io.github.skakumanu/llm-pricing-mcp-server

Est-ce que io.github.skakumanu/llm-pricing-mcp-server est sûr ?

Au dernier audit MCP Hub, le serveur MCP « io.github.skakumanu/llm-pricing-mcp-server » est classé « Non encore testé ». Référencé dans l'annuaire. Seul le pentest comportemental fait foi, et il n'a pas encore été exécuté sur ce serveur. Le verdict est réévalué en continu ; consultez la fiche pour l'état à jour.

Méthode : MCP Hub analyse la description de chaque outil (couche 1) et, pour le verdict fort, exécute le serveur dans une micro-VM isolée avec leurres et réseau bloqué (couche 2). On publie des noms et des compteurs, jamais le contenu brut renvoyé par un outil.

Les 29 outils

• analyze_session_usage≈ 268 tokens

  Analyze one specific session's actual recorded LLM usage (tagged via record_usage's session_id) on demand: total input/output tokens, total actual cost, and a per-model breakdown if more than one model was used. Also runs the session's own observed token pattern through the same routing engine behind recommend_model / POST /router/recommend to produce a grounded recommendation — or confirm the current choice is already optimal — with the estimated dollar savings or increase versus this session's actual cost. Returns has_data: false with no recommendation if the session_id has no recorded usage. Advisory only — never switches or reroutes anything.

  Paramètres, retour & exemple (2)

  Paramètres

  • org_id · string · optionnel
    Optional organisation ID filter — scopes the lookup to usage events recorded under that org_id, same as get_usage_summary's org_id
  • session_id · string · requis
    The session_id previously used when calling record_usage

  Exemple d'appel

  {"name": "analyze_session_usage", "arguments": {"session_id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• ask_agent≈ 160 tokens

  Ask the LLM Pricing AI agent a question in natural language. Use for complex queries about pricing, model recommendations, cost optimisation advice, or anything that benefits from multi-step reasoning.

  Paramètres, retour & exemple (3)

  Paramètres

  • message · string · requis
    The question or task for the pricing agent
  • autonomous · boolean · optionnel
    Run in autonomous task mode (default: false)
  • conversation_id · string · optionnel
    Optional conversation ID to continue a previous session

  Exemple d'appel

  {"name": "ask_agent", "arguments": {"message": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• check_price_drift≈ 256 tokens

  Audit this server's own pricing data against an external reference registry. Prices here are hand-maintained and go stale silently; a price that disagrees with the registry by more than the threshold is automatically withheld from serving the moment it's detected, not just when this tool runs. This reports what's currently withheld and why. The price value itself is never overwritten by the registry. Use when the user asks whether the pricing data is accurate or up to date, or wants to audit a specific provider's rates.

  Paramètres, retour & exemple (3)

  Paramètres

  • limit · integer · optionnel
    Maximum findings to return (default: 50, max: 200)
  • provider · string · optionnel
    Limit the audit to one provider (partial, case-insensitive)
  • threshold_pct · number · optionnel
    Minimum % difference to report (default: 5)

  Exemple d'appel

  {"name": "check_price_drift", "arguments": {"limit": 1, "provider": "texte", "threshold_pct": 1}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• compare_costs≈ 123 tokens

  Compare costs for multiple LLM models

  Paramètres, retour & exemple (3)

  Paramètres

  • model_names · array · requis
    List of model names to compare
  • input_tokens · integer · requis
    Number of input tokens
  • output_tokens · integer · requis
    Number of output tokens

  Exemple d'appel

  {"name": "compare_costs", "arguments": {"model_names": [], "input_tokens": 1, "output_tokens": 1}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• delete_budget_alert≈ 77 tokens

  Delete a registered budget-spend alert by its ID.

  Paramètres, retour & exemple (1)

  Paramètres

  • alert_id · integer · requis
    The ID of the alert to delete (from list_budget_alerts or register_budget_alert)

  Exemple d'appel

  {"name": "delete_budget_alert", "arguments": {"alert_id": 1}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• delete_conversation≈ 101 tokens

  Delete a specific chat conversation by its ID. Use when the user asks to delete, clear, or remove a past conversation. Use list_conversations first to find the conversation ID.

