{"data":{"name":"dev.aicomputeradar/ai-compute-radar","title":"AI Compute Radar","description":"Which open models fit your GPU or Mac, measured. Model momentum, GPU rental prices, weekly pick.","version":"1.2.3","websiteUrl":"https://aicomputeradar.dev/developers","repositoryUrl":null,"remotes":[{"type":"streamable-http","url":"https://aicomputeradar.dev/api/mcp"}],"packages":[{"registryType":"npm","identifier":"ai-compute-radar","version":"1.2.1","runtimeHint":"stdio","runtimeArguments":null,"environmentVariables":null}],"status":"active","isLatest":true,"publishedAt":"2026-10-27T17:17:24.765Z","updatedAt":"2026-10-27T17:17:24.765Z","source":"official-registry","verification":"official","confidence":100,"stars":null,"sources":[{"source":"official-registry","sourceId":"dev.aicomputeradar/ai-compute-radar","verification":"official","confidence":100,"stars":null,"updatedAt":"2026-10-27T17:17:24.765Z","title":"AI Compute Radar","description":"Which open models fit your GPU or Mac, measured. Model momentum, GPU rental prices, weekly pick.","websiteUrl":"https://aicomputeradar.dev/developers","repositoryUrl":null}],"toolIndex":{"tools":[{"serverName":"dev.aicomputeradar/ai-compute-radar","endpointFingerprint":"00de53d7703d074381f989860ca63872740c0c4d3aa3772f7a1274bc885b981e","name":"find_fit","title":"Find models that fit a machine","description":"Which tracked models run on a given GPU or Mac: measured GGUF weights + computed context cache + runtime overhead versus usable memory. Returns the best recommendation and every verdict (EXCELLENT/GOOD/TIGHT/OFFLOAD_REQUIRED/NOT_RECOMMENDED/UNKNOWN) with plain-language reasons. Get hardware ids from list_hardware.","inputSchema":{"type":"object","properties":{"hardware":{"type":"string","description":"Hardware id or page slug, e.g. rtx-4090, mac-studio-m3-ultra-96gb."},"model":{"description":"Restrict to one model slug.","type":"string"},"context":{"description":"Context length in tokens (default 8192).","type":"integer","minimum":512,"maximum":1048576},"kv":{"description":"KV-cache quantization (default f16).","type":"string","enum":["f16","q8_0","q4_0"]}},"required":["hardware"],"$schema":"https://json-schema.org/draft/2020-12/schema"},"annotations":null,"definitionHash":"4159c63e6c5987bfb3e5615088df23d8441ddfbc4d072078e247efb7abb938e2","schemaStatus":"valid","origin":"official-registry","observedAt":"2026-11-17T17:46:40.012Z","metadataTrust":"untrusted"},{"serverName":"dev.aicomputeradar/ai-compute-radar","endpointFingerprint":"00de53d7703d074381f989860ca63872740c0c4d3aa3772f7a1274bc885b981e","name":"gpu_prices","title":"GPU rental prices","description":"Median verified on-demand rental price per GPU class on Vast.ai (USD per hour), with min/p75 and offer counts, the collection timestamp, and per class the Rent Index: this week's median against last week and against the first week collected, a trend word, and the days excluded as marketplace glitches, plus RunPod's lowest posted on-demand price per class (a list price, not a median), Clore.ai's median for the same class (a second marketplace, never blended), and the AWS, Azure and Oracle Cloud pay-as-you-go list prices per GPU-hour, each with the instance type, VM size or bare-metal shape the price sits in (list prices, read four times a day, no statement about capacity). The index describes what prices did; it never forecasts.","inputSchema":{"type":"object","properties":{},"$schema":"https://json-schema.org/draft/2020-12/schema"},"annotations":null,"definitionHash":"4dc8079f5fd3a1397ff12d0d77c93e932c8eab6eff29eb80b4c3ed8458375f28","schemaStatus":"valid","origin":"official-registry","observedAt":"2026-11-17T17:46:40.012Z","metadataTrust":"untrusted"},{"serverName":"dev.aicomputeradar/ai-compute-radar","endpointFingerprint":"00de53d7703d074381f989860ca63872740c0c4d3aa3772f7a1274bc885b981e","name":"list_hardware","title":"List hardware profiles","description":"Curated GPU and Mac profiles the fit engine knows — ids, memory, usable memory after margins, bandwidth. Use an id with find_fit.","inputSchema":{"type":"object","properties":{},"$schema":"https://json-schema.org/draft/2020-12/schema"},"annotations":null,"definitionHash":"ada91aead54c38bf5bfe2851004d90dedde5afe6f7eb140006ab321b026cb889","schemaStatus":"valid","origin":"official-registry","observedAt":"2026-11-17T17:46:40.012Z","metadataTrust":"untrusted"},{"serverName":"dev.aicomputeradar/ai-compute-radar","endpointFingerprint":"00de53d7703d074381f989860ca63872740c0c4d3aa3772f7a1274bc885b981e","name":"price_history","title":"GPU rental price history","description":"Daily price history per GPU class and source, up to 90 days: the rows the Rent Index and the 30-day range are computed from. Marketplace days (Vast.ai, Clore.ai) are medians over the day's counted hourly medians with min, p75 and offer count; list-price days (RunPod, AWS, Azure, Oracle Cloud, Lambda, Nebius, CoreWeave, Hyperstack) carry the posted price. Each row says which kind it is; never blend the two. Describes what prices did; it never forecasts.","inputSchema":{"type":"object","properties":{"gpu":{"description":"One class by slug or name, e.g. rtx-4090, h100. Every