List LangSmith experiment projects (reference projects) with mandatory dataset filtering. Requires either reference_dataset_id or reference_dataset_name. Args: reference_dataset_id (str, optional): Dataset ID to filter experiments by reference_dataset_name (str, optional): Dataset name to filter ...
AI agents call list_experiments to retrieve information from Langsmith without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
limit | number | — | Maximum number of experiments to return |
project_name | string | — | Filter projects by name using partial matching |
reference_dataset_id | string | — | The ID of the reference dataset to filter experiments by |
reference_dataset_name | string | — | The name of the reference dataset to filter experiments by |
Parameters from the server's own tool schema.
This tool retrieves and filters a list of experiment projects without creating, modifying, deleting, or executing any operations. It is a straightforward query operation that returns data based on filter criteria, placing it firmly in the Read category with low severity and high confidence.
From the tool's definition Tool name is 'list_experiments' and description states it 'List[s] LangSmith experiment projects' with filtering parameters.
Attacks that exploit this kind of access
List LangSmith experiment projects (reference projects) with mandatory dataset filtering. Requires either reference_dataset_id or reference_dataset_name. Args: reference_dataset_id (str, optional): Dataset ID to filter experiments by reference_dataset_name (str, optional): Dataset name to filter experiments by limit (int): Maximum number of experiments to return (default: 5) project_name (str, optional): Filter by name (partial match). It is categorised as a Read tool in the Langsmith MCP Server, which means it retrieves data without modifying state.
list_experiments accepts 4 parameters: limit, project_name, reference_dataset_id, reference_dataset_name. The full parameter table on this page comes from the server's own tool schema.
Register the Langsmith MCP server in PolicyLayer and add a rule for list_experiments: 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. Nothing to install.
list_experiments 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_experiments 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_experiments. 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_experiments is provided by the Langsmith MCP server (langsmith-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →