Pull the latest code from the remote repository into the project on the HPC cluster.
AI agents invoke git_pull to trigger actions in Tacc Mcp Bio. 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.
git pull fetches and merges remote changes into the working directory, modifying files on the HPC cluster. This is an external operation that triggers code changes on a remote system. It's more than a simple write because it executes a git operation that can overwrite local changes, trigger merge conflicts, and alter the state of a bioinformatics pipeline environment.
From the tool's definition Pull the latest code from the remote repository into the project on the HPC cluster
Attacks that exploit this kind of access
Pull the latest code from the remote repository into the project on the HPC cluster. It is categorised as a Execute tool in the Tacc Mcp Bio MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Tacc Mcp Bio MCP server in PolicyLayer and add a rule for git_pull: 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 Tacc Mcp Bio. Nothing to install.
git_pull 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 git_pull 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 git_pull. 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.
git_pull is provided by the Tacc Mcp Bio MCP server (narasimhan-lab/tacc-mcp-bio). 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 →