  Paramètres, retour & exemple (1)

  Paramètres

  • conversation_id · string · requis
    The ID of the conversation to delete

  Exemple d'appel

  {"name": "delete_conversation", "arguments": {"conversation_id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• delete_price_alert≈ 76 tokens

  Delete a registered price-change alert by its ID.

  Paramètres, retour & exemple (1)

  Paramètres

  • alert_id · integer · requis
    The ID of the alert to delete (from list_price_alerts or register_price_alert)

  Exemple d'appel

  {"name": "delete_price_alert", "arguments": {"alert_id": 1}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• estimate_cost≈ 124 tokens

  Estimate the cost of using a specific LLM model

  Paramètres, retour & exemple (3)

  Paramètres

  • model_name · string · requis
    Name of the LLM model (e.g., 'gpt-4', 'claude-3-opus')
  • input_tokens · integer · requis
    Number of input tokens
  • output_tokens · integer · requis
    Number of output tokens

  Exemple d'appel

  {"name": "estimate_cost", "arguments": {"model_name": "texte", "input_tokens": 1, "output_tokens": 1}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• get_all_pricing≈ 43 tokens

  Get current pricing for all LLM models from all providers

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "get_all_pricing", "arguments": {}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• get_cache_stats≈ 124 tokens

  Report process-lifetime hit/miss counts, total lookups, and hit rate for the ~5-minute recommendation cache, separately for the recommend_model tool and POST /router/recommend (never combined). Server-operations introspection for confirming the cache is reducing recomputation in production, not a pricing question. Counts reset on process restart; reading them never changes them.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "get_cache_stats", "arguments": {}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• get_data_quality≈ 140 tokens

  Report an aggregate accuracy summary for the pricing catalogue: what percentage of models have a confirmed, fresh price, how many are currently withheld due to price drift, how many are newly discovered and not yet priced, and how many confirmed prices are over 90 days old. A single trust signal, distinct from check_price_drift which lists individual disputes. Use when the user asks how accurate or trustworthy the pricing data is, overall.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "get_data_quality", "arguments": {}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• get_ide_pricing≈ 244 tokens

  Get subscription pricing for AI coding IDE tools: GitHub Copilot, Cursor, Windsurf, Claude.ai, JetBrains AI, Amazon Q Developer, and Tabnine. Returns monthly subscription cost, inline completion support, context window, and per-tool strengths. Use this when the user asks to compare IDE AI tools, subscription-based coding assistants, or wants to know which IDE AI fits their budget.

  Paramètres, retour & exemple (3)

  Paramètres

  • provider · string · optionnel
    Filter by provider name (partial match, case-insensitive). Examples: 'GitHub Copilot', 'Cursor', 'Windsurf', 'JetBrains', 'Amazon Q', 'Tabnine'
  • inline_only · boolean · optionnel
    If true, only return tools that support real-time inline code completion
  • max_monthly · number · optionnel
    Only return plans at or below this monthly USD price (e.g. 20 for $20/mo)

  Exemple d'appel

  {"name": "get_ide_pricing", "arguments": {"provider": "texte", "inline_only": true, "max_monthly": 1}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• get_performance_metrics≈ 105 tokens

  Get performance metrics (throughput, latency, context window) for models

  Paramètres, retour & exemple (2)

  Paramètres

  • provider · string · optionnel
    Optional provider filter (e.g., 'openai', 'anthropic')
  • include_cost · boolean · optionnel
    Include cost metrics in response (default: true)

  Exemple d'appel

  {"name": "get_performance_metrics", "arguments": {"provider": "texte", "include_cost": true}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• get_pricing_export_url≈ 239 tokens

  Generate a download URL for the pricing history export. Returns a URL the user can open in their browser to download snapshot history as CSV (for spreadsheets) or JSON (for code). Use this when the user asks to export, download, or save pricing data.

  Paramètres, retour & exemple (5)

  Paramètres

  • days · integer · optionnel
    Look-back window in days (default: 30, max: 365)
  • limit · integer · optionnel
    Max rows to export (default: 10000, max: 100000)
  • format · string · optionnel · csv | json
    Output format: 'csv' (default) or 'json'
  • provider · string · optionnel
    Filter by provider (optional)
  • model_name · string · optionnel
    Filter by model name (optional)

  Exemple d'appel

  {"name": "get_pricing_export_url", "arguments": {"days": 1, "limit": 1, "format": "csv", "provider": "texte", "model_name": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• get_pricing_history≈ 203 tokens

  Query historical pricing snapshots recorded over time. Use this to look up past prices for a model or provider, or to see how prices have changed over a given number of days.

