List all runs (experiments) in a project with optional filtering.
AI agents call swanlab_list_runs to retrieve information from Swanlab without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries experiment run data from a SwanLab project without modifying, deleting, or executing anything. It is purely informational. The read-only constraint of the server further confirms the lack of write or execute capabilities. Severity is low because listing metadata poses minimal risk even if misused by an agent.
From the tool's definition Tool description states 'List all runs' and server description emphasizes 'read-only access'. The verb 'list' is a query operation with no side effects.
Documented attack patterns abuse exactly the kind of access swanlab_list_runs gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Swanlab, and nothing reaches the server without passing your rules. This is the rule we recommend for swanlab_list_runs:
{
"version": "1",
"default": "deny",
"tools": {
"swanlab_list_runs": {}
}
}swanlab_list_runs 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.
List all runs (experiments) in a project with optional filtering. It is categorised as a Read tool in the Swanlab MCP Server, which means it retrieves data without modifying state.
Register the Swanlab MCP server in PolicyLayer and add a rule for swanlab_list_runs: 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 Swanlab. Nothing to install.
swanlab_list_runs 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 swanlab_list_runs 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 swanlab_list_runs. 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.
swanlab_list_runs is provided by the Swanlab MCP server (nexisato/swanlab-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Swanlab, 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.
11 Swanlab tools catalogued and risk-classified — across an index of 43,000+ MCP servers.