AI agents call get_cdr_records to retrieve information from Oitvoip without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Call detail records contain sensitive telecommunications metadata (call duration, participants, timestamps, call outcomes). While this is fundamentally a Read operation with no data modification, CDR data has compliance and privacy implications (GDPR, HIPAA, local telecom regulations).
From the tool's definition Tool name 'get_cdr_records' with description 'Retrieve call detail records (CDR)' indicates a retrieval operation. The verb 'Retrieve' and 'get' prefix confirm read-only access without modification or execution of side effects.
Attacks that exploit this kind of access
Retrieve call detail records (CDR). It is categorised as a Read tool in the Oitvoip MCP Server, which means it retrieves data without modifying state.
Register the Oitvoip MCP server in PolicyLayer and add a rule for get_cdr_records: 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 Oitvoip. Nothing to install.
get_cdr_records 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_cdr_records 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_cdr_records. 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_cdr_records is provided by the Oitvoip MCP server (oitapps/oitvoip-mcp-server). 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 →