Evaluate feature flags using OpenFeature Remote Evaluation Protocol (OFREP). If flag_key is omitted, performs bulk evaluation.
Accepts URL/endpoint input (base_url); Handles credentials or secrets (auth)
Part of the Openfeature MCP server. Enforce policies on this tool with Intercept, the open-source MCP proxy.
AI agents call ofrep_flag_eval to perform operations in Openfeature. While the risk category is not fully classified, applying a rate limit gives you visibility into how often the tool is called and prevents unexpected bursts of activity from autonomous agents.
Applying a policy to ofrep_flag_eval gives you an audit trail of every call an AI agent makes. Even for low-risk tools, visibility into agent behaviour helps you debug issues, optimise workflows, and maintain compliance with your organisation's security requirements.
Apply a rate limit to control usage and monitor for unexpected behaviour.
tools:
ofrep_flag_eval:
rules:
- action: allow
rate_limit:
max: 60
window: 60See the full Openfeature policy for all 2 tools.
Agents calling other-class tools like ofrep_flag_eval have been implicated in these attack patterns. Read the full case and prevention policy for each:
Other tools in the Other risk category across the catalogue. The same policy patterns (rate-limit, validate) apply to each.
Evaluate feature flags using OpenFeature Remote Evaluation Protocol (OFREP). If flag_key is omitted, performs bulk evaluation.. It is categorised as a Other tool in the Openfeature MCP Server, which means it performs auxiliary operations.
Add a rule in your Intercept YAML policy under the tools section for ofrep_flag_eval. You can allow, deny, rate-limit, or validate arguments. Then run Intercept as a proxy in front of the Openfeature MCP server.
ofrep_flag_eval is a Other tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the ofrep_flag_eval rule in your Intercept policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the Intercept policy for ofrep_flag_eval. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
ofrep_flag_eval is provided by the Openfeature MCP server (@openfeature/mcp). Intercept sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Open source. One binary. Zero dependencies.
npx -y @policylayer/intercept