// MCP TOOL REFERENCE

UNLEASH TOOLS

9 tools from the Unleash MCP Server, categorised by risk level.

READ TOOLS

cleanup_flag Generate instructions for removing flagged code 2/5 detect_flag Discover existing feature flags 2/5 evaluate_change Score risk and recommend feature flag usage 2/5 get_flag_state Get feature flag metadata and strategies 2/5 wrap_change Get guidance on wrapping code in a flag 2/5

WRITE TOOLS

create_flag Create a feature flag in Unleash 4/5 set_flag_rollout Configure rollout strategy for a feature flag 5/5 toggle_flag_environment Enable or disable a flag in an environment 5/5

DESTRUCTIVE TOOLS

remove_flag_strategy Delete a feature flag strategy 5/5

// FAQ

How many tools does the Unleash MCP server have? +

The Unleash MCP server exposes 9 tools across 3 categories: Read, Write, Destructive.

How do I enforce policies on Unleash tools? +

Use Intercept, the open-source MCP proxy. Write YAML rules for each tool — rate limits, argument validation, or deny rules — then run Intercept in front of the Unleash server.

What risk categories do Unleash tools fall into? +

Unleash tools are categorised as Read (5), Write (3), Destructive (1). Each category has a recommended default policy.

Enforce policies on Unleash

Open source. One binary. Zero dependencies.

npx -y @policylayer/intercept

github.com/policylayer/intercept →