  Paramètres, retour & exemple (4)

  Paramètres

  • days · integer · optionnel
    Look-back window in days (default: 30, max: 365)
  • limit · integer · optionnel
    Maximum number of snapshot rows to return (default: 50, max: 500)
  • provider · string · optionnel
    Filter by provider (e.g. 'openai'). Omit for all providers.
  • model_name · string · optionnel
    Filter by model name (e.g. 'gpt-4o'). Omit for all models.

  Exemple d'appel

  {"name": "get_pricing_history", "arguments": {"days": 1, "limit": 1, "provider": "texte", "model_name": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• get_pricing_trends≈ 176 tokens

  Find models whose prices changed the most over a given period. Returns models sorted by absolute percentage price change with a direction label ('increased', 'decreased', or 'unchanged'). Use this to answer questions like 'which models got cheaper this month?' or 'which providers raised prices recently?'

  Paramètres, retour & exemple (2)

  Paramètres

  • days · integer · optionnel
    Look-back window in days (default: 30, max: 365)
  • limit · integer · optionnel
    Maximum models to return (default: 20, max: 100)

  Exemple d'appel

  {"name": "get_pricing_trends", "arguments": {"days": 1, "limit": 1}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• get_telemetry≈ 118 tokens

  Get MCP server telemetry and usage statistics including tool usage, response times, and error rates

  Paramètres, retour & exemple (2)

  Paramètres

  • limit · integer · optionnel
    Maximum items per category (default: 10, max: 50)
  • include_details · boolean · optionnel
    Include detailed statistics (default: true)

  Exemple d'appel

  {"name": "get_telemetry", "arguments": {"limit": 1, "include_details": true}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• get_usage_summary≈ 148 tokens

  Get a summary of actual recorded LLM spend: total cost, request count, and breakdowns by model and provider, from usage events previously logged via record_usage. Use when the user asks what they've actually spent, as opposed to a hypothetical cost estimate.

  Paramètres, retour & exemple (2)

  Paramètres

  • days · integer · optionnel
    Look-back window in days (default: 30, max: 365)
  • org_id · string · optionnel
    Optional organisation ID filter

  Exemple d'appel

  {"name": "get_usage_summary", "arguments": {"days": 1, "org_id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• get_use_cases≈ 60 tokens

  Get recommended use cases and strengths for LLM models

  Paramètres, retour & exemple (1)

  Paramètres

  • provider · string · optionnel
    Optional provider filter

  Exemple d'appel

  {"name": "get_use_cases", "arguments": {"provider": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• import_session_usage≈ 662 tokens

  Bulk-import a completed session's usage in a single call — the retroactive counterpart to record_usage, for when a session wasn't instrumented live. Use when a calling agent (e.g. VS Code Copilot Chat) already has a session's turn-by-turn history in its own local store and wants this server to report on it exactly as if it had been tracked live. Accepts a list of entries under one shared session_id; each entry resolves its input and output tokens independently, either from exact counts when known or by estimating from raw turn text using this server's existing token counter. Cost is always computed server-side from current pricing, never trusted from the caller. A malformed entry (no usable tokens/text on one side, or an unresolvable model_name) is reported as its own per-entry failure and does not fail the rest of the batch. Idempotent like record_usage — resubmitting the same entries (same request_id, or the same session_id/model/occurred_at/token-or-text when request_id is omitted) is a no-op. Recorded usage is then readable via analyze_session_usage and GET /usage/session/{session_id}.

  Paramètres, retour & exemple (3)

  Paramètres

  • org_id · string · optionnel
    Optional organisation ID to attribute this usage to
  • entries · array · requis
    Usage entries to import, one per turn/call in the session
  • session_id · string · requis
    Shared session ID to tag every entry in this batch with

  Exemple d'appel

  {"name": "import_session_usage", "arguments": {"entries": [], "session_id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• list_budget_alerts≈ 48 tokens

  List all registered budget-spend webhook alerts with their IDs and settings.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "list_budget_alerts", "arguments": {}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• list_conversations≈ 122 tokens

  List stored chat conversation sessions with their IDs, last-updated timestamp, turn count, and a preview of the most recent user message. Use this when the user asks to see their past conversations or chat history.

