run_experiment

Call this tool when you need to understand how to run experiments and evaluations in LangSmith. This is a documentation-only tool.

Server Langsmith langsmith-mcp-server
Category Read
Risk class Low
Parameters 00 required

What run_experiment does on Langsmith

AI agents call run_experiment 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.

Why run_experiment needs a policy

Despite the name 'run_experiment' suggesting execution, the description explicitly clarifies this is a documentation-only tool that explains how to run experiments rather than actually running them. It retrieves/returns informational content with no side effects.

From the tool's definition "This is a documentation-only tool." — the tool explicitly states it only provides documentation, not actual execution

Questions about run_experiment

What does the run_experiment tool do? +

Call this tool when you need to understand how to run experiments and evaluations in LangSmith. This is a documentation-only tool. It is categorised as a Read tool in the Langsmith MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on run_experiment? +

Register the Langsmith MCP server in PolicyLayer and add a rule for run_experiment: 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.

What risk level is run_experiment? +

run_experiment is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit run_experiment? +

Yes. Add a rate_limit block to the run_experiment 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.

How do I block run_experiment completely? +

Set action: deny in the PolicyLayer policy for run_experiment. 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.

What MCP server provides run_experiment? +

run_experiment 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.

// LOOK UP ANOTHER 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 →

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.