search_runs
AI agents call search_runs to retrieve information from NGS360 MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Search operations are fundamentally retrieval-based with no side effects. The empty description prevents full certainty, but the tool name strongly implies querying/filtering existing sequencing run records in the NGS360 bioinformatics platform rather than creating, executing, or destroying data. Low severity because misuse would only expose or retrieve information about existing runs, not modify or damage data.
From the tool's definition Tool name 'search_runs' indicates a query/search operation with no modifying action. The pattern matches sibling tools like 'browse_s3' and other read-only operations on this server (list, fetch patterns).
Attacks that exploit this kind of access
search_runs. It is categorised as a Read tool in the NGS360 MCP Server MCP Server, which means it retrieves data without modifying state.
Register the NGS360 MCP Server MCP server in PolicyLayer and add a rule for search_runs: 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 NGS360 MCP Server. Nothing to install.
search_runs 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 search_runs 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 search_runs. 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.
search_runs is provided by the NGS360 MCP Server MCP server (ngs360/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 →