io.github.tehtelabs/cheapestllmapi

Est-ce que io.github.tehtelabs/cheapestllmapi est sûr ?

Au dernier audit MCP Hub, le serveur MCP « io.github.tehtelabs/cheapestllmapi » 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 12 outils

• benchmark_list≈ 462 tokens

  Discover exact benchmark IDs, editions, score units, configurations, provenance, and reviewed result counts before calling benchmark_results. Empty benchmarks are retained with resultCount 0.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "benchmark_list", "arguments": {}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"data": {}, "meta": {}}}

• benchmark_results≈ 1243 tokens

  Get reviewed scores for an exact benchmark_id from benchmark_list. Join result.modelId to catalog_search model.id. Compare scores only within the same benchmark edition and configuration. Includes source provenance and reported coding-agent usage when published. Follow pagination.hasMore.

  Paramètres, retour & exemple (3)

  Paramètres

  • limit · integer · optionnel
  • offset · integer · optionnel
  • benchmark_id · string · requis

  Exemple d'appel

  {"name": "benchmark_results", "arguments": {"benchmark_id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"data": {}, "meta": {}, "pagination": {}}}

• catalog_search≈ 795 tokens

  Find canonical model slugs, context limits, and provider prices. Optional provider_slug filters availability, not the provider in bestOffer. bestOffer is selected for 10M input + 2M output tokens; use offer_compare for your workload. Follow pagination.hasMore.

  Paramètres, retour & exemple (5)

  Paramètres

  • page · integer · optionnel
  • query · string · optionnel
  • page_size · integer · optionnel
  • category_slug · string · optionnel
  • provider_slug · string · optionnel

  Exemple d'appel

  {"name": "catalog_search", "arguments": {"page": 1, "query": "texte", "page_size": 1, "category_slug": "texte", "provider_slug": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"data": {}, "meta": {}, "pagination": {}}}

• coding_agent_detail≈ 2602 tokens

  Get a coding-agent profile by agent_slug from coding_agent_list, including official source, latest stable release, freshness, and history coverage. An unavailable archive is explicit in state. This does not assert product benchmark rankings or subscription prices.

  Paramètres, retour & exemple (1)

  Paramètres

  • agent_slug · string · requis

  Exemple d'appel

  {"name": "coding_agent_detail", "arguments": {"agent_slug": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"data": {}, "meta": {}}}

• coding_agent_list≈ 2600 tokens

  List coding-agent profiles, interfaces, model access, official sources, latest stable release, archive counts, freshness, coverage limits, and sourced model/provider compatibility, BYOK, billing and setup facts. Includes agents whose release archive is unavailable; inspect state. Use coding_agent_releases to page through source-linked changelogs.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "coding_agent_list", "arguments": {}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"data": {}, "meta": {}}}

• coding_agent_releases≈ 3173 tokens

  Search archived coding-agent releases by agent_slug, query (title, version, excerpt), topic, and channel. Stable only by default; channel all includes prereleases. Newest first; advance offset by limit while pagination.hasMore. Includes source URLs, abbreviated excerpts, and per-agent freshness/coverage. Topics are keyword mentions, not assessments. Partial coverage is explicit in meta.completeness; all unavailable returns an error. Archives reflect configured source history, not every product announcement.

  Paramètres, retour & exemple (6)

  Paramètres

  • limit · integer · optionnel
  • query · string · optionnel
  • topic · string · optionnel · Models | MCP | Security | Performance | Fixes
  • offset · integer · optionnel
  • channel · string · optionnel · stable | all
  • agent_slug · string · optionnel

  Exemple d'appel

  {"name": "coding_agent_releases", "arguments": {"limit": 1, "query": "texte", "topic": "Models", "offset": 1, "channel": "stable", "agent_slug": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"data": {}, "meta": {}, "pagination": {}}}

• coding_agent_upgrade≈ 3930 tokens

  Find archived changes published after an installed version or exact release ID. Get agent_slug and source_id from coding_agent_detail; default source_id is primary. Only the same publisher source and recognizable product stream are compared. Stable only by default; use channel all for prereleases. The ready response is publication order, not semantic-version precedence or an upgrade safety assessment; backports may appear. An unknown or ambiguous baseline is explicit in data.status, never treated as no changes. Follow data.pagination.hasMore with offset and limit.

  Paramètres, retour & exemple (6)

  Paramètres

  • limit · integer · optionnel
  • offset · integer · optionnel
  • channel · string · optionnel · stable | all
  • installed · string · requis
  • source_id · string · optionnel
  • agent_slug · string · requis

  Exemple d'appel

  {"name": "coding_agent_upgrade", "arguments": {"installed": "texte", "agent_slug": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"data": {}, "meta": {}}}

• execute≈ 398 tokens

  Run a JavaScript async function in an isolated sandbox, composing catalog_search, model_detail, offer_compare, benchmark_results, provider_list, benchmark_list, coding_agent_list, coding_agent_detail, coding_agent_releases, coding_agent_upgrade, and price_watch as catalog.* methods. Return a small JSON value. Example: async () => { const page = await catalog.catalog_search({query: 'claude', page_size: 5}); return page.data.models.map(m => ({slug: m.slug, prices: m.bestOffer?.prices})); }. No network, secrets, or database binding is exposed. Shared worldwide execution budgets: 100 per UTC minute and 5000 per UTC day. Limits: 30 executions per client per minute (IPv6 /64), 20 catalog calls and read units (offer_compare and price_watch use 5), at most two concurrent calls, 5 seconds wall time, 50ms sandbox CPU, 32KiB code, 64KiB JSON output. JavaScript only; no imports or TypeScript syntax. Use /mcp?mode=code for only search + execute.

