Get one sample by accession (e.g.
AI agents call mgnify_get_sample to retrieve information from MGnify 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 or queries data from the MGnify metagenomics database without side effects. It is a straightforward data lookup operation that returns information about a specific sample. No data creation, modification, deletion, or code execution occurs. The low severity reflects that sample metadata retrieval poses minimal risk even if accessed by an unauthorized agent.
From the tool's definition Tool name 'mgnify_get_sample' with verb 'get' and description indicates retrieval of a single sample resource by accession identifier. No modification, deletion, or execution implied.
Attacks that exploit this kind of access
Get one sample by accession (e.g. It is categorised as a Read tool in the MGnify MCP Server MCP Server, which means it retrieves data without modifying state.
Register the MGnify MCP Server MCP server in PolicyLayer and add a rule for mgnify_get_sample: 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 MGnify MCP Server. Nothing to install.
mgnify_get_sample 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 mgnify_get_sample 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 mgnify_get_sample. 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.
mgnify_get_sample is provided by the MGnify MCP Server MCP server (mgs-sails/mgnify-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 →