Skip to main content

Documentation Index

Fetch the complete documentation index at: https://www.truefoundry.com/llms.txt

Use this file to discover all available pages before exploring further.

What Is An Agent Harness?

An agent harness is the runtime layer around an LLM that turns it into a reliable, long-running agent. Instead of only generating text, the harness manages the full execution loop: planning, tool calling, context management, approvals, state, and observability. Most production harnesses include:
  • An orchestration loop (plan -> act -> observe -> continue/stop)
  • Tool routing and execution (for APIs, MCP tools, and code)
  • Memory and context controls for long-running tasks
  • Security boundaries (sandboxing, credentials, permissions)
  • Human-in-the-loop gates for sensitive actions
  • Tracing, logs, metrics, and cost visibility

TrueFoundry Agent Harness

TrueFoundry Agent Harness is a managed harness built on top of the AI Gateway and MCP Gateway. You choose a model, connect MCP servers, add skills, and write instructions. TrueFoundry manages orchestration, sandbox lifecycle, tool execution, approvals, governance, and observability.
TrueFoundry Agent Harness builder showing model selection, MCP servers, skills, instructions, and a playground test button

Harness Capabilities

Agent Harness combines the core capabilities needed to ship agents safely in production:

Models

Use all model providers through AI Gateway, with support for advanced routing patterns.

MCP Servers

Connect governed MCP tools with centralized auth, policy controls, and approvals.

Skills

Add reusable, versioned skills to keep agent behavior stable in production.

Sandbox

Managed secure execution environment for code, files, and long-running tasks.

Subagents

Delegate complex work to isolated subagents with clean context boundaries.

Context Engineering

Understand what fills the agent’s context and how the harness keeps it within model limits.

Deferred Tool Loading

Load tool definitions on demand to reduce context overhead and improve efficiency.

Handling Large Tool Results

Safely process oversized tool outputs without losing critical information.

Human in the Loop

Pause sensitive tool calls and require explicit user approval before execution.

Ask User Questions

Request missing inputs during execution when the agent needs clarification.

Code Mode Tool Calling

Programmatically call tools from code while preserving agent control flow.

Generative UI

Generate structured UI responses that are easy to render in applications.

No Keys, Full Governance

A key difference between TrueFoundry Agent Harness and other hosted runtimes is that no API keys or credentials are ever pasted into agent definitions. Models, MCP servers, and skills are all managed through TrueFoundry’s central control plane:
  • Models — Provider credentials live in AI Gateway. Agents reference model names. RBAC controls who can use which models. Budgets, rate limits, and guardrails are enforced at the gateway.
  • MCP Servers — Authentication (OAuth tokens, API keys) lives in MCP Gateway. Agents call tools by name. The gateway handles credential injection, token refresh, and user delegation.
  • Skills — Published in the Skills Registry with full versioning and RBAC. Agents pick from a governed catalog. Platform teams control what’s available to whom.
In Claude Managed Agents or LangSmith Managed Deep Agents, developers must register credentials (vault IDs, header arrays with bearer tokens) per agent or workspace. In TrueFoundry, platform teams configure access once and agent builders never handle secrets.

Architecture

Agent Harness runs in the same gateway plane as model and MCP traffic, so orchestration, governance, and observability stay in one system.
TrueFoundry Agent Platform architecture showing sandbox, subagents, generative UI, context management, human-in-the-loop approvals, model gateway, MCP gateway, skills registry, and observability

How It Compares

Claude Managed Agents and LangSmith Managed Deep Agents are both strong hosted runtimes. The differences become clear when you look at how each platform handles credential management, tool governance, and model access in practice.

MCP credential management

TrueFoundryClaude Managed AgentsLangSmith Managed Deep Agents
Where credentials liveMCP Gateway — centrally managed with OAuth flows, token refresh, and user-scoped delegationVaults — per-user credential containers. You create a vault per user, register credentials per MCP server URL, and pass vault_ids at session creation.MCP server registrationPOST /v1/deepagents/mcp-servers with raw headers arrays containing bearer tokens.
Multi-user credential isolationBuilt into MCP Gateway. Per-user OAuth tokens managed and refreshed automatically.You must create and manage a separate vault per end-user programmatically.Not supported in preview. One credential set per workspace.
In-app auth flowUser authenticates inline in chat (OAuth popup → continue).Not available. Developer must handle token acquisition externally and register in vault.Not available. Static headers only (OAuth planned for future release).
Credential rotationManaged by gateway (OAuth refresh) or admin updates once centrally.PATCH the credential per vault. Must be done per-user for user-scoped tokens.PATCH /mcp-servers/{id} replaces entire headers array.

Tool approval and safety policies

TrueFoundryClaude Managed AgentsLangSmith Managed Deep Agents
Default behaviorTools marked as destructive at MCP Gateway layer automatically require approval. No per-agent configuration needed.MCP tools default to always_ask. You configure per-tool policies via permission_policy in the agent JSON definition.Configure interrupt_config per tool using {mcp_server_url}::{tool_name} keys set to true/false.
GranularityGateway-level policy. Applies uniformly to all agents using that tool — set once, enforced everywhere.Per-agent, per-tool JSON config. Each agent definition must explicitly declare policies.Per-agent, per-tool in agent payload. Each agent must list every tool’s interrupt preference.
Governance scopePolicies are org-wide. Platform team configures which tools are destructive — agent builders don’t need to think about it.Developer responsibility. If you forget to set always_ask on a sensitive tool, it runs without confirmation.Developer responsibility. Missed interrupt_config entries mean no approval gate.

Model access and governance

TrueFoundryClaude Managed AgentsLangSmith Managed Deep Agents
Supported modelsAll providers through AI GatewayAnthropic models only (claude-opus-4-7, claude-sonnet-4-6, etc.)Any model via {provider}:{model_id} format through init_chat_model
Access controlRBAC — control which teams/users can use which models. Budgets and rate limits per team.No model-level RBAC. Any API key holder can use any model.No model-level RBAC within the platform.
Cost governancePer-user and per-team budgets, rate limits, and cost attribution enforced at gateway.Not available at platform level. Track externally.Not available in preview.
Guardrails on model callsGateway-level content policies, PII filters, custom guardrails applied before/after every model call.Not available at harness level.Not available in managed runtime.

Deployment flexibility

TrueFoundryClaude Managed AgentsLangSmith Managed Deep Agents
Deployment optionsSaaS (globally distributed), self-hosted, on-premManaged Anthropic cloud + separate self-hosted SDK pathManaged cloud (US-only in preview) + self-host via langgraph build
Data residencyDeploy in your own cloud/region. Full control.US region only during beta. EU planned post-GA.US region only during private preview.
On-premSupportedNot supportedNot supported

Start Building

Create an agent by choosing a model, connecting MCP servers, adding skills, and writing instructions. Then test in playground, integrate via API, monitor through traces and metrics, and ship it to users.

Build From UI

Create and test a managed agent from the TrueFoundry console.

Use The API

Create sessions, stream progress, and integrate Agent Harness into your application.