AI agents use xcode_add_spm_package to create or update resources in Xcode — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Xcode environment.
Adding an SPM dependency modifies the project's package manifest (Package.swift or Xcode project file) to include a new external dependency. This is a Write action because it creates/modifies data reversibly—dependencies can be removed. However, severity is medium rather than low because a malicious actor could inject compromised packages, leading to supply chain risks and code execution via the dependency.
From the tool's definition The tool "add" and description "Add a Swift Package Manager dependency" indicate it modifies the project configuration by introducing a new dependency.
Attacks that exploit this kind of access
Add a Swift Package Manager dependency to the project. It is categorised as a Write tool in the Xcode MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Xcode MCP server in PolicyLayer and add a rule for xcode_add_spm_package: 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 Xcode. Nothing to install.
xcode_add_spm_package 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 xcode_add_spm_package 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 xcode_add_spm_package. 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.
xcode_add_spm_package is provided by the Xcode MCP server (raunaksplanet/xcode-mcp-server). 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 →