Policies

Configure rate limits, budgets, caching, tool governance, and guardrails globally or per consumer

A policy attaches behavior to a gateway’s traffic. Each policy configures one built-in plugin with settings, runs at one or more lifecycle stages, and can apply to the whole gateway or selected consumers.

Policies screen

Open Agent Gateway → Policies.

Tab	Purpose
Policies	Search configured policies, filter by protocol (LLM / MCP), pause or resume them, and open their details.
Catalog	Browse plugins by category (guardrails first). Add policy starts create.

Create or edit

1. Catalog → pick a plugin, or New policy.
2. Set Name (catalog types use a fixed prefix where required).
3. Scope
   • Mode: Enforce · Observe · Throttle (when the plugin supports it).
   • Coverage: Gateway-wide or Targeted (pick consumers).
4. Fill Configuration (dedicated form or schema-driven fields).
5. Save. Use Pause / Resume / Delete from the detail panel without losing history of attachments.

Attach from a consumer

Open a consumer → Policies → Add Policy, or Clone policies from another consumer. Global policies still apply automatically.

Catalog (UI plugins)

Traffic control

Policy	UI / slug	Docs
Rate Limiter	rate_limiter	Rate limiting & budgets
Request size	request_size_limiter	Request size
Per-Tool Rate Limiter	per_tool_rate_limiter	Tool governance

Quota

Policy	UI / slug	Docs
LLM Budget	token_rate_limiter	Rate limiting & budgets

Prompt management

Policy	UI / slug	Docs
Prompt Template	prompt_template	Prompt management
Prompt Compression	prompt_compression	Prompt management

Tool governance

Policy	UI / slug	Docs
Tool Injection	tool_injection	Tool governance

Guardrails

Policy	UI / slug	Docs
TrustGuard	trustguard	Guardrails · TrustGuard gateway integration
OpenAI Moderation	openai_moderation	Guardrails
Azure Content Safety	azure_content_safety	Guardrails
Bedrock Guardrail	bedrock_guardrail	Guardrails
Regex Replace	regex_replace	Guardrails

TrustGuard in the UI. Adding the TrustGuard policy walks you through selecting or creating an Agent Runtime collector. Connection details are injected by the platform; you do not paste base URLs by hand in normal SaaS use.

The live Catalog tab is authoritative for what you can add in your tenant.

Stages

Stage	When
Pre-request	Before the request is forwarded upstream.
Pre-response	After the upstream responds, before returning to the client.
Post-response	After the response is returned (cache populate, budget accrual).

Mode

Mode	Behavior
Enforce	Reject, transform, or block violations (default).
Throttle	Delay rather than reject (rate/budget plugins).
Observe	Record violations without enforcing them.

Ordering

Lower priority runs earlier. Same-priority policies may run in parallel when enabled. Global policies are the baseline; targeted policies refine per consumer.