MCP App StoreMCP App Store
from tfy-gateway-skills13
Configure and use TrueFoundry's OpenAI-compatible AI Gateway to route, rate-limit, and observe LLM calls across providers.
This skill documents how to configure and call TrueFoundry's AI Gateway — a single OpenAI-compatible endpoint that routes requests to many LLM providers (OpenAI, Anthropic, Azure, self-hosted vLLM, etc.), enforces rate limits and budgets, and provides observability. It includes language snippets (Python, Node, curl) and YAML examples for routing, load-balancing, rate limits, and budget controls.
Use this skill when you want a unified API to call multiple LLM providers, implement rate limiting or cost budgets, add failover/load-balancing between providers, or attach self-hosted models to a central gateway. Also useful when integrating the gateway with LangChain, LlamaIndex, or CI/CD flows that apply gateway config.
Typical callers: coding agents and automation that use OpenAI-compatible SDKs (Copilot/Codex-style integrations, LangChain runners, CI automation).
TrueFoundry AI Gateway skill for configuring and managing LLM gateway routing, rate-limiting, and observability. SKILL.md is well-structured with clear checklists and ambiguity guidance. Scripts are auto-generated Pydantic schema validators (50KB+ monolithic manifest_schemas.py) that require TrueFoundry-specific dependencies. Not runnable outside the TrueFoundry platform context. No security concerns — no credential exfiltration, destructive commands, or phone-home behavior.
pydantic.v1yamlNarrow-audience skill (TrueFoundry Gateway users only). Well-written SKILL.md with good progressive disclosure. Scripts are codegen artifacts — functional but not hand-crafted. No security issues found.
NGINX Integration
Integrate with NGINX via the Membrane CLI to query, manage, and proxy requests to NGINX for configuration, logs, and runtime operations.
Yielding Bear — Unified LLM Routing
A unified LLM routing API that automatically routes requests to the cheapest capable model across providers to reduce inference cost by ~60-80%.
Starlark Dev
Create, debug, and test Kurtosis Starlark packages — write package structure, run dry-runs, and inspect plan execution for reliable orchestration.
Sync Production Database to Development
Run a safe, scripted workflow to download production database dumps and restore them into a development environment (download-only and restore options).
Markdrop
Convert PDFs to structured Markdown or interactive HTML and generate AI-powered descriptions for images and tables using multiple LLM providers.
Sandbox0 Integration
Guidance and templates for integrating Sandbox0 sandboxing into AI agents — CLI/SDK patterns, templates, volumes, network policy, and deployment choices.
Cost Tracker
Monitor agent session costs, set budget alerts, and get actionable token-spend optimizations to keep multi-session workflows within budget.
Alpha Forge Pre-Ship Quality Gates
Pre-merge quality gates for PRs that validate RNG determinism, forked URLs, runtime parameter ranges, and manifest synchronization to reduce review cycles.