AI agents call list_datasets to retrieve information from LangSmith MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool performs dataset enumeration with no side effects. While the description is empty, the naming convention combined with the server's observability platform context and sibling read operations strongly indicates this retrieves or queries dataset metadata without modification. The blast radius of misuse is minimal—listing available datasets poses no data integrity or operational risk.
From the tool's definition Tool name is 'list_datasets' which indicates a listing operation. Server description states it enables access to 'working with datasets' and 'managing datasets'.
Documented attack patterns abuse exactly the kind of access list_datasets gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and LangSmith MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for list_datasets:
{
"version": "1",
"default": "deny",
"tools": {
"list_datasets": {}
}
}list_datasets 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.
list_datasets. It is categorised as a Read tool in the LangSmith MCP Server MCP Server, which means it retrieves data without modifying state.
Register the LangSmith MCP Server MCP server in PolicyLayer and add a rule for list_datasets: 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 LangSmith MCP Server. Nothing to install.
list_datasets 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 list_datasets 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 list_datasets. 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.
list_datasets is provided by the LangSmith MCP Server MCP server (langchain-ai/langsmith-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from LangSmith 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.
15 LangSmith MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.