AI agents use find_and_replace_doc to create or update resources in VaultAssist — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your VaultAssist environment.
This tool modifies existing document content by replacing text throughout a Google Doc. It is reversible in principle (edits can be undone via version history) but has a high blast radius because a poorly scoped find-and-replace could corrupt large portions of a document. It fits the Write category as it creates/modifies data, not Destructive since it doesn't delete documents outright.
From the tool's definition Find and replace text throughout a Google Doc
Documented attack patterns abuse exactly the kind of access find_and_replace_doc gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and VaultAssist, and nothing reaches the server without passing your rules. This is the rule we recommend for find_and_replace_doc:
{
"version": "1",
"default": "deny",
"tools": {
"find_and_replace_doc": {
"limits": [
{
"counter": "find_and_replace_doc_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}find_and_replace_doc stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Find and replace text throughout a Google Doc. It is categorised as a Write tool in the VaultAssist MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the VaultAssist MCP server in PolicyLayer and add a rule for find_and_replace_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 VaultAssist. Nothing to install.
find_and_replace_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 find_and_replace_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 find_and_replace_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.
find_and_replace_doc is provided by the VaultAssist MCP server (3xcaffeine/mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from VaultAssist, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
79 VaultAssist tools catalogued and risk-classified — across an index of 43,000+ MCP servers.