{"server":"ai.openmark/openmark","count":7,"tools":[{"name":"get_account","title":"Account, credits and plans","description":"The user's plan, credit balance and limits, and what a credit pack, Pro or Expert would unlock. Use it before large runs, or when a run is refused for credits or limits.","input_schema":{"type":"object","properties":{}},"output_schema":null,"annotations":null,"source":"probe","observed_at":"2026-10-18T21:29:54.286Z"},{"name":"get_results","title":"Get benchmark results","description":"Status of a benchmark job, and once completed the ranked results (score, stability, cost per run, latency) plus a recommendation for the chosen objective and quick picks for the others.","input_schema":{"type":"object","required":["job_id"],"properties":{"job_id":{"type":"string"},"tolerance":{"type":"number","default":2,"maximum":50,"minimum":0,"description":"Score points below the top score that still count as good enough"},"optimize_for":{"enum":["accuracy","cost","speed","stability"],"type":"string","default":"accuracy","description":"accuracy: best score, cheapest on ties. cost / speed / stability: cheapest / fastest / most consistent model within `tolerance` points of the top score"}}},"output_schema":null,"annotations":null,"source":"probe","observed_at":"2026-10-18T21:29:54.286Z"},{"name":"get_task_format","title":"Task YAML format","description":"How to write an OpenMark task: the YAML structure, every scoring mode, and tips. Call this before writing a task.","input_schema":{"type":"object","properties":{}},"output_schema":null,"annotations":null,"source":"probe","observed_at":"2026-10-18T21:29:54.286Z"},{"name":"list_models","title":"List models","description":"Current OpenMark model ids with list prices ($ per 1M tokens). Use these ids in run_benchmark. Append @low, @medium or @high to a reasoning model id to set its reasoning effort.","input_schema":{"type":"object","properties":{"search":{"type":"string","description":"Filter by id, name or provider, e.g. 'claude', 'gemini flash'"},"images_only":{"type":"boolean","description":"Only models that accept image attachments"},"max_output_price":{"type":"number","description":"Only models at or below this $ per 1M output tokens"}}},"output_schema":null,"annotations":null,"source":"probe","observed_at":"2026-10-18T21:29:54.286Z"},{"name":"prepare_attachments","title":"Prepare file attachments","description":"Get an upload_uid and the exact command to upload images, PDFs or text documents for a task. Upload the files, reference them by file name in each test's attachments list, then pass the upload_uid to run_benchmark.","input_schema":{"type":"object","properties":{"file_names":{"type":"array","items":{"type":"string"},"maxItems":20,"description":"Optional: the local file paths to upload, to get a ready-to-run command"}}},"output_schema":null,"annotations":null,"source":"probe","observed_at":"2026-10-18T21:29:54.286Z"},{"name":"run_benchmark","title":"Run a benchmark","description":"Save a task (YAML, see get_task_format) to the user's OpenMark account and run it on the given models with real API calls. Returns a job_id; poll get_results. Spends the user's credits.","input_schema":{"type":"object","required":["task_yaml","models"],"properties":{"models":{"type":"array","items":{"type":"string"},"maxItems":20,"minItems":1,"description":"Model ids from list_models"},"task_yaml":{"type":"string","description":"The full task YAML (a JSON object with the same fields also works)"},"upload_uid":{"type":"string","description":"From prepare_attachments, when tests use attachments"},"stability_runs":{"type":"integer","default":2,"maximum":3,"minimum":1,"description":"Passes per model; 2+ shows which models are consistent"}}},"output_schema":null,"annotations":null,"source":"probe","observed_at":"2026-10-18T21:29:54.286Z"},{"name":"watch_task","title":"Watch a task for better models","description":"Watch the task of a completed job: OpenMark re-tests it on new or cheaper models as they ship (no credits used) and emails the user only when one beats the best model of that job.","input_schema":{"type":"object","required":["job_id"],"properties":{"job_id":{"type":"string"}}},"output_schema":null,"annotations":null,"source":"probe","observed_at":"2026-10-18T21:29:54.286Z"}],"next_cursor":null,"next_actions":[{"action":"get_connection","description":"Connection block to call these tools","href":"/v1/servers/ai.openmark%2Fopenmark/connection?target=mcpServers","arguments":{"name":"ai.openmark/openmark","target":"mcpServers"}},{"action":"get_server","description":"Full descriptor with trust and connectability","href":"/v1/servers/ai.openmark%2Fopenmark","arguments":{"name":"ai.openmark/openmark"}}]}