This record as markdown: /tools/io-github-dave-london-github/pm-ls.md
What pm-ls does on Github
AI agents call pm-ls to retrieve information from Github without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Why pm-ls is rated Low
Based on the naming convention 'pm-ls' (package manager list), this appears to be a read-only operation that lists packages or dependencies. The incomplete description prevents higher confidence, but the 'ls' suffix strongly indicates a listing/query operation with no side effects. If it executes arbitrary code despite its name, severity could be higher, but evidence points to a benign Read operation.
From the tool's definition Tool name 'pm-ls' suggests a package manager list command; description is incomplete ('Runs' with no further detail), making full assessment difficult.
Attacks that exploit this kind of access
The rule that runs pm-ls safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Github, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For pm-ls, this is the rule to start with:
pm-ls is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Github, apply this rule, and every pm-ls call is checked against it from then on.
Questions about pm-ls
Runs. It is categorised as a Read tool in the Github MCP Server, which means it retrieves data without modifying state.
Register the Github MCP server in PolicyLayer and add a rule for pm-ls: 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 Github. Nothing to install.
pm-ls is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the pm-ls 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 pm-ls. 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.
pm-ls is provided by the Github MCP server (@paretools/github). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Github, and thousands of servers like it.
This server
Across the catalogue