AI agents call task_context to retrieve information from Todos without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves task information without side effects. It queries and returns existing data (context, metadata, relationships) without creating, modifying, or deleting anything. The 'Get' verb and read-only nature of the operations described place it squarely in the Read category with low severity.
From the tool's definition Tool name 'task_context' and description 'Get compact context for a task' explicitly indicates data retrieval. The description lists retrieval operations: 'details, dependencies, relationships, comments, files, commits, and watchers' with optional full detail.
Risk signalsBulk/mass operation — affects multiple targets
Attacks that exploit this kind of access
Get compact context for a task by default: details, dependencies, relationships, comments, files, commits, and watchers. Pass detail=full for all data. It is categorised as a Read tool in the Todos MCP Server, which means it retrieves data without modifying state.
Register the Todos MCP server in PolicyLayer and add a rule for task_context: 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 Todos. Nothing to install.
task_context 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 task_context 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 task_context. 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.
task_context is provided by the Todos MCP server (@hasna/todos). 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 →