Get all links in a specific lab
AI agents call get_lab_links 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 retrieves link information from an existing lab environment. It performs a read-only operation on lab configuration data without creating, modifying, deleting, or executing any actions. The low severity reflects minimal risk even if misused, as it only exposes lab topology information.
From the tool's definition Tool name 'get_lab_links' and description 'Get all links in a specific lab' indicate a retrieval operation with no modification or side effects.
Attacks that exploit this kind of access
Get all links in a specific lab. 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 get_lab_links: 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.
get_lab_links 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 get_lab_links 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 get_lab_links. 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.
get_lab_links 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 →