AI agents call read_example 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 |
|---|---|---|---|
as_of | string | — | Dataset version tag or ISO timestamp |
example_id | string | Yes | Example ID to retrieve |
Parameters from the server's own tool schema.
This tool retrieves data from LangSmith (a specific example record) with no side effects or modifications. It matches the Read category definition: retrieves or queries data with no side effects. The blast radius if misused is minimal—an AI agent could only access existing example data it is authorized to query.
From the tool's definition Tool name is 'read_example' and description states 'Read a specific example from LangSmith.' The arguments are example_id and optional as_of timestamp, with no mutation or deletion capabilities.
Attacks that exploit this kind of access
Read a specific example from LangSmith. Args: example_id (str): Example ID to retrieve as_of (str, optional): Dataset version tag or ISO timestamp. It is categorised as a Read tool in the Langsmith MCP Server, which means it retrieves data without modifying state.
read_example accepts 2 parameters: as_of, example_id. Required: example_id. 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 read_example: 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.
read_example 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 read_example 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 read_example. 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.
read_example 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 →