Policy Management

Unbound has four policy types: Cost, Model, Security, and Tool. Each has its own subcommand for type-specific creation. Generic commands (list, get, delete) work across Cost, Model, and Security; Tool policies use a separate policy tool subcommand.

Reference data

Before creating policies, pull the available user groups, models, guardrails, and tool types:

unbound policy form-data

Generic commands (Cost / Model / Security)

unbound policy list                    # List all policies
unbound policy list --type COST        # Filter by type: COST, MODEL, SECURITY
unbound policy list --enabled          # Only show currently enabled policies
unbound policy list --search "budget"  # Filter by name substring
unbound policy get <id>                # View a policy's full config
unbound policy delete <id>             # Delete a policy
unbound policy effective <id>          # Effective policies for the given ID
unbound policy effective --user <id>   # Effective policies for a specific user
unbound policy effective --group <id>  # Effective policies for a specific group

There is no generic unbound policy create or unbound policy update. Creates and updates are type-specific — use policy cost create, policy model create, policy security create, or the policy tool subcommand family below.

The same type filter applies to type-specific list and update commands:

unbound policy cost list
unbound policy model list
unbound policy security list
unbound policy cost update <id> --monthly-budget 2000

Cost policies

Set a monthly spend limit per user group:

unbound policy cost create \
  --name "Engineering Budget" \
  --monthly-budget 1000 \
  --group engg

See Cost Policies for all configuration options.

Model policies

Control which AI models are available to a group:

# Allow all models except one:
unbound policy model create \
  --name "No Opus" \
  --all-models \
  --excluded anthropic/claude-3-opus-20240229

# Allow only a specific model:
unbound policy model create \
  --name "GPT-4o only" \
  --allowed openai/gpt-4o

See Model Policies for all configuration options.

Security policies

Apply guardrails for PII, secrets detection, and model routing:

# Block requests containing PII:
unbound policy security create \
  --name "Block PII" \
  --sub-type guardrails \
  --guardrail PII:BLOCK

# Redact secrets before they leave the gateway:
unbound policy security create \
  --name "Redact Secrets" \
  --sub-type guardrails \
  --guardrail SECRETS:REDACT

Routing sub-type flags

Routing has two sub-types — default-routing (swap the model on a sensitive request, shown below) and error-code-routing. Routing swaps the model rather than blocking or redacting:

unbound policy security create \
  --name "Route PII to private model" \
  --sub-type default-routing \
  --route PII \
  --route-model anthropic/claude-3-opus-20240229 \
  --error-route block

Flag	Purpose
`--route`	Which guardrail trigger swaps the model (e.g. `PII`, `SECRETS`)
`--route-model`	The model to swap to when the trigger fires
`--error-route`	Behavior when the routed model is unavailable (`block`, `passthrough`)

See Security Policies for all configuration options.

Tool policies

Tool policies control shell commands and MCP tool calls. They use a separate backend and are reached via unbound policy tool.

List and inspect

unbound policy tool list
unbound policy tool get <id>
unbound policy tool delete <id>

Discover available targets

unbound policy tool families      # Terminal command families and the fields they accept
unbound policy tool mcp-servers   # Known MCP servers and their available tools

Create a terminal command policy

unbound policy tool create-terminal \
  --name "Block rm -rf" \
  --command-family filesystem \
  --field command='rm -rf*' \
  --action BLOCK \
  --custom-message "Destructive command blocked by policy."

Create an MCP tool policy

# Match by action type (e.g. all write operations on a server):
unbound policy tool create-mcp \
  --name "Audit Linear writes" \
  --mcp-server Linear \
  --mcp-action-type write \
  --action AUDIT

# Match a specific tool:
unbound policy tool create-mcp \
  --name "Block PR creation" \
  --mcp-server GitHub \
  --mcp-tool create_pull_request \
  --action BLOCK

Available actions: BLOCK, WARN, AUDIT, REQUIRE_SLACK_APPROVAL

Update a tool policy

unbound policy tool update <id> --action WARN

Only the fields you provide are changed.

See Tool Policies for the full list of actions, NL rules, and canonical group targeting. All commands support --json for machine-readable output.

Tool Policies

Dashboard reference for actions, NL rules, and Slack approvals

Cost Policies

Dashboard reference for budget limits and spend controls

Getting Started

CLI

Policies

Analytics

API Reference

Integrations

MDM Integrations

Connections

Support & Troubleshooting

Reference data

Generic commands (Cost / Model / Security)

Cost policies

Model policies

Security policies

Routing sub-type flags

Tool policies

List and inspect

Discover available targets

Create a terminal command policy

Create an MCP tool policy

Update a tool policy

Tool Policies

Cost Policies

​Reference data

​Generic commands (Cost / Model / Security)

​Cost policies

​Model policies

​Security policies

​Routing sub-type flags

​Tool policies

​List and inspect

​Discover available targets

​Create a terminal command policy

​Create an MCP tool policy

​Update a tool policy

Tool Policies

Cost Policies

Reference data

Generic commands (Cost / Model / Security)

Cost policies

Model policies

Security policies

Routing sub-type flags

Tool policies

List and inspect

Discover available targets

Create a terminal command policy

Create an MCP tool policy

Update a tool policy