Add new document
AI agents use add_doc to create or update resources in Firebase Realtime Database — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Firebase Realtime Database environment.
This tool creates new documents in the database, which is a reversible write operation. The severity is medium because unintended document creation could pollute the database and consume resources, but the action is not destructive (data can be deleted) and not financial. Confidence is high given the clear semantic intent of the tool name and description in the Firebase context.
From the tool's definition Tool named 'add_doc' with description 'Add new document' indicates creation of new data in the Firebase Realtime Database.
Attacks that exploit this kind of access
Add new document. It is categorised as a Write tool in the Firebase Realtime Database MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Firebase Realtime Database MCP server in PolicyLayer and add a rule for add_doc: 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 Firebase Realtime Database. Nothing to install.
add_doc 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 add_doc 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 add_doc. 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.
add_doc is provided by the Firebase Realtime Database MCP server (ytzlax/firebase-realtimedb-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 →