AI agents call samtools_idxstats 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 idxstats command generates and returns summary statistics (alignment counts per reference sequence) derived from BAM/CRAM index files. This is a pure read operation with no side effects, data modification, or execution of arbitrary commands. The tool only retrieves pre-computed statistics from index metadata.
From the tool's definition Tool name 'samtools_idxstats' and description 'Generate statistics from a BAM/CRAM index' indicate a read-only operation that queries and retrieves statistical information from existing indexed files without modifying data.
Attacks that exploit this kind of access
Generate statistics from a BAM/CRAM index. 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_idxstats: 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_idxstats 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_idxstats 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_idxstats. 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_idxstats 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 →