Get a specific prompt by its exact name. Args: prompt_name (str): The exact name of the prompt to retrieve ctx: FastMCP context (automatically provided) Returns: Dict[str, Any]: Dictionary containing the prompt details and template, or an error message if the prompt cannot be found
AI agents call get_prompt_by_name 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.
This tool performs a straightforward data retrieval operation from the LangSmith observability platform. It queries for and returns a prompt object by name. There are no side effects, no data modification, no code execution, and no destructive capabilities. It is a read-only access pattern.
From the tool's definition Tool description states it 'Get[s] a specific prompt by its exact name' and returns 'prompt details and template'. The operation retrieves data without modification, deletion, or execution of external operations.
Documented attack patterns abuse exactly the kind of access get_prompt_by_name 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 get_prompt_by_name:
{
"version": "1",
"default": "deny",
"tools": {
"get_prompt_by_name": {}
}
}get_prompt_by_name 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.
Get a specific prompt by its exact name. Args: prompt_name (str): The exact name of the prompt to retrieve ctx: FastMCP context (automatically provided) Returns: Dict[str, Any]: Dictionary containing the prompt details and template, or an error message if the prompt cannot be found. 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 get_prompt_by_name: 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.
get_prompt_by_name 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 get_prompt_by_name 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 get_prompt_by_name. 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.
get_prompt_by_name 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.