Search tasks by keyword in text and notes
AI agents call oscribble_search_tasks to retrieve information from Oscribble MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a search query across task data, returning results without modifying, deleting, or executing any operations. It is purely informational—searching/filtering is a classic Read operation with minimal blast radius if misused by an AI agent.
From the tool's definition Tool name 'oscribble_search_tasks' and description 'Search tasks by keyword in text and notes' indicate a retrieval operation with no side effects.
Attacks that exploit this kind of access
Search tasks by keyword in text and notes. It is categorised as a Read tool in the Oscribble MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Oscribble MCP Server MCP server in PolicyLayer and add a rule for oscribble_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 Oscribble MCP Server. Nothing to install.
oscribble_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 oscribble_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 oscribble_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.
oscribble_search_tasks is provided by the Oscribble MCP Server MCP server (oscargavin/oscribble-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 →