save_contact
AI agents use save_contact to create or update resources in Cryptosense — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Cryptosense environment.
The name 'save_contact' suggests storing or updating contact information, which is a reversible write operation typical of a Write category tool. However, confidence is moderate due to the empty description and the generic nature of the tool name without context about scope or side effects.
From the tool's definition Tool name 'save_contact' indicates a create/modify operation. Description is empty, providing no specific details about what data is saved or how it is used.
Attacks that exploit this kind of access
save_contact. It is categorised as a Write tool in the Cryptosense MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Cryptosense MCP server in PolicyLayer and add a rule for save_contact: 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 Cryptosense. Nothing to install.
save_contact is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the save_contact 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 save_contact. 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.
save_contact is provided by the Cryptosense MCP server (josephibra/cryptosense-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 →