Skip to main content
Glama
HenryGetz

aa-mcp

by HenryGetz
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Remote

Related Servers

Alternatives to aa-mcp

No user-submitted related servers found.

    Related Servers

    • aa-mcp

      Leev1s
      A
      license
      A
      quality
      D
      maintenance
      Enables AI agents to query LLM and multimodal model benchmarks, pricing, speed, and track model updates via structured diffs using the Artificial Analysis public API.
      7
      27 PyPI
      2
      MIT

    • Artificial Analysis MCP Server

      davidhariri
      A
      license
      A
      quality
      D
      maintenance
      Provides access to real-time LLM pricing, speed metrics, and performance benchmarks for over 300 models from Artificial Analysis. It enables users to list, filter, and compare models based on costs, tokens per second, and intelligence indices.
      2
      30 npm
      9
      MIT

    • agentcrush

      kristof-sudo
      F
      license
      Not graded
      quality
      B
      maintenance
      Provides protocol-neutral market intelligence for the AI agent economy, with read-only tools to search agents, retrieve details and histories, compare agents, list categories, view category rankings, and access methodology.
      -

    • whichapiapi

      uriruhman
      A
      license
      Not graded
      quality
      B
      maintenance
      Enables agents to rank model variants and hunt down API offers for a specific task, estimate real billed cost, audit n8n/Make automations for overpay, missing fallbacks and deprecated models, and plan or run evaluation and canary suites on the user's own examples. It also supports price comparison, custom reseller channels with measured per-call cost, and non-LLM capabilities such as web search and speech-to-text.
      AGPL 3.0
    Deploy Server
    One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

    TDQS

    A4/5.0

    Scored across 12 tools

    Disambiguation4/5

    Tools mostly have distinct roles: aa_search resolves names, aa_reference explains fields, aa_raw is an escape hatch, aa_model is single-model detail. There is some overlap between aa_leaderboard, aa_benchmark_leaderboard, aa_pareto and aa_compare since all rank/compare models and share many filter args, but the descriptions clearly delineate rank-vs-frontier-vs-side-by-side-vs-single-benchmark usage.

    Naming Consistency5/5

    All 12 tools use the aa_ prefix with lowercase snake_case (aa_leaderboard, aa_model, aa_pareto, aa_benchmark_leaderboard, aa_reference, aa_raw). The pattern is predictable throughout, with only the shared 'aa_' namespace prefix adding any variation.

    Tool Count5/5

    12 tools is a well-scoped set for a model-intelligence data server, each mapping to a coherent capability (leaderboard, single model, Pareto, compare, benchmarks, providers, media, agents, search, reference, raw). Nothing feels redundant or missing at the count level.

    Completeness4/5

    Coverage is strong: ranking, single-model digests, Pareto frontiers, side-by-side comparison, benchmark search, provider endpoints, media/agents arenas, fuzzy name resolution, static reference, and a raw JSON escape hatch. Minor gaps remain (no explicit write/refresh-scheduling or per-benchmark-specific tools), but aa_benchmark_leaderboard and aa_raw largely cover the workarounds.

    Maintenance

    ActivityMaintained
    ResponsivenessNo issues

    Resources