package-update
Updates Swift package dependencies and returns structured update results.
This record as markdown: /tools/io-github-dave-london-http/package-update.md
What package-update does on Http
AI agents use package-update to create or update resources in Http, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Http environment.
Why package-update is rated Medium
The tool modifies package dependency state in a Swift project, which is a reversible write operation (dependencies can be changed back or rolled back). It is not destructive since package updates can be undone.
From the tool's definition Tool description states it "Updates Swift package dependencies", which is a write operation that modifies dependency configuration files and potentially downloads/installs new package versions.
Attacks that exploit this kind of access
The rule that runs package-update safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Http, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For package-update, this is the rule to start with:
package-update stays usable, but capped: an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Http, apply this rule, and every package-update call is checked against it from then on.
Questions about package-update
Updates Swift package dependencies and returns structured update results. It is categorised as a Write tool in the Http MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Http MCP server in PolicyLayer and add a rule for package-update: 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 Http. Nothing to install.
package-update 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 package-update 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 package-update. 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.
package-update is provided by the Http MCP server (@paretools/http). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Http, and thousands of servers like it.
This server
Across the catalogue