Get child concepts
AI agents call get_concept_children to retrieve information from SNOMED CT 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 hierarchical relationships in a medical terminology database (SNOMED CT). It queries existing data and returns child concept information—a pure read operation with no ability to create, modify, delete, or execute code. The blast radius of misuse is minimal; an AI agent could retrieve unwanted medical data but cannot alter records or perform actions beyond data retrieval.
From the tool's definition Tool name 'get_concept_children' and description 'Get child concepts' indicate a retrieval operation that browses SNOMED CT hierarchy without modification. The server context confirms this is a 'querying and browsing' tool with no side effects mentioned.
Attacks that exploit this kind of access
Get child concepts. It is categorised as a Read tool in the SNOMED CT MCP Server MCP Server, which means it retrieves data without modifying state.
Register the SNOMED CT MCP Server MCP server in PolicyLayer and add a rule for get_concept_children: 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 SNOMED CT MCP Server. Nothing to install.
get_concept_children 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_concept_children 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_concept_children. 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_concept_children is provided by the SNOMED CT MCP Server MCP server (orglance/snomed-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 →