raw_request
Escape hatch to call any Google Calendar API v3 path directly, for requests the typed tools don't cover — e.g. events.quickAdd ("calendar/v3/calendars/primary/events/quickAdd?text=Lunch tomorrow noon", POST), the colors palette ("calendar/v3/colors"), ACL rules, secondary-calendar creation ("cale...
This record as markdown: /tools/a1-x-tech-mcp-google-calendar/raw-request.md
What raw_request does on Mcp Google Calendar
AI agents call raw_request to retrieve information from Mcp Google Calendar without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
body | object | — | JSON request body (POST/PUT/PATCH only). |
path | string | Yes | API path relative to https://www.googleapis.com, starting with "calendar/v3/", e.g. "calendar/v3/calendars/primary/events". |
method | string | — | HTTP method. Defaults to GET. |
Parameters from the server's own tool schema.
Why raw_request is rated Low
Even though raw_request only reads data, uncontrolled read access leaks sensitive information and racks up API costs: an agent caught in a retry loop can make thousands of calls a minute without anyone noticing.
Risk signalsAccepts file system path (path) · Accepts raw HTML/template content (body) · Bulk/mass operation — affects multiple targets
Attacks that exploit this kind of access
The rule that runs raw_request safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Mcp Google Calendar, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For raw_request, this is the rule to start with:
raw_request 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 Mcp Google Calendar, apply this rule, and every raw_request call is checked against it from then on.
Questions about raw_request
Escape hatch to call any Google Calendar API v3 path directly, for requests the typed tools don't cover — e.g. events.quickAdd ("calendar/v3/calendars/primary/events/quickAdd?text=Lunch tomorrow noon", POST), the colors palette ("calendar/v3/colors"), ACL rules, secondary-calendar creation ("calendar/v3/calendars", POST), removing a Meet conference (PATCH with {"conferenceData":null} and ?conferenceDataVersion=1), watch channels, or an event PUT that replaces every field. The path is relative to https://www.googleapis.com, must stay under calendar/v3/ (other Google APIs on this host — drive/v3, gmail/v1, ... — are rejected before any request is sent) and may carry a query string. The Bearer token is added automatically; the method defaults to GET. Remember: PUT replaces unspecified fields with defaults — prefer PATCH semantics via update_event when possible. It is categorised as a Read tool in the Mcp Google Calendar MCP Server, which means it retrieves data without modifying state.
raw_request accepts 3 parameters: body, path, method. Required: path. The full parameter table on this page comes from the server's own tool schema.
Register the Mcp Google Calendar MCP server in PolicyLayer and add a rule for raw_request: 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 Mcp Google Calendar. Nothing to install.
raw_request 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 raw_request 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 raw_request. 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.
raw_request is provided by the Mcp Google Calendar MCP server (@a1-x-tech/mcp-google-calendar). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Mcp Google Calendar, and thousands of servers like it.
This server
Across the catalogue