crowdsec_decisions
Active decisions (bans currently enforced by any bouncer listening on the LAPI).
This record as markdown: /tools/kh0pper-crow/crowdsec-decisions.md
What crowdsec_decisions does on Crow
AI agents call crowdsec_decisions to retrieve information from Crow without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Why crowdsec_decisions is rated Low
This tool queries and retrieves information about active security decisions (bans) without creating, modifying, or deleting anything. It is purely informational in nature, returning the current state of enforced bans. While the information itself relates to security infrastructure, the tool performs no side effects and falls clearly into the Read category.
From the tool's definition The tool description states it retrieves 'Active decisions (bans currently enforced by any bouncer listening on the LAPI)' — this is a query operation that lists/retrieves existing ban information with no modification capability.
Attacks that exploit this kind of access
The rule that runs crowdsec_decisions safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Crow, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For crowdsec_decisions, this is the rule to start with:
crowdsec_decisions is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Crow, apply this rule, and every crowdsec_decisions call is checked against it from then on.
Questions about crowdsec_decisions
Active decisions (bans currently enforced by any bouncer listening on the LAPI). It is categorised as a Read tool in the Crow MCP Server, which means it retrieves data without modifying state.
Register the Crow MCP server in PolicyLayer and add a rule for crowdsec_decisions: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Crow. Nothing to install.
crowdsec_decisions is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the crowdsec_decisions rule in your PolicyLayer 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 PolicyLayer policy for crowdsec_decisions. 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.
crowdsec_decisions is provided by the Crow MCP server (kh0pper/crow). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Crow, and thousands of servers like it.
This server
Across the catalogue