This record as markdown: /tools/io-github-dave-london-npm/bisect.md
What bisect does on Npm
AI agents invoke bisect to trigger actions in Npm. 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.
Why bisect is rated High
The bisect tool runs git bisect operations, which executes git commands to check out different commits and navigate repository history. This involves running external operations (git checkout, git bisect) that change the working directory state.
From the tool's definition Binary search for the commit that introduced a bug... action taken, current commit, remaining steps estimate
Attacks that exploit this kind of access
The rule that runs bisect safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Npm, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For bisect, this is the rule to start with:
bisect stays usable, but rate-capped: a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Npm, apply this rule, and every bisect call is checked against it from then on.
Questions about bisect
Binary search for the commit that introduced a bug. Returns structured data with action taken, current commit, remaining steps estimate, and result. It is categorised as a Execute tool in the Npm MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Npm MCP server in PolicyLayer and add a rule for bisect: 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 Npm. Nothing to install.
bisect 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 bisect 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 bisect. 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.
bisect is provided by the Npm MCP server (Dave-London/Pare). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Npm, and thousands of servers like it.
This server
Across the catalogue