accueil / serveurs / Dev & Code / io.github.AtticStandard/atom-mcp-server
io.github.AtticStandard/atom-mcp-server
serveur MCP (Model Context Protocol) · attic-standard-mcp 2.1.0
Référencé dans l'annuaire. Seul le pentest comportemental fait foi, et il n'a pas encore été exécuté sur ce serveur.
Est-ce que io.github.AtticStandard/atom-mcp-server est sûr ?
Au dernier audit MCP Hub, le serveur MCP « io.github.AtticStandard/atom-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 11 outils
- compare_prices≈ 400 tokens
The same model, or a whole family, priced across every vendor that sells it: cheapest and dearest offer, vendor count and spread ratio for each direction, plus each offer with its channel. Free tier returns counts, ranges and redacted samples; Attic Standard MCP PRO ($500/month, https://atticstandard.com/mcp) returns vendor names, model names and exact prices. Token prices are per 1,000 tokens; other modalities use their own unit (per image, per second, per minute, per 1,000 characters). Examples: - "Cheapest place to run Llama 3.3 70B" -> model_name="Llama 3.3 70B" - "Qwen family output prices" -> model_family="Qwen", direction="Output"
Paramètres, retour & exemple (5)
Paramètreslimit· integer · optionnel
Maximum SKUs (default 50)direction· string · optionnel · Input | Output | Cached Input
Pricing directionmodel_name· string · optionnel
Model to compare, e.g. 'GPT-4o', 'Llama 3.3 70B', 'DeepSeek V3'model_family· string · optionnel
Whole family instead of one model, e.g. 'Llama', 'Qwen'_atom_api_key· string · optionnel
Your Attic Standard MCP PRO key for vendor- and SKU-level data. Omit for the free tier.
Exemple d'appel{"name": "compare_prices", "arguments": {"limit": 1, "direction": "Input", "model_name": "texte", "model_family": "texte", "_atom_api_key": "texte"}}Exemple de retour{"content": [{"type": "text", "text": "…"}]} - get_index_benchmarks≈ 492 tokens
The Attic Standard price indexes for AI inference: every published index at the week the site shows. Six families: Modality (text, multimodal, image, video, audio, voice, embeddings), Channel (model developers, cloud marketplaces, inference platforms, neoclouds), Tier (flagship, core, compact), License (open weights, restricted weights, proprietary), Origin (United States, China) and Use case (reasoning, coding). For each index and direction (input, cached input, output) it returns the benchmark level (May 2026 = 100) with week, month and vs-base changes, the spot price (median, p25, p75 in dollars) with its own week, month and vs-base changes, and coverage counts with the May 2026 basket size, flagged where the basket has changed materially since the base. Free: fully public, the same figures atticstandard.com publishes. Token prices are per 1,000 tokens; other modalities use their own unit (per image, per second, per minute, per 1,000 characters). Examples: - "Where is text inference priced this week?" -> index_code="TXT" - "Compare the four channels" -> index_category="Channel" - "Open-weight versus proprietary" -> index_category="License"
Paramètres, retour & exemple (3)
Paramètresindex_code· string · optionnel
One index, e.g. 'TXT', 'NCL', 'FLG' or the full code 'AIPI TXT GLB'. Omit for all published indexes._atom_api_key· string · optionnel
Your Attic Standard MCP PRO key for vendor- and SKU-level data. Omit for the free tier.index_category· string · optionnel
Index family: 'Modality', 'Channel', 'Tier', 'License', 'Origin', 'Use case'.
Exemple d'appel{"name": "get_index_benchmarks", "arguments": {"index_code": "texte", "_atom_api_key": "texte", "index_category": "texte"}}Exemple de retour{"content": [{"type": "text", "text": "…"}]} - get_index_constituents≈ 281 tokens
What sits inside an index basket this week. Free tier: the composition (SKUs, models and vendors, split by channel, origin, tier and license). Attic Standard MCP PRO: the model-by-model basket with the vendors selling each model. Examples: - "What is in the flagship index?" -> index_code="FLG" - "How much of the China index is sold through neoclouds?" -> index_code="CHN"
Paramètres, retour & exemple (3)
Paramètresdirection· string · optionnel · Input | Cached Input | Output
Limit to one pricing directionindex_code· string · requis
Index to open, e.g. 'TXT', 'FLG', 'CHN' or 'AIPI TXT GLB'_atom_api_key· string · optionnel
Your Attic Standard MCP PRO key for vendor- and SKU-level data. Omit for the free tier.
