Read email by UID
AI agents call read_protonmail to retrieve information from Garza Home MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves email messages from a ProtonMail account based on a unique identifier (UID). Reading email is a query operation with no side effects, no code execution, no data modification, and no financial impact. It is the lowest-risk category. Confidence is high because the verb 'read' is unambiguous and the description confirms retrieval-only semantics.
From the tool's definition Tool name is 'read_protonmail' and description explicitly states 'Read email by UID' — a retrieval operation with no modification, deletion, or execution.
Attacks that exploit this kind of access
Read email by UID. It is categorised as a Read tool in the Garza Home MCP MCP Server, which means it retrieves data without modifying state.
Register the Garza Home MCP server in PolicyLayer and add a rule for read_protonmail: 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 Garza Home MCP. Nothing to install.
read_protonmail 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 read_protonmail 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 read_protonmail. 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.
read_protonmail is provided by the Garza Home MCP server (itsablabla/garza-home-mcp). 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 →