// SCAN REPORT

Langsmith

15 tools. 1 can modify or destroy data without limits.

1 write tool that can modify data. Rate limits recommended.

Last updated: 5 Jul 2026

1 can modify or destroy data

14 read-only

15 tools total

Verified server · catalogue entry verified 05/07/2026 · full schemas captured for 11 of 15 tools

How to control Langsmith ↓

TOOL MAP

What Langsmith exposes to your agents

Read (14) Write / Execute (1) Destructive / Financial (0)

Running more than one server? Check your whole stack →

CONTEXT-WINDOW COST

What Langsmith costs in tokens

3,203 tokens of tool definitions, loaded on every request

1.6% of a 200k context window

701 heaviest tool: fetch_runs

Full per-tool breakdown → Model it in the token calculator →

MOST DANGEROUS TOOLS

High Risk

The most dangerous Langsmith tools

Write · Medium push_prompt This tool creates and modifies prompts in LangSmith, which is a reversible operation (prompts can be updated or reverted via version control).

1 of Langsmith's 15 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Langsmith

PolicyLayer is an MCP gateway — it sits between your AI agents and Langsmith, and nothing reaches the server without passing your rules. These are the rules we recommend:

Rate limit write operations

{
  "push_prompt": {
    "limits": [
      {
        "counter": "push_prompt_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "create_dataset": {
    "limits": [
      {
        "counter": "create_dataset_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register Langsmith — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON LANGSMITH →

Instant setup, no code required.

FULL CATALOGUE

All 15 Langsmith tools

WRITE 1 tools

Write push_prompt Call this tool when you need to understand how to create and push prompts to LangSmith. This is a documentati

READ 14 tools

Read create_dataset Call this tool when you need to understand how to create datasets in LangSmith. This is a documentation-only t Read fetch_runs Fetch LangSmith runs from one or more projects with flexible filters and automatic pagination. All results ar Read get_billing_usage Fetch organization billing usage (trace counts) with workspace names inline. Args: starting_on (str): Start Read get_prompt_by_name Get a specific prompt by its exact name. Args: prompt_name (str): The exact name of the prompt to retrieve Read get_thread_history Retrieve one page of message history for a specific conversation thread. Uses char-based pagination: pages ar Read list_datasets Fetch LangSmith datasets. If no arguments are provided, all datasets will be returned. Args: dataset_ids ( Read list_examples Fetch examples from a LangSmith dataset with advanced filtering options. Either dataset_id, dataset_name, or Read list_experiments List LangSmith experiment projects (reference projects) with mandatory dataset filtering. Requires either ref Read list_projects List LangSmith projects with optional filtering and detail level control. Args: limit (int): Maximum number Read list_prompts Fetch prompts from LangSmith with optional filtering. Args: is_public (str): Filter by prompt visibility - Read read_dataset Read a specific dataset from LangSmith. Either dataset_id or dataset_name must be provided. Args: dataset_ Read read_example Read a specific example from LangSmith. Args: example_id (str): Example ID to retrieve as_of (str, option Read run_experiment Call this tool when you need to understand how to run experiments and evaluations in LangSmith. This is a docu Read update_examples Call this tool when you need to understand how to update dataset examples in LangSmith. This is a documentatio

EXPLORE

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

FAQ

Questions about Langsmith

How do I prevent bulk modifications through Langsmith? +

The Langsmith server has 1 write tools including push_prompt. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach Langsmith.

How many tools does the Langsmith MCP server expose? +

15 tools across 3 categories: Execute, Read, Write. 14 are read-only. 1 can modify, create, or delete data.

How do I enforce a policy on Langsmith? +

Register the Langsmith MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every Langsmith tool call.

Deterministic rules across all 15 Langsmith tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON LANGSMITH →

Instant setup, no code required.

15 Langsmith tools catalogued and risk-classified — across an index of 43,000+ MCP servers.