{"id":222048,"recorded_at":"2026-10-26T15:16:23.054062Z","observed_at":"2026-10-26T15:16:23.054012Z","subject_kind":"endpoint","subject":"10bdfa4b-ac8e-41b9-a18d-9e1d225b0fe9","kind":"mcp.tools","method":"probe.mcp/1","body":{"count":12,"tools":[{"description":"Use for LLM inference/reasoning cost per successful multi-step agent task, including failure overhead and context growth across turns. Use agent-workflow-cost-calculator for iPaaS/app-action/MCP orchestration fees. Use automation-cost-calculator for generic Zapier/Make/n8n workflow billing.","inputSchema":{"examples":[{"tasks_per_month":60000}],"properties":{"avg_tokens_in_per_turn":{"description":"Avg input tokens per turn (default 3000)","minimum":0,"type":"number"},"avg_tokens_out_per_turn":{"description":"Avg output tokens per turn (default 400)","minimum":0,"type":"number"},"context_growth_factor":{"description":"Multiplier on input tokens as conversation grows (default 1.4)","minimum":1,"type":"number"},"model":{"description":"LLM model (default claude-sonnet-4-6)","type":"string"},"provider":{"description":"LLM provider (default anthropic)","type":"string"},"steps_per_task":{"description":"Avg reasoning steps per task (default 5)","minimum":1,"type":"number"},"success_rate":{"description":"Task success rate 0-1 (default 0.7)","maximum":1,"minimum":0.01,"type":"number"},"tasks_per_month":{"description":"Tasks attempted per month","minimum":0,"type":"number"},"tool_calls_per_step":{"description":"Avg tool invocations per step (default 2)","minimum":0,"type":"number"}},"required":["tasks_per_month"],"type":"object"},"name":"agent-loop-cost-calculator"},{"description":"Use for automation-platform/iPaaS cost of an AI agent workflow, including app-action fan-out and MCP tool-call accounting, explicitly excluding LLM token spend. Use automation-cost-calculator for generic non-agent workflow billing. Use agent-loop-cost-calculator for LLM inference/reasoning cost per successful multi-step agent task.","inputSchema":{"examples":[{"agent_runs_per_month":20000}],"properties":{"agent_runs_per_month":{"description":"Agent workflow runs per month","minimum":0,"type":"number"},"app_actions_per_run":{"description":"Downstream app actions per agent run (default 3)","minimum":0,"type":"number"},"make_modules_per_run":{"description":"Make modules per run; defaults to app actions + MCP calls","minimum":1,"type":"number"},"mcp_tool_calls_per_run":{"description":"MCP tool calls per agent run (default 1)","minimum":0,"type":"number"}},"required":["agent_runs_per_month"],"type":"object"},"name":"agent-workflow-cost-calculator"},{"description":"Use for generic or non-agent recurring workflow platform billing across Zapier task billing, Make credit billing, and n8n execution billing. Use agent-workflow-cost-calculator instead when the workflow is explicitly an AI agent with app actions or MCP tool calls. Use agent-loop-cost-calculator instead when the question is about LLM inference/reasoning cost per successful agent task.","inputSchema":{"examples":[{"workflow_runs_per_month":120000}],"properties":{"billable_steps_per_run":{"description":"Billable actions/modules per run (default 5)","minimum":1,"type":"number"},"make_modules_per_run":{"description":"Make module actions per scenario run; defaults to billable_steps_per_run","minimum":1,"type":"number"},"workflow_runs_per_month":{"description":"Workflow/scenario runs per month","minimum":0,"type":"number"}},"required":["workflow_runs_per_month"],"type":"object"},"name":"automation-cost-calculator"},{"description":"Use when a user needs to know whether a document plus prompt plus output fits within a model's context window, or wants a strategy recommendation (truncate/summarize/rag/chunk).","inputSchema":{"examples":[{"doc_tokens":18000,"model_context_window":200000}],"properties":{"doc_tokens":{"description":"Primary document/content tokens","minimum":0,"type":"number"},"expected_out_tokens":{"description":"Reserved output budget (default 1000)","minimum":0,"type":"number"},"model_context_window":{"description":"Target model context size","minimum":1,"type":"number"},"overhead_tokens":{"description":"System prompt + few-shot + history (default 2000)","minimum":0,"type":"number"},"strategy_hint":{"description":"Preferred strategy (optional)","enum":["truncate","summarize","rag","chunk"],"type":"string"}},"required":["doc_tokens","model_context_window"],"type":"object"},"name":"context-window-planner"},{"description":"Use