filter_pipelines
AI agents call filter_pipelines to retrieve information from CATS MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The name 'filter_pipelines' strongly suggests retrieving or querying pipeline records without modifying them. In an ATS context, filtering pipelines means listing or searching existing pipelines based on criteria—a read operation with no side effects. The empty description prevents higher confidence, but the naming convention and context (recruiting workflows) support the Read classification.
From the tool's definition Tool name 'filter_pipelines' indicates a query/filter operation on pipeline data, consistent with the Read category pattern of other tools on this server (attach_*, authorize_*, change_*).
Attacks that exploit this kind of access
filter_pipelines. It is categorised as a Read tool in the CATS MCP Server MCP Server, which means it retrieves data without modifying state.
Register the CATS MCP Server MCP server in PolicyLayer and add a rule for filter_pipelines: 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 CATS MCP Server. Nothing to install.
filter_pipelines 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 filter_pipelines 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 filter_pipelines. 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.
filter_pipelines is provided by the CATS MCP Server MCP server (vanman2024/cats-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 →