Low Risk

continue_work_session

프로젝트명이나 키워드로 작업 세션을 찾아서 이어가기. 세션 정보와 관련 작업기억들을 함께 로딩하여 컨텍스트를 완전히 복원합니다.

How to control continue_work_session ↓

What continue_work_session does on Work Memory MCP Server

AI agents call continue_work_session to retrieve information from Work Memory MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

Low Risk

Why continue_work_session needs a policy

The tool performs retrieval and restoration of previously stored session data and context. No creation, modification, deletion, or execution of external operations occurs. This is a read-only operation that queries and fetches existing work memories and session information to resume work context. The severity is low because retrieval of internal work data poses minimal risk even if misused by an agent.

From the tool's definition Tool description indicates 'find work session by project name or keyword' and 'load session information and related work memories to restore context completely' — operations that retrieve and load existing data without modification or deletion.

Documented attack patterns abuse exactly the kind of access continue_work_session gives an agent:

How to control continue_work_session

PolicyLayer is an MCP gateway — it sits between your AI agents and Work Memory MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for continue_work_session:

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "continue_work_session": {}
  }
}

continue_work_session is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.

  1. Create a free account and register Work Memory MCP Server — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
CAP THIS TOOL →

Free to start. No card required.

Related tools and policies

Go deeper

Questions about continue_work_session

What does the continue_work_session tool do? +

프로젝트명이나 키워드로 작업 세션을 찾아서 이어가기. 세션 정보와 관련 작업기억들을 함께 로딩하여 컨텍스트를 완전히 복원합니다. It is categorised as a Read tool in the Work Memory MCP Server MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on continue_work_session? +

Register the Work Memory MCP Server MCP server in PolicyLayer and add a rule for continue_work_session: 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 Work Memory MCP Server. Nothing to install.

What risk level is continue_work_session? +

continue_work_session is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit continue_work_session? +

Yes. Add a rate_limit block to the continue_work_session 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.

How do I block continue_work_session completely? +

Set action: deny in the PolicyLayer policy for continue_work_session. 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.

What MCP server provides continue_work_session? +

continue_work_session is provided by the Work Memory MCP Server MCP server (moontmsai/work-memory-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Work Memory MCP Server tool call.

Start from Work Memory MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

Free to start. No card required.

24 Work Memory MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.