AI agents call pipeline_list to retrieve information from Dobbe without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves information about available pipelines without creating, modifying, deleting, or executing any workflows. It is purely informational (Read category). Severity is low because listing available pipelines poses minimal security risk—the data returned is metadata about what pipelines exist, not sensitive operational data, and listing commands causes no side effects.
From the tool's definition Tool name 'pipeline_list' and description 'List all available pipeline commands' indicate a query/retrieval operation with no modification or side effects.
Attacks that exploit this kind of access
List all available pipeline commands. It is categorised as a Read tool in the Dobbe MCP Server, which means it retrieves data without modifying state.
Register the Dobbe MCP server in PolicyLayer and add a rule for pipeline_list: 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 Dobbe. Nothing to install.
pipeline_list 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 pipeline_list 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 pipeline_list. 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.
pipeline_list is provided by the Dobbe MCP server (nareshnavinash/dobbe-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 →