AI agents call get_mesh_tree to retrieve information from MeSH MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves hierarchical MeSH tree data from a medical authority database. It performs no modifications, deletions, or external operations—only queries and returns information. The blast radius of misuse is minimal, limited to exposure of medical terminology data that is already public. Low severity reflects the read-only nature and non-sensitive context.
From the tool's definition Tool name 'get_mesh_tree' combined with server context indicating retrieval of MeSH (Medical Subject Headings) data from the National Library of Medicine APIs. Sibling tools are get_mesh_qualifiers, get_mesh_record, and search_mesh—all read-only operations.
Attacks that exploit this kind of access
get_mesh_tree. It is categorised as a Read tool in the MeSH MCP MCP Server, which means it retrieves data without modifying state.
Register the MeSH MCP server in PolicyLayer and add a rule for get_mesh_tree: 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 MeSH MCP. Nothing to install.
get_mesh_tree 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_mesh_tree 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_mesh_tree. 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_mesh_tree is provided by the MeSH MCP server (msuicaut/mesh-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 →