Universal search across all Trello content (boards, cards, members). Use this to find specific items by keywords or phrases.
AI agents call trello_search to retrieve information from Trello Desktop MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The trello_search tool retrieves and queries data from Trello without creating, modifying, or deleting any content. It is a standard search/query operation that fits the Read category. Severity is low because search operations have minimal blast radius — the worst case is information disclosure of already-accessible data, with no side effects on data integrity or business operations.
From the tool's definition Tool description states 'Universal search across all Trello content' and 'Use this to find specific items by keywords or phrases' — a read-only query operation with no modification or destructive capability.
Documented attack patterns abuse exactly the kind of access trello_search gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Trello Desktop MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for trello_search:
{
"version": "1",
"default": "deny",
"tools": {
"trello_search": {}
}
} trello_search is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Universal search across all Trello content (boards, cards, members). Use this to find specific items by keywords or phrases. It is categorised as a Read tool in the Trello Desktop MCP MCP Server, which means it retrieves data without modifying state.
Register the Trello Desktop MCP server in PolicyLayer and add a rule for trello_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 Trello Desktop MCP. Nothing to install.
trello_search 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 trello_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 trello_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.
trello_search is provided by the Trello Desktop MCP server (kocakli/trello-desktop-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Trello Desktop MCP, 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.
19 Trello Desktop MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.