it composes: pipe to `jq` to pick a field, or `\u003e /tmp/…` to keep it.\nRun a study with no arguments — `agentrank monid` — to see what it takes.\n","example_command":"agentrank apify 25 --category SOCIAL_MEDIA","example_output":"","cost_class":"upstream-fetch","tier":"metered","billing_items":["agentrank_answer"],"price_per_1k_calls":null,"price_is_from":true,"status":"available","commands":["agentrank"],"studies":[{"call":"monid","about":"calls, calling accounts and change per provider or endpoint, with the free share of all traffic","args":[{"name":"view","positional":true,"list":false,"hint":"providers | endpoints | rising | new"},{"name":"window","positional":false,"list":false,"hint":"7d (default) | 30d"},{"name":"provider","positional":false,"list":false,"hint":"one provider, by Monid slug or name"},{"name":"category","positional":false,"list":false,"hint":"endpoints in one category, e.g. 'Web search'"},{"name":"limit","positional":false,"list":false,"hint":"rows, default 30"}]},{"call":"smithery","about":"MCP servers matching a name, with Smithery's use count for each","args":[{"name":"query","positional":true,"list":false,"hint":"a provider or server name, e.g. exa"},{"name":"limit","positional":false,"list":false,"hint":"servers, default 10"}]},{"call":"apify","about":"Apify Store tools with users in the last 7 and 30 days and runs in the last 30 days","args":[{"name":"limit","positional":true,"list":false,"hint":"actors, 1-100, most popular first, e.g. 25"},{"name":"query","positional":false,"list":false,"hint":"words to search the store for, e.g. instagram"},{"name":"category","positional":false,"list":false,"hint":"an Apify category, e.g. SOCIAL_MEDIA, LEAD_GENERATION"}]},{"call":"docker","about":"MCP server images in Docker's MCP Catalog by all-time pulls","args":[{"name":"limit","positional":true,"list":false,"hint":"images, 1-100, most pulled first, e.g. 25"}]},{"call":"answers","about":"ask ChatGPT, Perplexity, Gemini, AI Mode and Copilot a question; answers come back as task ids to read with `agentrank answer` — billed per assistant","args":[{"name":"prompt","positional":true,"list":false,"hint":"what to ask, e.g. 'best web scraping API for an AI agent'"},{"name":"engines","positional":false,"list":true,"hint":"chatgpt,perplexity,gemini,aimode,copilot (default all five)"},{"name":"country","positional":false,"list":false,"hint":"two-letter country the assistants answer from, default US"}]},{"call":"answer","about":"one assistant's answer once it is done, its sources, and which of your tools it names first","args":[{"name":"task","positional":true,"list":false,"hint":"a task id from `agentrank answers`"},{"name":"tools","positional":false,"list":false,"hint":"comma-separated tools to look for: Firecrawl,Apify,Exa"}]}],"default_enabled":false,"first_seen":"2026-10-23T05:02:16.142721Z","enabled":false}