google_gmails_get
AI agents call google_gmails_get to retrieve information from ContextCore MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool retrieves Gmail data without modifying, deleting, or executing operations. Sibling naming patterns (_get vs _create, _update, _delete) establish that _get tools are read-only. Read operations have low severity because they expose information but don't cause direct damage; however, exposure of email contents could enable social engineering or privacy violations, preventing a 'minimal' severity rating.
From the tool's definition Tool name 'google_gmails_get' indicates retrieval of Gmail messages. Context from sibling tool 'google_gmails_get_counts' (which retrieves counts) and the server's role as a 'briefing' aggregator confirms this is a data-retrieval operation.
Attacks that exploit this kind of access
google_gmails_get. It is categorised as a Read tool in the ContextCore MCP MCP Server, which means it retrieves data without modifying state.
Register the ContextCore MCP server in PolicyLayer and add a rule for google_gmails_get: 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 ContextCore MCP. Nothing to install.
google_gmails_get 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 google_gmails_get 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 google_gmails_get. 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.
google_gmails_get is provided by the ContextCore MCP server (rkpraveendev/contextcore-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 →