Skip to main content
Glama
743,433 tools. Updated 2026-11-04 20:36

"OpenAI Gym" matching MCP tools:

  • Capture explicit user feedback on Blueprint surfaces, recording what helped and what's missing, with optional contact email only when follow-up permission is granted.
    MIT
  • Find curated coding examples by free-text query, ranked by relevance, with optional filters for principle, difficulty, library, or pattern family — returning summaries, metadata, and source-code links.
    MIT
  • Evaluate frontend UI surfaces against 8 experience-design laws, scoring craft, accessibility, and readiness. Returns per-law findings and a severity-weighted grade.
    MIT
  • Review a written spec, proposal, or task plan against the 8 Spec Quality Laws before coding. Get per-law findings and a readiness grade that flags untestable requirements or irreversible steps as production blockers.
    MIT
  • Place an outbound AI phone call with a saved agent or custom prompt, attest recipient consent, and configure language, recording, first message, tools, and metadata.
    AGPL 3.0

Matching MCP Servers

  • A
    license
    A
    quality
    D
    maintenance
    MCP server for querying OpenAI usage and cost data, including spend summaries, daily breakdowns, month-over-month comparisons, and token usage by model.
    3
    MIT
  • A
    license
    A
    quality
    D
    maintenance
    Enables Claude to perform real-time web searches and fetch web page content via MCP, using OpenAI-compatible APIs with optional Tavily or Firecrawl engines.
    5
    12 npm
    13
    MIT

Matching MCP Connectors

  • Hosted OpenAI Ads MCP server for Claude, ChatGPT and Cursor, with each action switched per account.

  • OpenAI Sora: Sora & Sora 2 (new social media like TikTok) API by ChatGPT creator OpenAI. Access.

  • Check whether a brand is actively cited by OpenAI, Gemini, and Claude for industry queries—or if competitors dominate—to guide LLM visibility and citation strategy.
    Apache 2.0
  • Run a combined safety scan to detect prompt injection, PII, and secrets in user input before sending to an LLM. Returns risk level and findings for informed blocking decisions.
    MIT
  • Scan text for API keys, secrets, and PII before sending it to external LLMs or publishing. Redact detected sensitive data to prevent credential leaks.
    MIT
  • Scan text or document URLs for PII and secrets before sharing with an LLM, then redact findings into placeholders, masks, or hashes.
    MIT
  • Lists configured upstream vendors and their readiness, BYOK header names, and billing models so you can debug failed chat completions or verify a vendor is available. Reports key presence only.
    MIT
  • Tracks daily LLM costs in USD for a workspace or pipeline to identify cost spikes and compare periods; filter results by service, provider, or API key.
    Apache 2.0
  • Retrieve sessions, traces, or completions from a Freeplay project using flexible filters to analyze observability data and identify issues.
    Apache 2.0
  • Start a temporary local mock server from OpenAPI specs or public URLs, combining multiple APIs into one server, no account needed. Use for local experimentation before deploying hosted mocks.
    MIT
  • Rank hosted AI inference API providers by measured network latency from a chosen probe region in the last 24 hours. Use it to pick the provider or endpoint closest to your users.
    MIT
  • Fetch file bytes from a shareable URL into an EasyDeploy upload session server-side when sandbox egress is blocked; pass a URL, not file contents.
    MIT
  • Judges how memory entries relate, flagging contradictions, progress, or independence so you know where to inspect; returns disputed pairs and requires an OpenAI-compatible endpoint.
    MIT