Search tasks by name, tags, due date, status, or workspace.
AI agents call search_tasks to retrieve information from Streamline MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Search functionality is inherently a read-only operation that retrieves data without side effects. Even in the context of a full CRUD system, this specific tool is limited to retrieval and does not create, modify, delete, or execute operations. The blast radius of misuse is minimal—an AI could over-search or retrieve unintended data, but no data is at risk of loss or unwanted modification.
From the tool's definition Tool performs a search operation on tasks using filters (name, tags, due date, status, workspace). The description contains no language indicating modification, deletion, or execution of arbitrary code—only querying and filtering existing data.
Attacks that exploit this kind of access
Search tasks by name, tags, due date, status, or workspace. It is categorised as a Read tool in the Streamline MCP MCP Server, which means it retrieves data without modifying state.
Register the Streamline MCP server in PolicyLayer and add a rule for search_tasks: 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 Streamline MCP. Nothing to install.
search_tasks 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 search_tasks 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 search_tasks. 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.
search_tasks is provided by the Streamline MCP server (rostehea/streamline-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 →