List all labs in CML
AI agents call list_labs to retrieve information from Claude-Modeling-Labs MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and returns information about labs without creating, modifying, deleting, or executing any operations. It is a straightforward read operation with minimal security risk—the data returned is already accessible to authenticated users within the CML system.
From the tool's definition Tool name 'list_labs' and description 'List all labs in CML' indicate retrieval of existing lab information with no modification, deletion, or execution of commands.
Attacks that exploit this kind of access
List all labs in CML. It is categorised as a Read tool in the Claude-Modeling-Labs MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Claude-Modeling-Labs MCP Server MCP server in PolicyLayer and add a rule for list_labs: 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 Claude-Modeling-Labs MCP Server. Nothing to install.
list_labs 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 list_labs 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 list_labs. 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.
list_labs is provided by the Claude-Modeling-Labs MCP Server MCP server (mediocretriumph/claude-cml-toolkit). 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 →