Exemple d'appel{"name": "get_index_constituents", "arguments": {"index_code": "texte"}}Exemple de retour{"content": [{"type": "text", "text": "…"}]} - get_kpis≈ 297 tokens
The nine market KPIs Attic Standard publishes each week. - Price structure: output premium, caching discount, caching availability - Price dynamics: repricing activity, repricing depth, post-launch drift - Competition: multi-vendor spread, first-party premium, marketplace premium Each KPI returns its value, interquartile range, population, week, month and vs-base changes, and its published definition. Free: fully public, the same figures atticstandard.com publishes.
Paramètres, retour & exemple (3)
Paramètresgroup· string · optionnel
Optional group: 'Price structure', 'Price dynamics' or 'Competition'weeks· integer · optionnel
Weeks of history per KPI (default 1, latest only)_atom_api_key· string · optionnel
Your Attic Standard MCP PRO key for vendor- and SKU-level data. Omit for the free tier.
Exemple d'appel{"name": "get_kpis", "arguments": {"group": "texte", "weeks": 1, "_atom_api_key": "texte"}}Exemple de retour{"content": [{"type": "text", "text": "…"}]} - get_market_stats≈ 270 tokens
Coverage of the tracked market (active vendors by channel, countries, models, priced SKUs, published indexes) and price distributions split by modality, unit and direction. Free tier returns counts, ranges and redacted samples; Attic Standard MCP PRO ($500/month, https://atticstandard.com/mcp) returns vendor names, model names and exact prices. Token prices are per 1,000 tokens; other modalities use their own unit (per image, per second, per minute, per 1,000 characters).
Paramètres, retour & exemple (2)
Paramètresmodality· string · optionnel
Optional modality: Text, Multimodal, Image, Video, Audio, Voice_atom_api_key· string · optionnel
Your Attic Standard MCP PRO key for vendor- and SKU-level data. Omit for the free tier.
Exemple d'appel{"name": "get_market_stats", "arguments": {"modality": "texte", "_atom_api_key": "texte"}}Exemple de retour{"content": [{"type": "text", "text": "…"}]} - get_model_detail≈ 245 tokens
One model in depth: specs (creator, origin, tier, license, context window, output limit, training cutoff, modalities), the Attic Standard indexes it belongs to, and its price at every vendor. Free tier returns counts, ranges and redacted samples; Attic Standard MCP PRO ($500/month, https://atticstandard.com/mcp) returns vendor names, model names and exact prices.
Paramètres, retour & exemple (2)
Paramètresmodel_name· string · requis
Model to look up, e.g. 'GPT-4o', 'Claude Sonnet 4.5', 'Llama 3.3 70B'_atom_api_key· string · optionnel
Your Attic Standard MCP PRO key for vendor- and SKU-level data. Omit for the free tier.
Exemple d'appel{"name": "get_model_detail", "arguments": {"model_name": "texte"}}Exemple de retour{"content": [{"type": "text", "text": "…"}]} - get_model_intelligence≈ 215 tokens
Six capability and coverage measures drawn from the metadata behind every tracked model: reasoning tier share, long-context saturation, frontier context ceiling, output ceiling spread, training cutoff lag and vendor modality breadth. Read alongside the market KPIs, they explain why models are priced the way they are. Free: fully public, the same figures atticstandard.com publishes.
Paramètres, retour & exemple (1)
Paramètres_atom_api_key· string · optionnel
Your Attic Standard MCP PRO key for vendor- and SKU-level data. Omit for the free tier.
Exemple d'appel{"name": "get_model_intelligence", "arguments": {"_atom_api_key": "texte"}}Exemple de retour{"content": [{"type": "text", "text": "…"}]} - get_price_history≈ 414 tokens
Weekly history. With index_code: the index series (benchmark level, May 2026 = 100, and the spot price with its 25th and 75th percentiles) for up to 260 weeks; free. With model_name: every vendor's price for that model week by week, showing when each SKU was repriced; Attic Standard MCP PRO. Token prices are per 1,000 tokens; other modalities use their own unit (per image, per second, per minute, per 1,000 characters). Examples: - "How has the neocloud index moved since May?" -> index_code="NCL" - "Has anyone cut the price of DeepSeek V3 this quarter?" -> model_name="DeepSeek V3", weeks=13
Paramètres, retour & exemple (6)
Paramètresweeks· integer · optionnel
How many weeks back (default 26)vendor· string · optionnel
With model_name: limit to one vendor. PRO.direction· string · optionnel · Input | Cached Input | Output
Pricing directionindex_code· string · optionnel
Index history, e.g. 'TXT', 'DEV', 'OSS' or 'AIPI TXT GLB'. Free.model_name· string · optionnel
Model price history across every vendor that sells it, e.g. 'GPT-4o'. PRO._atom_api_key· string · optionnel
Your Attic Standard MCP PRO key for vendor- and SKU-level data. Omit for the free tier.
