AI agents call samtools_depth to retrieve information from Samtools without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The samtools depth utility queries and retrieves coverage depth information from alignment files without modifying, deleting, or executing external commands. It is a read-only analysis operation with no side effects, consistent with other query tools in the suite. Description is empty, which reduces confidence slightly, but the tool name and server context provide sufficient clarity.
From the tool's definition Tool name 'samtools_depth' combined with SAMtools context and sibling tools (flagstat, idxstats, view) that perform read-only analysis. The samtools depth command computes per-base depth of coverage from BAM/SAM files.
Attacks that exploit this kind of access
samtools_depth. It is categorised as a Read tool in the Samtools MCP Server, which means it retrieves data without modifying state.
Register the Samtools MCP server in PolicyLayer and add a rule for samtools_depth: 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 Samtools. Nothing to install.
samtools_depth 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 samtools_depth 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 samtools_depth. 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.
samtools_depth is provided by the Samtools MCP server (sirusb/samtools_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 →