when a user needs to budget an LLM evaluation run. Given samples/models/trials, returns total cost, per-run cost, and parallel time estimate.","inputSchema":{"examples":[{"samples":2000}],"properties":{"avg_tokens_in":{"description":"Avg input tokens per sample (default 2000)","minimum":0,"type":"number"},"avg_tokens_out":{"description":"Avg output tokens per sample (default 500)","minimum":0,"type":"number"},"judge_enabled":{"description":"Enable LLM-as-judge second pass (default false)","type":"boolean"},"judge_tokens_in":{"description":"Judge input tokens (default 1500)","minimum":0,"type":"number"},"judge_tokens_out":{"description":"Judge output tokens (default 200)","minimum":0,"type":"number"},"model":{"description":"Eval model (default claude-sonnet-4-6)","type":"string"},"models":{"description":"Candidate models (default 1)","minimum":1,"type":"number"},"provider":{"description":"Eval provider (default anthropic)","type":"string"},"samples":{"description":"Number of eval samples","minimum":1,"type":"number"},"trials_per_sample":{"description":"Repeats per sample (default 1)","minimum":1,"type":"number"}},"required":["samples"],"type":"object"},"name":"eval-cost-calculator"},{"description":"Use when a user is considering fine-tuning vs prompt engineering. Returns training cost, monthly inference savings, months-to-ROI, and breakeven volume.","inputSchema":{"examples":[{"monthly_inference_tokens":300000000,"train_tokens":50000000}],"properties":{"base_inference_cost_1m":{"description":"Baseline API output cost per 1M","minimum":0,"type":"number"},"finetuned_inference_cost_1m":{"description":"Fine-tuned inference cost per 1M","minimum":0,"type":"number"},"monthly_inference_tokens":{"description":"Expected monthly inference volume (output tokens)","minimum":0,"type":"number"},"prompt_reduction_pct":{"description":"Prompt size reduction % from eliminating few-shot (default 0)","maximum":100,"minimum":0,"type":"number"},"train_cost_per_1m":{"description":"Training cost per 1M tokens","minimum":0,"type":"number"},"train_tokens":{"description":"Training tokens (dataset × epochs)","minimum":0,"type":"number"}},"required":["train_tokens","monthly_inference_tokens"],"type":"object"},"name":"fine-tune-roi-calculator"},{"description":"Use when a user needs to budget LLM observability tooling. Returns monthly cost at given request volume with retention adjustment.","inputSchema":{"examples":[{"provider":"langsmith","requests_per_day":50000}],"properties":{"avg_log_bytes":{"description":"Avg payload bytes per traced request (default 4096)","minimum":0,"type":"number"},"provider":{"description":"Observability provider","enum":["langsmith","langfuse","helicone","portkey","arize","braintrust"],"type":"string"},"requests_per_day":{"description":"Average daily LLM requests","minimum":0,"type":"number"},"retention_days":{"description":"Retention in days (default 30)","minimum":1,"type":"number"}},"required":["requests_per_day","provider"],"type":"object"},"name":"observability-cost-calculator"},{"description":"Use when a user asks what an LLM workload costs on a specific provider/model, or wants to compare cost across providers. Given tokens per call and call volume, returns monthly cost plus a tier comparison table.","inputSchema":{"examples":[{"calls_per_month":100000,"tokens_in":1200,"tokens_out":400}],"properties":{"calls_per_month":{"description":"Monthly call volume","minimum":1,"type":"number"},"include_comparison":{"description":"Include tier comparison table (default true)","type":"boolean"},"model":{"description":"Target model (e.g. claude-sonnet-4-6)","type":"string"},"provider":{"description":"Target provider (e.g. anthropic, openai, together)","type":"string"},"tokens_in":{"description":"Input tokens per call","minimum":0,"type":"number"},"tokens_out":{"description":"Output tokens per call","minimum":0,"type":"number"}},"required":["tokens_in","tokens_out"],"type":"object"},"name":"provider-cost-calculator"},{"description":"Use when a user is planning to quantize an LLM to fit on smaller hardware. Given parameter count and precision transition, returns VRAM requirement, speedup estimate, and approximate quality delta.","inputSchema":{"examples":[{"params_billions":8}],"properties":{"batch_size":{"description":"Serving batch size (default 