Exemple d'appel{"name": "get_price_history", "arguments": {"weeks": 1, "vendor": "texte", "direction": "Input", "index_code": "texte", "model_name": "texte", "_atom_api_key": "texte"}}Exemple de retour{"content": [{"type": "text", "text": "…"}]} - get_vendor_catalog≈ 338 tokens
Everything one vendor sells: channel, country, pricing page, model and SKU counts, and the full price list. Free tier returns counts, ranges and redacted samples; Attic Standard MCP PRO ($500/month, https://atticstandard.com/mcp) returns vendor names, model names and exact prices. Token prices are per 1,000 tokens; other modalities use their own unit (per image, per second, per minute, per 1,000 characters).
Paramètres, retour & exemple (5)
Paramètreslimit· integer · optionnel
Maximum SKUs (default 100)vendor· string · requis
Vendor name or id, as listed by list_vendorsmodality· string · optionnel
Optional modality: Text, Multimodal, Image, Video, Audio, Voicedirection· string · optionnel · Input | Output | Cached Input
Optional pricing direction_atom_api_key· string · optionnel
Your Attic Standard MCP PRO key for vendor- and SKU-level data. Omit for the free tier.
Exemple d'appel{"name": "get_vendor_catalog", "arguments": {"vendor": "texte"}}Exemple de retour{"content": [{"type": "text", "text": "…"}]} - list_vendors≈ 258 tokens
Every vendor in the Attic Standard fleet with its channel (model developer, cloud marketplace, inference platform or neocloud), country, region and pricing page. Filter by channel, region or country.
Paramètres, retour & exemple (4)
Paramètresregion· string · optionnel
Optional region, e.g. 'North America', 'Europe', 'Asia'channel· string · optionnel
Optional channel: 'Model developer' (DEV), 'Cloud marketplace' (CLD), 'Inference platform' (PLT), 'Neocloud' (NCL)country· string · optionnel
Optional country, e.g. 'United States', 'China', 'France'_atom_api_key· string · optionnel
Your Attic Standard MCP PRO key for vendor- and SKU-level data. Omit for the free tier.
Exemple d'appel{"name": "list_vendors", "arguments": {"region": "texte", "channel": "texte", "country": "texte", "_atom_api_key": "texte"}}Exemple de retour{"content": [{"type": "text", "text": "…"}]} - search_models≈ 692 tokens
Search every priced SKU by modality, vendor, channel, creator, family, tier, license, origin, reasoning, open weights, direction, maximum price and minimum context window. Cheapest first. Free tier returns counts, ranges and redacted samples; Attic Standard MCP PRO ($500/month, https://atticstandard.com/mcp) returns vendor names, model names and exact prices. Token prices are per 1,000 tokens; other modalities use their own unit (per image, per second, per minute, per 1,000 characters). Examples: - "Open-weight text models under $0.0005 per 1,000 output tokens" -> open_source="true", modality="Text", direction="Output", max_price=0.0005 - "Chinese reasoning models on neoclouds" -> origin="China", reasoning="true", channel="Neocloud"
Paramètres, retour & exemple (16)
Paramètrestier· string · optionnel
Lineup tier: 'Flagship', 'Core' or 'Compact'limit· integer · optionnel
Results to return (default 20)offset· integer · optionnel
Offset for pagingorigin· string · optionnel
Creator's home country, e.g. 'United States', 'China'vendor· string · optionnel
Vendor name or idchannel· string · optionnel
'Model developer', 'Cloud marketplace', 'Inference platform' or 'Neocloud'creator· string · optionnel
Model creator (the lab that built the model)license· string · optionnel
License class, e.g. 'open', 'restricted', 'proprietary'modality· string · optionnel
Text, Multimodal, Image, Video, Audio, Voicedirection· string · optionnel · Input | Output | Cached Input
Pricing directionmax_price· number · optionnel
Maximum price in the SKU's own unit (per 1,000 tokens for token models)reasoning· string · optionnel
'true' for reasoning models only, 'false' to exclude themopen_source· string · optionnel
'true' for models with published weightsmodel_family· string · optionnel
Model family, e.g. 'Llama', 'Qwen', 'Claude'_atom_api_key· string · optionnel
Your Attic Standard MCP PRO key for vendor- and SKU-level data. Omit for the free tier.min_context_window· integer · optionnel
Minimum context window in tokens
Exemple d'appel{"name": "search_models", "arguments": {"tier": "texte", "limit": 1, "offset": 1, "origin": "texte", "vendor": "texte", "channel": "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 ».