AI agents use samtools_merge to create or update resources in Samtools — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Samtools environment.
This tool combines multiple input BAM/CRAM files into a single output file. This is a reversible write operation—the merged file can be recreated or deleted, and the original input files remain intact. It does not delete, destroy, or execute arbitrary code. While it modifies the filesystem by creating a new file, this is within the Write category.
From the tool's definition Tool name 'samtools_merge' and description 'Merge multiple sorted BAM/CRAM files' indicate creation of a new combined file from existing input files.
Attacks that exploit this kind of access
Merge multiple sorted BAM/CRAM files. It is categorised as a Write tool in the Samtools MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Samtools MCP server in PolicyLayer and add a rule for samtools_merge: 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_merge is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the samtools_merge 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_merge. 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_merge 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 →