  Paramètres, retour & exemple (1)

  Paramètres

  • limit · integer · optionnel
    Maximum number of conversations to return (default: 20, max: 100)

  Exemple d'appel

  {"name": "list_conversations", "arguments": {"limit": 1}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• list_price_alerts≈ 48 tokens

  List all registered price-change webhook alerts with their IDs and settings.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "list_price_alerts", "arguments": {}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• optimize_workload≈ 634 tokens

  Optimise a multi-task LLM workload by assigning the cheapest qualifying model to each task instead of running everything through one model. Takes a list of workloads (task type + monthly volume + optional quality floor and capability requirements) and returns a per-task model allocation, the total monthly cost, and the saving versus the best single-model deployment. If a monthly budget is given, leftover headroom is spent on the most cost-efficient quality upgrades. Use when the user asks how to cut LLM spend across several task types, or whether tiered model routing is worth it.

  Paramètres, retour & exemple (3)

  Paramètres

  • workloads · array · requis
    One entry per task type in the workload mix
  • min_quality_score · number · optionnel
    Global quality floor (0-100) applied to every workload
  • monthly_budget_usd · number · optionnel
    Total monthly budget in USD. Leftover headroom is spent on the most cost-efficient quality upgrades.

  Exemple d'appel

  {"name": "optimize_workload", "arguments": {"workloads": []}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• predict_cost≈ 509 tokens

  Predict the real cost of an LLM call from your actual prompt text — no need to know token counts in advance. Counts tokens locally, infers the task type (or accepts one explicitly), estimates output length from empirical I/O profiles, and returns all models ranked cheapest-first with effective cost after prompt-cache savings. Also surfaces the best quality-per-dollar pick. Use this before making any LLM API call to avoid surprise bills.

  Paramètres, retour & exemple (7)

  Paramètres

  • top_n · integer · optionnel
    Number of models to return, ranked cheapest-first (default: 10, max: 50)
  • prompt · string · requis
    The actual prompt text to cost-estimate (required)
  • task_type · string · optionnel · classification | extraction | summarization | qa | code_generation | translation | chat | content_generation
    Task type for output-length estimation. Auto-inferred from prompt if omitted. Options: classification, extraction, summarization, qa, code_generation, translation, chat, content_generation, reasoning, function_calling, data_analysis, rewrite
  • require_vision · boolean · optionnel
    Only include models that support image/vision input (default: false)
  • cache_hit_ratio · number · optionnel
    Fraction of calls that hit the prompt cache (0–1). Set this if you have a large reusable system prompt. Supported providers: Anthropic (10% cache rate), OpenAI (50%), Google (25%). Default: 0
  • min_context_tokens · integer · optionnel
    Minimum context window size required in tokens (optional)
  • require_function_calling · boolean · optionnel
    Only include models that support function/tool calling (default: false)

  Exemple d'appel

  {"name": "predict_cost", "arguments": {"prompt": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• recommend_model≈ 744 tokens

  Recommend the optimal LLM model from a free-text description of your use case — no need to already know the routing engine's task_type vocabulary. Classifies the description into a task type, then runs it through the same routing engine behind /router/recommend (live pricing + benchmark quality, hard filters for cost/quality/context window, scored by quality-per-dollar). Returns the best match plus up to 3 alternatives. Read-only — use predict_cost first if you also want per-model cost estimates for an actual prompt, and optimize_workload if you have several distinct task types to route at once.

  Paramètres, retour & exemple (13)

