Run the OakVar annotation pipeline on input files
AI agents invoke oakvar_run to trigger actions in OakVar MCP Server. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
The tool executes an external annotation pipeline process rather than merely querying or retrieving data. Execution of annotation pipelines can be computationally intensive and may produce various side effects depending on the pipeline configuration and input data.
From the tool's definition Tool performs 'Run the OakVar annotation pipeline on input files' – this executes a bioinformatics processing pipeline whose behavior and output depend entirely on the input files and pipeline configuration provided by the user.
Attacks that exploit this kind of access
Run the OakVar annotation pipeline on input files. It is categorised as a Execute tool in the OakVar MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the OakVar MCP Server MCP server in PolicyLayer and add a rule for oakvar_run: 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 OakVar MCP Server. Nothing to install.
oakvar_run is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the oakvar_run 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 oakvar_run. 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.
oakvar_run is provided by the OakVar MCP Server MCP server (miliyarsh/oakvar-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 →