By truefoundry
Manage the full lifecycle of TrueFoundry AI Gateway — configure model routing, guardrails, MCP servers, prompt registry, and Skills Registry; migrate existing codebase to gateway; diagnose issues with logs and traces.
Orchestrates TrueFoundry AI Gateway configuration. Use when setting up model routing, guardrails, rate limits, MCP servers, prompts, agents, or Skills Registry entries. Ensures workspace confirmation, secret creation, and configuration verification.
Diagnoses TrueFoundry AI Gateway issues. Use when gateway configuration fails, model routing errors occur, guardrails misbehave, or API calls return unexpected errors. Fetches logs, identifies root causes, and suggests fixes.
UI-first guide for TrueFoundry Agent Registry. Use when creating, publishing, sharing, editing, testing, or attaching MCP servers and skills to TrueFoundry Agents. Agent authoring is not API-driven.
Configures TrueFoundry AI Gateway end-to-end. Covers unified OpenAI-compatible LLM access, provider account integrations, content safety guardrails, and observability (traces, costs, errors) via the spans query API.
Integrates a codebase with TrueFoundry AI Gateway. Scans for all LLM calls, MCP configs, and credentials, diffs against existing gateway config, generates a migration plan, applies code changes, and verifies routing end-to-end. Invoked from within the customer's codebase.
Manages TrueFoundry MCP Gateway server registry entries. Covers listing, creating, updating, tool selection, access control, and client attachment for remote, official remote, virtual, hosted STDIO, and OpenAPI-backed MCP servers. Delete operations are manual dashboard-only.
Views application logs and adds OpenTelemetry-based tracing to applications via TrueFoundry. Supports log filtering, Traceloop SDK instrumentation for Python/TypeScript, and custom spans.
Executes bash commands
Hook triggers when Bash tool is used
Uses power tools
Uses Bash, Write, or Edit tools
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
This plugin requires configuration values that are prompted when the plugin is enabled. Sensitive values are stored in your system keychain.
TFY_BASE_URLTrueFoundry platform URL (e.g., https://your-org.truefoundry.cloud)
${user_config.TFY_BASE_URL}TrueFoundry AI Gateway is the proxy layer that sits between your applications and LLM providers and MCP servers. It's an enterprise-grade platform that gives you access to 1000+ LLMs through a unified interface while handling observability and governance.
This is the official skills repo — it lets your coding agent set up and manage the gateway through plain English.
Open terminal and install truefoundry skills:
npx skills add truefoundry/skills --yes
To create an account, open Claude Code, Codex, or Cursor and say:
sign me up for truefoundry
The harness will check the CLI, walk you through account creation if needed, run tfy login --host <tenant-url>, and stop once login is verified.
Claude Code
/plugin marketplace add truefoundry/skills
/plugin install truefoundry@truefoundry-skills
Codex
codex plugin marketplace add truefoundry/skills
Then open the plugin list with /plugins and install truefoundry.
| Skill | What it does |
|---|---|
gateway | Model routing, providers, guardrails, rate limits, budget controls |
integrate-gateway | Integrates a codebase with the AI Gateway — scans, plans, migrates, verifies |
observability | Usage dashboards, logs, OpenTelemetry tracing |
platform | CLI login, workspaces, clusters, secrets, access control |
mcp-servers | Create and manage remote, virtual, and hosted MCP servers |
prompts | Prompt registry — versioning, tagging, references |
agents | Agent registry — create, test, publish, attach MCP servers |
skills-registry | Publish and version reusable agent skills |
onboard | First-time setup flow — registration through login verification |
truefoundry/skills/
├── skills/ ← shared skill definitions (all agents read these)
│ ├── gateway/
│ ├── integrate-gateway/
│ ├── observability/
│ ├── platform/
│ ├── mcp-servers/
│ ├── prompts/
│ ├── agents/
│ ├── skills-registry/
│ └── onboard/
├── agents/ ← subagent definitions (Claude Code)
├── hooks/ ← event hooks (credential bootstrap, secret scanning)
├── commands/ ← slash commands
├── rules/ ← Cursor .mdc rules
├── .claude-plugin/ ← Claude Code manifest
├── .codex-plugin/ ← Codex manifest
└── .cursor-plugin/ ← Cursor manifest
Three hooks run automatically on Claude Code and Codex:
tfy-secret:// referencesBug fixes, doc improvements, and new skills are welcome. If you're adding a skill, follow the structure in skills/gateway/ as a reference.
TrueFoundry | Docs | Register
MIT
npx claudepluginhub truefoundry/skills --plugin truefoundryDeploy, monitor, and manage ML infrastructure on TrueFoundry. Enforces reliable deployment workflows with automatic health verification, credential checks, and failure diagnosis.
Flagship+ skill pack for OpenRouter - 30 skills for multi-model routing, fallbacks, and LLM gateway mastery
Centralized Claude Code configuration: Docker-first guards, permissions, MCP gateway, and workflow skills
OpenRouter SDK plugin - unified interface for 500+ LLM models with intelligent routing, cost optimization, and framework integrations (Vercel AI SDK, LangChain, OpenAI SDK, PydanticAI)
Spawn any third-party LLM provider with an Anthropic-compatible API (e.g. DeepSeek, GLM, Kimi, Qwen, MiniMax) as real Claude Code agent-team teammates or one-shot subagents — driven exactly like native teammates. Your main session's own auth is untouched (OAuth subscription or API key, either works); provider workers bill the provider API key via apiKeyHelper (the key never enters env/argv/history). Requires the `cc-fleet` binary on PATH, installed separately.
When calling LLM APIs from Python code. When connecting to llamafile or local LLM servers. When switching between OpenAI/Anthropic/local providers. When implementing retry/fallback logic for LLM calls. When code imports litellm or uses completion() patterns.
Harness-native ECC operator layer - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses