This record as markdown: /tools/20alexl-claude-engram/work.md
What work does on Claude Engram
AI agents call work to retrieve information from Claude Engram without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Why work is rated Low
The tool name alone is ambiguous, but given the server's purpose (persistent memory, session tracking, pattern mining, cross-session search), a tool named 'work' without further specification most probably reads or retrieves session work data rather than modifying or deleting it.
From the tool's definition Tool name 'work' with empty description provides no explicit indication of write or destructive capability.
Attacks that exploit this kind of access
The rule that runs work safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Claude Engram, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For work, this is the rule to start with:
work is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Claude Engram, apply this rule, and every work call is checked against it from then on.
Questions about work
work is a read tool on the Claude Engram MCP server. It is categorised as a Read tool in the Claude Engram MCP Server, which means it retrieves data without modifying state.
Register the Claude Engram MCP server in PolicyLayer and add a rule for 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 Claude Engram. Nothing to install.
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 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 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.
work is provided by the Claude Engram MCP server (20alexl/claude-engram). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Claude Engram, and thousands of servers like it.
This server
Across the catalogue