truefoundry

Manages TrueFoundry roles, teams, and collaborators. Create custom roles, organize users into teams, and grant access to resources. Use when managing permissions, creating teams, or adding collaborators.

Manages TrueFoundry personal access tokens (PATs). List, create, and delete tokens for API auth and CI/CD.

Lists, inspects, and manages TrueFoundry application deployments. Shows status, health, and details for services, jobs, and Helm releases. Also handles requests to delete, remove, or destroy applications by directing users to the TrueFoundry UI.

Deploys applications to TrueFoundry. Handles single HTTP services, async/queue workers, multi-service projects, and declarative manifest apply. Supports `tfy apply`, `tfy deploy`, docker-compose translation, and CI/CD pipelines. Use when deploying apps, applying manifests, shipping services, or orchestrating multi-service deployments.

Fetches TrueFoundry documentation, API reference, and deployment guides. Use when the user needs platform docs or how-to guidance.

Sets up GitOps CI/CD pipelines for TrueFoundry using tfy apply. Supports GitHub Actions, GitLab CI, and Bitbucket Pipelines.

Deploys infrastructure components via Helm charts on TrueFoundry. Supports any public or private OCI Helm chart including databases (Postgres, MongoDB, Redis), message brokers (Kafka, RabbitMQ), and vector databases (Qdrant, Milvus). Uses YAML manifests with `tfy apply`. Use when installing Helm charts or deploying infrastructure on TrueFoundry.

Deploys and monitors TrueFoundry batch jobs, scheduled cron jobs, and one-time tasks. Uses YAML manifests with `tfy apply`. Use when deploying jobs, scheduling cron tasks, checking job run status, or viewing execution history. For listing job applications, use `applications` skill.

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.

Platform access management for TrueFoundry. Covers connection status checks, workspace and cluster discovery, role and team management, secret groups, and personal access token lifecycle.

Manages TrueFoundry Prompt Registry. Covers listing, creating, updating, versioning, tagging, and using prompts through the AI Gateway. Agent authoring belongs to the agents skill.

Manages TrueFoundry Skills Registry workflows. Covers creating, publishing, versioning, downloading, updating, and attaching reusable Agent Skills through UI or tfy apply.

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.

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.

Answer questions about TrueFoundry — an enterprise AI platform with two products - AI Gateway (proxy for LLMs, MCP servers, and agents with governance) and AI Engineering (deploy services, async services, jobs, notebooks, SSH servers, workflows, helm charts, volumes; ML repos, model registry, fine-tuning). Trigger on any mention of TrueFoundry, the `tfy` CLI, AI Gateway entities (models, virtual models, MCP servers, guardrails), gateway policies (rate limit, budget, caching, guardrail), gateway tracing/observability, prompt management, or deploying applications/jobs/workflows on TrueFoundry — even when the product name isn't explicitly stated.

Build a new custom guardrail integration for the TrueFoundry AI Gateway by wrapping a vendor's library or service behind a small FastAPI wrapper that conforms to TFY's custom-guardrail HTTP contract. Use this skill when the user asks to integrate ANY guardrail vendor (NVIDIA NeMo Guardrails, Llama Guard, Lakera, Robust Intelligence, ShieldGemma, custom PII filters, internal policy engines, in-house safety classifiers, etc.) with TrueFoundry as a custom guardrail. Also trigger when the user says "add X as a guardrail to truefoundry", "wrap X as a guardrail", "integrate X with tfy guardrails", "build a custom guardrail for tfy", or references the truefoundry/custom-guardrails-template repo. This skill encodes the wrapper architecture, the gateway's verdict semantics, an example hosting playbook, and every gotcha learned from real end-to-end builds.