  Paramètres

  • task_type · string · optionnel · classification | extraction | summarization | qa | code_generation | translation | chat | content_generation
    Optional explicit task type, bypassing auto-classification of the description. Options: classification, extraction, summarization, qa, code_generation, translation, chat, content_generation, reasoning, function_calling, data_analysis, rewrite
  • description · string · requis
    Free-text description of the use case, e.g. 'summarize long customer support tickets' or 'generate Python unit tests'
  • ide_context · string · optionnel
    IDE context hint — boosts IDE-native tools: 'copilot' | 'cursor' | 'windsurf' | 'claude_code' | 'jetbrains' | 'amazon_q'
  • avg_input_tokens · integer · optionnel
    Average input tokens per request (default: 500)
  • avg_output_tokens · integer · optionnel
    Average output tokens per request (default: 200)
  • min_quality_score · number · optionnel
    Minimum required quality score (0-100)
  • min_context_window · integer · optionnel
    Minimum required context window size (tokens)
  • monthly_budget_usd · number · optionnel
    Monthly spend ceiling in USD. Combined with estimated_monthly_requests, avg_input_tokens, and avg_output_tokens to hard-filter models that would exceed it.
  • prefer_low_latency · boolean · optionnel
    Prioritise lower-latency models (default: false)
  • preferred_provider · string · optionnel
    Preferred provider name (10% score boost applied)
  • max_cost_per_1m_tokens · number · optionnel
    Maximum acceptable average cost per 1M tokens (USD)
  • exclude_reasoning_models · boolean · optionnel
    Exclude slow thinking/reasoning models (default: false)
  • estimated_monthly_requests · integer · optionnel
    Estimated requests per month (default: 1000)

  Exemple d'appel

  {"name": "recommend_model", "arguments": {"description": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• record_usage≈ 358 tokens

  Record actual token usage for a completed LLM call. Cost is computed server-side from current pricing, never trusted from the caller — this is the 'actual spend' counterpart to estimate_cost's hypothetical numbers. Optionally scope to an org_id for per-org spend tracking. Resubmitting the same request_id for the same org is a no-op. Use when the user wants to log or track real LLM spend, not just estimate it.

  Paramètres, retour & exemple (7)

  Paramètres

  • org_id · string · optionnel
    Optional organisation ID to attribute this usage to
  • model_name · string · requis
    Name of the LLM model that was called
  • request_id · string · optionnel
    Optional idempotency key — resubmitting the same value is a no-op
  • session_id · string · optionnel
    Optional session ID to tag this event with, so it can later be grouped and retrieved via analyze_session_usage — e.g. a bounded burst of calls like a coding-agent run or a chat session
  • occurred_at · number · optionnel
    Unix timestamp when the call happened (default: now)
  • input_tokens · integer · requis
    Number of input tokens actually used
  • output_tokens · integer · requis
    Number of output tokens actually used

  Exemple d'appel

  {"name": "record_usage", "arguments": {"model_name": "texte", "input_tokens": 1, "output_tokens": 1}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• register_budget_alert≈ 221 tokens

  Register a webhook URL to receive notifications when actual recorded spend (from record_usage) crosses a USD threshold within a rolling window. Optionally scope to a specific org_id (omit for total spend across all orgs). Fires at most once per period_days while spend stays over threshold. Returns the alert ID.

  Paramètres, retour & exemple (4)

  Paramètres

  • url · string · requis
    Webhook URL to POST when the alert fires
  • org_id · string · optionnel
    Organisation to monitor. Omit for total spend across all orgs.
  • period_days · integer · optionnel
    Rolling look-back window for the spend check, in days (default: 30)
  • threshold_usd · number · requis
    Spend level in USD that triggers the alert

  Exemple d'appel

  {"name": "register_budget_alert", "arguments": {"url": "texte", "threshold_usd": 1}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• register_price_alert≈ 190 tokens

  Register a webhook URL to receive notifications when a model's price changes by more than a specified percentage. Optionally scope the alert to a specific provider or model. Returns the alert ID.

  Paramètres, retour & exemple (4)

  Paramètres

  • url · string · requis
    Webhook URL to POST when the alert fires
  • provider · string · optionnel
    Limit to a specific provider (e.g. 'openai'). Omit for all.
  • model_name · string · optionnel
    Limit to a specific model name. Omit for all models.
  • threshold_pct · number · optionnel
    Minimum absolute % price change to trigger the alert (default: 5.0)

  Exemple d'appel

  {"name": "register_price_alert", "arguments": {"url": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

C'est votre serveur ?

Revendiquez-le sur l'espace créateur (preuve GitHub, domaine ou npm) pour afficher le badge « propriétaire vérifié » et lancer un pentest comportemental à la demande afin d'obtenir le badge « Vérifié ».

Créer un compte / revendiquer →

Source

https://llm-pricing-api.fly.dev/mcp