  Paramètres, retour & exemple (1)

  Paramètres

  • code · string · requis

  Exemple d'appel

  {"name": "execute", "arguments": {"code": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"logs": [], "calls": 1, "result": "texte"}}

• model_detail≈ 1030 tokens

  Get capabilities, context/output limits, and current sourced provider offers by model_slug from catalog_search. Prices are base-context rates; long-context tiers, cache writes, batch discounts, and free-tier quotas can change actual cost.

  Paramètres, retour & exemple (1)

  Paramètres

  • model_slug · string · requis

  Exemple d'appel

  {"name": "model_detail", "arguments": {"model_slug": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"data": {}, "meta": {}}}

• offer_compare≈ 2429 tokens

  Rank current chat offers for up to five canonical model slugs with the website calculator: context-tier prices, cache reads/writes, retries, supported batch rates, capability/benchmark requirements, provider/route preferences, and evidence filters. Input totals include cache shares; cache_hit_percent plus cache_write_percent must be <=100. Average request sizes determine tiers and capacity. Batch is Anthropic direct only. Unknown required evidence excludes offers; missing cache-read rates use standard input rates. Inspect costs, qualification, warnings, assumptions, excludedModels, and pagination.hasMore. Free quotas, non-token fees, and media token accounting are excluded.

  Paramètres, retour & exemple (21)

  Paramètres

  • task · string · optionnel · chat | coding | extraction | custom
    Coding requires the code capability; extraction requires structured output. Every offer must support chat.
  • limit · integer · optionnel
  • offset · integer · optionnel
  • execution · string · optionnel · standard | batch
    Batch supports Anthropic direct routes with a published 50% token discount; unsupported routes are excluded.
  • route_type · string · optionnel · all | official | cloud | gateway | unverified
  • model_slugs · array · requis
  • benchmark_id · string · optionnel · livebench | aa-intelligence | aa-coding | aa-agentic | swe-bench-verified-epoch-2-0-2 | terminal-bench-2-1-terminus-2 | terminal-bench-2-1-claude-code | terminal-bench-2-1-codex
  • input_tokens · integer · optionnel
  • open_weights · boolean · optionnel
  • minimum_score · number · optionnel
    Zero disables score qualification; a positive threshold excludes missing exact benchmark matches.
  • output_tokens · integer · optionnel
  • retry_percent · number · optionnel
  • provider_slugs · array · optionnel
  • cache_hit_percent · number · optionnel
  • require_known_host · boolean · optionnel
    Exclude routes without a named underlying inference provider.
  • cache_write_percent · number · optionnel
  • average_input_tokens · integer · optionnel
  • average_output_tokens · integer · optionnel
  • required_capabilities · array · optionnel
  • minimum_context_tokens · integer · optionnel
  • require_official_prices · boolean · optionnel
    Require official paired input/output price verification. Cache rates may have different source provenance.

  Exemple d'appel

  {"name": "offer_compare", "arguments": {"model_slugs": []}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"data": {}, "meta": {}, "workload": {}, "pagination": {}, "assumptions": [], "requirements": {}}}

• price_watch≈ 2535 tokens

  Read current offers meeting a monthly baseline_usd minus minimum_saving_usd. Uses the same workload, qualifications and evidence filters as offer_compare. Omit model_slugs to watch all qualifying models. Returns up to 50 cheapest matches; no account or delivery subscription is created. The same query is available as RSS at /api/v1/price-watch/feed.xml; your RSS reader handles polling and notifications. Inspect offer warnings before switching.

  Paramètres, retour & exemple (23)

  Paramètres

  • task · string · optionnel · chat | coding | extraction | custom
    Coding requires the code capability; extraction requires structured output. Every offer must support chat.
  • limit · integer · optionnel
  • offset · integer · optionnel
  • execution · string · optionnel · standard | batch
    Batch supports Anthropic direct routes with a published 50% token discount; unsupported routes are excluded.
  • route_type · string · optionnel · all | official | cloud | gateway | unverified
  • model_slugs · array · optionnel
  • baseline_usd · number · requis
  • benchmark_id · string · optionnel · livebench | aa-intelligence | aa-coding | aa-agentic | swe-bench-verified-epoch-2-0-2 | terminal-bench-2-1-terminus-2 | terminal-bench-2-1-claude-code | terminal-bench-2-1-codex
  • input_tokens · integer · optionnel
  • open_weights · boolean · optionnel
  • minimum_score · number · optionnel
    Zero disables score qualification; a positive threshold excludes missing exact benchmark matches.
  • output_tokens · integer · optionnel
  • retry_percent · number · optionnel
  • provider_slugs · array · optionnel
  • cache_hit_percent · number · optionnel
  • minimum_saving_usd · number · requis
  • require_known_host · boolean · optionnel
    Exclude routes without a named underlying inference provider.
  • cache_write_percent · number · optionnel
  • average_input_tokens · integer · optionnel
  • average_output_tokens · integer · optionnel
  • required_capabilities · array · optionnel
  • minimum_context_tokens · integer · optionnel
  • require_official_prices · boolean · optionnel
    Require official paired input/output price verification. Cache rates may have different source provenance.

  Exemple d'appel

  {"name": "price_watch", "arguments": {"baseline_usd": 1, "minimum_saving_usd": 1}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"data": {}, "meta": {}, "watch": {}, "workload": {}, "pagination": {}, "assumptions": [], "requirements": {}}}

• provider_list≈ 457 tokens

  Discover accepted provider slugs, roles, and current comparable model/offer counts. Provider minimum input and output prices are independent minima and may belong to different models; use offer_compare for an actual quote.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "provider_list", "arguments": {}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"data": {}, "meta": {}}}

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://cheapestllmapi.com/mcp