AI agents call codebrain_status to retrieve information from CodeBrain without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool only queries and reports the availability status of Ollama models. It has no side effects, does not execute code, does not modify data, and does not perform destructive operations. It is a pure information retrieval function, fitting the Read category with low severity since knowing what models are available poses minimal security risk.
From the tool's definition Tool performs 'Report which Ollama models are available locally' - a status query operation that retrieves information about local models without modifying, executing, or deleting anything.
Attacks that exploit this kind of access
Report which Ollama models are available locally. It is categorised as a Read tool in the CodeBrain MCP Server, which means it retrieves data without modifying state.
Register the CodeBrain MCP server in PolicyLayer and add a rule for codebrain_status: 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 CodeBrain. Nothing to install.
codebrain_status 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 codebrain_status 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 codebrain_status. 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.
codebrain_status is provided by the CodeBrain MCP server (tschonsen/codebrain). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →