analyze_cof_stacking
AI agents call analyze_cof_stacking to retrieve information from Mofstructure without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
COF (Covalent Organic Framework) stacking analysis is a computational characterization operation that examines structural properties of crystal structures. It retrieves and analyzes geometric or structural information from CIF files without creating, modifying, deleting, or executing external operations.
From the tool's definition Tool name 'analyze_cof_stacking' with server context indicating 'COF stacking analysis' as a stated capability. Description is empty, but the server description explicitly lists this as an analytical function without modification or execution capabilities.
Attacks that exploit this kind of access
analyze_cof_stacking. It is categorised as a Read tool in the Mofstructure MCP Server, which means it retrieves data without modifying state.
Register the Mofstructure MCP server in PolicyLayer and add a rule for analyze_cof_stacking: 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 Mofstructure. Nothing to install.
analyze_cof_stacking 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 analyze_cof_stacking 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 analyze_cof_stacking. 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.
analyze_cof_stacking is provided by the Mofstructure MCP server (lichman0405/mofstructure-mcp). 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 →