AI agents use samtools_faidx 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 has dual functionality: (1) indexing FASTA files, which writes a new .fai index file to disk (a Write operation), and (2) extracting/reading sequences from an already-indexed FASTA (a Read operation). Since indexing creates a new file on disk, the most severe applicable category is Write. Misuse could overwrite existing index files, but data loss is unlikely since the original FASTA is not modified.
From the tool's definition Index FASTA files or extract sequences from indexed FASTA
Attacks that exploit this kind of access
Index FASTA files or extract sequences from indexed FASTA. 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_faidx: 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_faidx 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_faidx 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_faidx. 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_faidx 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 →