List Omniboard agentic runs for the resolved project, optionally scoped to one check name.
AI agents call omniboard_list_agentic_runs to retrieve information from Omniboard MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves or queries existing agentic run records from Omniboard for the current project. Listing operations have no side effects—they do not create, modify, delete, or trigger external operations. The optional scoping parameter allows filtering results but does not change the underlying data. This is a straightforward Read operation with low severity and high confidence.
From the tool's definition Tool name 'omniboard_list_agentic_runs' and description 'List Omniboard agentic runs' indicate retrieval/querying of run data with no modification.
Attacks that exploit this kind of access
List Omniboard agentic runs for the resolved project, optionally scoped to one check name. It is categorised as a Read tool in the Omniboard MCP MCP Server, which means it retrieves data without modifying state.
Register the Omniboard MCP server in PolicyLayer and add a rule for omniboard_list_agentic_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 Omniboard MCP. Nothing to install.
omniboard_list_agentic_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 omniboard_list_agentic_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 omniboard_list_agentic_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.
omniboard_list_agentic_runs is provided by the Omniboard MCP server (omniboard-dev/mcp). 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 →