AI agents use update_search to create or update resources in Evernote MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Evernote MCP Server environment.
This tool modifies an existing saved search reversibly. It does not retrieve data (Read), execute arbitrary code (Execute), irreversibly delete data (Destructive), or involve financial transactions (Financial). The blast radius is medium because modifying search configurations could affect query results for users relying on those searches, but the action is reversible and does not destroy data.
From the tool's definition Tool name 'update_search' and description 'Update an existing saved search' indicate modification of an existing search configuration without deletion.
Documented attack patterns abuse exactly the kind of access update_search gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Evernote MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for update_search:
{
"version": "1",
"default": "deny",
"tools": {
"update_search": {
"limits": [
{
"counter": "update_search_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}update_search 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.
Update an existing saved search. It is categorised as a Write tool in the Evernote MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Evernote MCP Server MCP server in PolicyLayer and add a rule for update_search: 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 Evernote MCP Server. Nothing to install.
update_search 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 update_search 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 update_search. 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.
update_search is provided by the Evernote MCP Server MCP server (kensou24/evernote-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Evernote MCP Server, 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.
52 Evernote MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.