Retrieve a D-Tools SI client record by its unique ID.
AI agents call get_client to retrieve information from D-Tools MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves existing data (a client record) without creating, modifying, deleting, executing code, or committing financial transactions. It is a standard Read operation with minimal risk — the worst case being unauthorized access to client information, which is containable through normal access controls.
From the tool's definition Tool name is 'get_client' and description states 'Retrieve a D-Tools SI client record by its unique ID' — a direct query/retrieval operation with no modification or side effects.
Attacks that exploit this kind of access
Retrieve a D-Tools SI client record by its unique ID. It is categorised as a Read tool in the D-Tools MCP Server MCP Server, which means it retrieves data without modifying state.
Register the D-Tools MCP Server MCP server in PolicyLayer and add a rule for get_client: 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 D-Tools MCP Server. Nothing to install.
get_client 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_client 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_client. 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_client is provided by the D-Tools MCP Server MCP server (saml1211/d-tools-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 →