class without it.","type":"string"},"source":{"description":"One source key, e.g. vast, runpod, aws. Every published source without it.","type":"string"},"days":{"description":"Days back from today (default 30, max 365; the series starts 26 August 2026).","type":"integer","minimum":1,"maximum":365}},"$schema":"https://json-schema.org/draft/2020-12/schema"},"annotations":null,"definitionHash":"00318cf78516d77c55b60bc8a309f69bdff56cd193a0f66ac457cea893d6aab4","schemaStatus":"valid","origin":"official-registry","observedAt":"2026-11-17T17:46:40.012Z","metadataTrust":"untrusted"},{"serverName":"dev.aicomputeradar/ai-compute-radar","endpointFingerprint":"00de53d7703d074381f989860ca63872740c0c4d3aa3772f7a1274bc885b981e","name":"trending_models","title":"Trending models","description":"Tracked AI models ranked by Heat Score (0–100, weighted percentiles of measured Hugging Face/OpenRouter signals) with the raw signals, local-run facts (GGUF size, quantization) and links. Models still collecting a week of history have heat=null and rank after scored ones.","inputSchema":{"type":"object","properties":{"limit":{"description":"How many models to return (default 12).","type":"integer","minimum":1,"maximum":100},"slug":{"description":"Return a single model by slug.","type":"string"}},"$schema":"https://json-schema.org/draft/2020-12/schema"},"annotations":null,"definitionHash":"5ebc303b3dcbd8c4e5635ccb7713b2863aa630deece72546052ec557d7d56345","schemaStatus":"valid","origin":"official-registry","observedAt":"2026-11-17T17:46:40.012Z","metadataTrust":"untrusted"},{"serverName":"dev.aicomputeradar/ai-compute-radar","endpointFingerprint":"00de53d7703d074381f989860ca63872740c0c4d3aa3772f7a1274bc885b981e","name":"weekly_pick","title":"Pick of the week","description":"The current pick of the week: one tracked model chosen by a published rule (largest counted Heat Score rise among models that run comfortably on a consumer card of up to 24 GB), with the numbers frozen at selection time, a device-by-device fit ladder and the written report including its caveats. Pass week (e.g. 2026-w37) for a past issue. issue is null until the first issue is published.","inputSchema":{"type":"object","properties":{"week":{"description":"ISO week label of a past issue, e.g. 2026-w37 (default: the current issue).","type":"string","pattern":"^\\d{4}-w\\d{2}$"}},"$schema":"https://json-schema.org/draft/2020-12/schema"},"annotations":null,"definitionHash":"53cfdcdb152f34429a3e6db4eed96634b491d7ed8c50757e28be2d18337d942b","schemaStatus":"valid","origin":"official-registry","observedAt":"2026-11-17T17:46:40.012Z","metadataTrust":"untrusted"}],"endpoints":[{"endpointFingerprint":"00de53d7703d074381f989860ca63872740c0c4d3aa3772f7a1274bc885b981e","protocol":"streamable-http","status":"indexed","toolCount":6,"observedAt":"2026-11-17T17:46:40.012Z"}],"authentication":"unknown"},"connectionConfigurations":{"status":"ready","authentication":"not embedded","clients":{"Claude Desktop":{"mcpServers":{"dev.aicomputeradar/ai-compute-radar":{"url":"https://aicomputeradar.dev/api/mcp"}}},"Cursor":{"mcpServers":{"dev.aicomputeradar/ai-compute-radar":{"url":"https://aicomputeradar.dev/api/mcp"}}},"VS Code":{"servers":{"dev.aicomputeradar/ai-compute-radar":{"type":"http","url":"https://aicomputeradar.dev/api/mcp"}}}}},"resourceType":"mcp-server","callable":true,"runtime":{"callable":true,"protocols":["mcp"]},"interfaces":[{"protocol":"mcp","transport":"streamable-http","url":"https://aicomputeradar.dev/api/mcp"},{"protocol":"mcp","package":"ai-compute-radar","registryType":"npm","version":"1.2.1"}],"profile":{"apiVersion":"1","schemaVersion":"1","id":"mcp-server:dev.aicomputeradar%2Fai-compute-radar","resourceType":"mcp-server","canonicalUrl":"https://www.agentsjunction.com/api/v1/servers/dev.aicomputeradar%2Fai-compute-radar","name":"dev.aicomputeradar/ai-compute-radar","description":"Which open models fit your GPU or Mac, measured. Model momentum, GPU rental prices, weekly pick.","interfaces":[{"protocol":"mcp","transport":"streamable-http","url":"https://aicomputeradar.dev/api/mcp"},{"protocol":"mcp","package":"ai-compute-radar","registryType":"npm","version":"1.2.1"}],"capabilities":[],"identity":{"source":"official-registry","websiteUrl":"https://aicomputeradar.dev/developers","repositoryUrl":null,"version":"1.2.3"},"verification":{"state":"official","confidence":100},"operations":{"resourceType":"mcp-server","name":"dev.aicomputeradar/ai-compute-radar","status":"online","lastCheckedAt":"2026-11-20T08:18:14.072Z","lastSuccessfulCheck":"2026-11-20T08:18:14.072Z","latencyMs":194,"consecutiveFailures":0,"isStale":false,"checks":{"endpointReachable":true,"protocolValid":true,"agentCardValid":null,"mcpHandshakeValid":true},"lastSeen":null,"lastSuccessfulInteraction":null,"lastHealthCheck":"2026-11-20T08:18:14.072Z","source":{"type":"health-check","url":null},"observedAt":"2026-11-20T08:18:14.072Z"},"security":null,"timestamps":{"createdAt":"2026-10-27T17:17:24.765Z","updatedAt":"2026-10-27T17:17:24.765Z","observedAt":"2026-11-20T08:18:14.072Z"},"compatibility":{"serverVersion":"1.2.3","protocolVersions":[{"protocol":"mcp","version":null}]}}}}