Get ALL active claims and intents for the current session.
AI agents call get_active_work to retrieve information from memro MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries existing in-memory state (active claims and intents) without side effects. It is a read-only operation that provides visibility into current session context. The blast radius of misuse is low—an agent retrieving this data cannot directly harm other systems or cause irreversible changes, only access information about the current session's active work items.
From the tool's definition Tool name 'get_active_work' and description 'Get ALL active claims and intents for the current session' indicate retrieval of session state data with no modification, deletion, or execution of external operations.
Attacks that exploit this kind of access
Get ALL active claims and intents for the current session. It is categorised as a Read tool in the memro MCP Server MCP Server, which means it retrieves data without modifying state.
Register the memro MCP Server MCP server in PolicyLayer and add a rule for get_active_work: 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 memro MCP Server. Nothing to install.
get_active_work 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 get_active_work 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 get_active_work. 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.
get_active_work is provided by the memro MCP Server MCP server (memrohq/memro-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 →