AI agents call list_prompts 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 'list_prompts' tool appears designed to enumerate or retrieve prompts from the LangSmith platform. This is a read-only operation that queries data without modifying, deleting, or executing anything. While the description is empty, the tool name and its placement alongside other list operations on an observability platform strongly indicate retrieval functionality.
From the tool's definition Tool name 'list_prompts' follows the list/query pattern typical of read operations. No description provided, but naming convention and context among sibling tools (list_datasets, list_examples, list_experiments, list_projects) clearly indicate a retrieval…
Documented attack patterns abuse exactly the kind of access list_prompts 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_prompts:
{
"version": "1",
"default": "deny",
"tools": {
"list_prompts": {}
}
}list_prompts 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_prompts. 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_prompts: 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_prompts 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_prompts 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_prompts. 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_prompts 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.