AI agents call infoset_batch_get_contacts to retrieve information from Infoset without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves/queries contact information from the CRM system. The verb 'Get' and the batch retrieval pattern clearly indicate a read-only operation with no side effects. The deduplication mentioned is a processing convenience, not a data modification. Blast radius is minimal since it only returns existing contact data.
From the tool's definition Tool name 'batch_get_contacts' and description 'Get multiple Infoset contacts in a single call' indicate retrieval of contact data with no modification, deletion, or execution capability.
Attacks that exploit this kind of access
Get multiple Infoset contacts in a single call (auto-deduplicates). It is categorised as a Read tool in the Infoset MCP Server, which means it retrieves data without modifying state.
Register the Infoset MCP server in PolicyLayer and add a rule for infoset_batch_get_contacts: 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 Infoset. Nothing to install.
infoset_batch_get_contacts 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 infoset_batch_get_contacts 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 infoset_batch_get_contacts. 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.
infoset_batch_get_contacts is provided by the Infoset MCP server (sudohakan/infoset-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 →