{"data":{"name":"com.grain64.clearbar/verdicts","title":"Clearbar model verdicts","description":"Cheapest LLM that passes each task: cost per successful task and pass rate on public datasets.","version":"1.0.0","websiteUrl":"https://clearbar.grain64.com/docs/#mcp","repositoryUrl":null,"remotes":[{"type":"streamable-http","url":"https://clearbar.grain64.com/mcp"}],"packages":[],"status":"active","isLatest":true,"publishedAt":"2026-11-06T11:17:05.084Z","updatedAt":"2026-11-06T11:17:05.084Z","source":"official-registry","verification":"official","confidence":100,"stars":null,"sources":[{"source":"official-registry","sourceId":"com.grain64.clearbar/verdicts","verification":"official","confidence":100,"stars":null,"updatedAt":"2026-11-06T11:17:05.084Z","title":"Clearbar model verdicts","description":"Cheapest LLM that passes each task: cost per successful task and pass rate on public datasets.","websiteUrl":"https://clearbar.grain64.com/docs/#mcp","repositoryUrl":null}],"toolIndex":{"tools":[{"serverName":"com.grain64.clearbar/verdicts","endpointFingerprint":"c5a4dcdd75c6185ae9c25e36760c5374212a4cab09ad5b785c99dd2ac1e9f72f","name":"cheapest_model","title":"Cheapest model that still passes, per task, in one call","description":"One call, the headline answer: which is the cheapest LLM that still passes? With no arguments you get every task family (classification, extraction, tool-call) with its cheapest passing model, cost per successful task in US dollars (retries and failures counted), how much cheaper it is than the baseline, and the verdict page that proves it. Pass {\"task\":\"spam detection\"} (plain words, or a family such as classification) for just that answer. Next call: get_verdict with the slug for the full candidate table, failures and the re-run script.","inputSchema":{"type":"object","properties":{"task":{"type":"string","description":"Optional. The task in plain words (spam detection, sentiment, json extraction, tool calling) or a family: classification, extraction, tool-call."}},"additionalProperties":false},"annotations":{"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false},"definitionHash":"67c276c64a17c0f8d27e79c7870791ab0f542832467c675bc6642c2b58dc6879","schemaStatus":"valid","origin":"official-registry","observedAt":"2026-11-19T17:46:33.165Z","metadataTrust":"untrusted"},{"serverName":"com.grain64.clearbar/verdicts","endpointFingerprint":"c5a4dcdd75c6185ae9c25e36760c5374212a4cab09ad5b785c99dd2ac1e9f72f","name":"get_verdict","title":"Get one verdict: cheapest passing model, cost, failures","description":"Answers: which is the cheapest LLM that still passes for <task>? Give the task in plain words (for example \"spam detection\", \"sentiment\", \"json extraction\", \"tool calling\", \"intent classification\") or a verdict slug, and get the cheapest model that clears the bar, its pass rate and cost per successful task in US dollars, the baseline it is compared with, every candidate's status, plus links to the verdict page, the run file (JSON) and the script that re-runs it. Example: {\"task\":\"spam detection\"} returns the sms-spam verdict. Not sure what exists? Call list_verdicts first.","inputSchema":{"type":"object","properties":{"task":{"type":"string","minLength":1,"description":"The task in plain words, for example spam detection, sentiment, json extraction. The closest published verdict answers."},"slug":{"type":"string","minLength":1,"description":"Or the exact verdict slug from list_verdicts, for example sms-spam."}},"additionalProperties":false},"annotations":{"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false},"definitionHash":"7b716b54823c35507af5a2d0848dfd1ecef5984a6830c63a88d74c40396a2f2a","schemaStatus":"valid","origin":"official-registry","observedAt":"2026-11-19T17:46:33.165Z","metadataTrust":"untrusted"},{"serverName":"com.grain64.clearbar/verdicts","endpointFingerprint":"c5a4dcdd75c6185ae9c25e36760c5374212a4cab09ad5b785c99dd2ac1e9f72f","name":"list_verdicts","title":"List verdicts: which model is cheapest for each task","description":"Which LLM is the cheapest that still passes? Lists every published Clearbar verdict at once: the task, the pass bar, the cheapest passing model, its cost per successful task (retries and failures counted) and the page to check it. Optional filter by task type. Next call: get_verdict with {\"task\":\"spam detection\"} (or a slug from this list) for the full table.","inputSchema":{"type":"object","properties":{"task":{"type":"string","description":"Only verdicts of this task type, for example classification, extraction or tool-call."}},"additionalProperties":false},"annotations":{"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false},"definitionHash":"d5ab911c3882b9205fbce03dfd2e747b10e1b0611687579f54e76bae1e101359","schemaStatus":"valid","origin":"official-registry","observedAt":"2026-11-19T17:46:33.165Z","metadataTrust":"untrusted"}],"endpoints":[{"endpointFingerprint":"c5a4dcdd75c6185ae9c25e36760c5374212a4cab09ad5b785c99dd2ac1e9f72f","protocol":"streamable-http","status":"indexed","toolCount":3,"observedAt":"2026-11-19T17:46:33.165Z"}],"authentication":"unknown"},"connectionConfigurations":{"status":"ready","authentication":"not embedded","clients":{"Claude Desktop":{"mcpServers":{"com.grain64.clearbar/verdicts":{"url":"https://clearbar.grain64.com/mcp"}}},"Cursor":{"mcpServers":{"com.grain64.clearbar/verdicts":{"url":"https://clearbar.grain64.com/mcp"}}},"VS Code":{"servers":{"com.grain64.clearbar/verdicts":{"type":"http","url":"https://clearbar.grain64.com/mcp"}}}}},"resourceType":"mcp-server","callable":true,"runtime":{"callable":true,"protocols":["mcp"]},"interfaces":[{"protocol":"mcp","transport":"streamable-http","url":"https://clearbar.grain64.com/mcp"}],"profile":{"apiVersion":"1","schemaVersion":"1","id":"mcp-server:com.grain64.clearbar%2Fverdicts","resourceType":"mcp-server","canonicalUrl":"https://www.agentsjunction.com/api/v1/servers/com.grain64.clearbar%2Fverdicts","name":"com.grain64.clearbar/verdicts","description":"Cheapest LLM that passes each task: cost per successful task and pass rate on public datasets.","interfaces":[{"protocol":"mcp","transport":"streamable-http","url":"https://clearbar.grain64.com/mcp"}],"capabilities":[],"identity":{"source":"official-registry","websiteUrl":"https://clearbar.grain64.com/docs/#mcp","repositoryUrl":null,"version":"1.0.0"},"verification":{"state":"official","confidence":100},"operations":{"resourceType":"mcp-server","name":"com.grain64.clearbar/verdicts","status":"online","lastCheckedAt":"2026-11-20T07:16:27.742Z","lastSuccessfulCheck":"2026-11-20T07:16:27.742Z","latencyMs":489,"consecutiveFailures":0,"isStale":false,"checks":{"endpointReachable":true,"protocolValid":true,"agentCardValid":null,"mcpHandshakeValid":true},"lastSeen":null,"lastSuccessfulInteraction":null,"lastHealthCheck":"2026-11-20T07:16:27.742Z","source":{"type":"health-check","url":null},"observedAt":"2026-11-20T07:16:27.742Z"},"security":null,"timestamps":{"createdAt":"2026-11-06T11:17:05.084Z","updatedAt":"2026-11-06T11:17:05.084Z","observedAt":"2026-11-20T07:16:27.742Z"},"compatibility":{"serverVersion":"1.0.0","protocolVersions":[{"protocol":"mcp","version":null}]}}}}