1)","minimum":1,"type":"number"},"kv_cache_tokens":{"description":"Max KV cache tokens (default 8192)","minimum":0,"type":"number"},"params_billions":{"description":"Model parameter count in billions","minimum":0.1,"type":"number"},"precision_from":{"description":"Starting precision (default bf16)","enum":["fp32","fp16","bf16","fp8","int8","int6","int5","int4","int3","int2","int1"],"type":"string"},"precision_to":{"description":"Target precision (default int4)","enum":["fp32","fp16","bf16","fp8","int8","int6","int5","int4","int3","int2","int1"],"type":"string"}},"required":["params_billions"],"type":"object"},"name":"quantization-calculator"},{"description":"Use when a user needs end-to-end RAG cost estimation (embedding + vector store + generation). Returns monthly cost with breakdown and dominant-component identification.","inputSchema":{"examples":[{"corpus_tokens":25000000,"queries_per_day":5000}],"properties":{"answer_tokens":{"description":"Avg answer tokens (default 400)","minimum":0,"type":"number"},"chunk_size_tokens":{"description":"Avg chunk size (default 512)","minimum":64,"type":"number"},"chunks_retrieved":{"description":"Chunks per query (default 5)","minimum":1,"type":"number"},"corpus_tokens":{"description":"Indexed corpus size in tokens","minimum":0,"type":"number"},"embedding_provider":{"description":"Embedding model","enum":["openai-3-small","openai-3-large","voyage-3","voyage-3-lite","cohere-embed-v3","google-text-embed-004"],"type":"string"},"generator_model":{"description":"Generator model (default claude-sonnet-4-6)","type":"string"},"generator_provider":{"description":"Generator LLM provider (default anthropic)","type":"string"},"queries_per_day":{"description":"User query volume per day","minimum":0,"type":"number"},"question_tokens":{"description":"Avg question tokens (default 100)","minimum":0,"type":"number"},"reindex_fraction_per_month":{"description":"Fraction of corpus re-embedded per month (default 0.1)","maximum":1,"minimum":0,"type":"number"},"vector_store":{"description":"Vector store","enum":["pinecone","weaviate","qdrant","chroma","turbopuffer"],"type":"string"}},"required":["queries_per_day","corpus_tokens"],"type":"object"},"name":"rag-pipeline-cost-calculator"},{"description":"Use when a user is deciding between API usage and self-hosted GPU inference at a given volume. Returns breakeven token volume, monthly cost comparison, and go/no-go recommendation.","inputSchema":{"examples":[{"monthly_tokens":750000000}],"properties":{"api_cost_per_1m_out":{"description":"Current API output cost per 1M tokens","minimum":0,"type":"number"},"gpu_provider":{"description":"GPU provider (e.g. runpod, modal)","type":"string"},"gpu_type":{"description":"GPU type (e.g. h100, a100-80gb)","type":"string"},"monthly_tokens":{"description":"Monthly output token volume","minimum":0,"type":"number"},"operational_overhead_pct":{"description":"Ops overhead % on GPU cost (default 40)","minimum":0,"type":"number"},"utilization_pct":{"description":"Expected GPU utilization % (default 60)","maximum":100,"minimum":1,"type":"number"}},"required":["monthly_tokens"],"type":"object"},"name":"self-host-breakeven-calculator"},{"description":"Use when a user asks how many tokens a given text will consume, or needs to estimate prompt size before pricing a workload. Given text and tokenizer family, returns low/high token range and byte-level measurements.","inputSchema":{"examples":[{"text":"Summarize the Q3 board deck into five concise bullet points for the exec team."}],"properties":{"expected_out_tokens":{"description":"Expected output token budget (optional)","minimum":0,"type":"number"},"text":{"description":"Text content to count tokens for","type":"string"},"tokenizer":{"description":"Tokenizer family (default: default)","enum":["cl100k_base","o200k_base","claude","gemini","llama3","mistral","default"],"type":"string"}},"required":["text"],"type":"object"},"name":"token-counter"}]},"body_sha256":"b3c8dcca245674e6c80a97c3bb73b19848e3dd920b798df0c8fb1297472f2c78","prev_id":null,"leaf":"0xe95a4509f4fc79b2b5a1a0e01fed354d6cf586fcd18fd393c80c7e9d7d757e46","leaf_text":"{\"body\":\"b3c8dcca245674e6c80a97c3bb73b19848e3dd920b798df0c8fb1297472f2c78\",\"id\":222048,\"kind\":\"mcp.tools\",\"method\":\"probe.mcp/1\",\"observed_us\":1793027783054012,\"prev\":null,\"subject\":\"10bdfa4b-ac8e-41b9-a18d-9e1d225b0fe9\",\"subject_kind\":\"endpoint\"}","day":null,"proof":[]}