init_project_context · Claude Session Continuity MCP

WHAT IT DOES

What init_project_context does on Claude Session Continuity

AI agents use init_project_context to create or update resources in Claude Session Continuity — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Claude Session Continuity environment.

WHY IT NEEDS A POLICY

Why init_project_context needs a policy

This tool initializes (creates) project context data, which is a Write operation. It creates new persistent state for a project session. The severity is medium because misuse could overwrite or corrupt project context, though it appears scoped to session/context data rather than production systems. Confidence is slightly reduced because the description is in Korean and details about overwrite behavior are unclear.

From the tool's definition 초기화합니다 (initializes) — creates/sets up fixed context for a new project, optionally auto-extracting from plan.md

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

init_project_context Rate-limited

init_project_context stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "init_project_context": {
      "limits": [
        {
          "counter": "init_project_context_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Claude Session Continuity, so you can run agents against it safely.

FAQ

Questions about init_project_context

What does the init_project_context tool do? +

새 프로젝트의 고정 컨텍스트를 초기화합니다. plan.md 기반으로 자동 추출하거나 직접 입력. It is categorised as a Write tool in the Claude Session Continuity MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on init_project_context? +

Register the Claude Session Continuity MCP server in PolicyLayer and add a rule for init_project_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 Claude Session Continuity. Nothing to install.

What risk level is init_project_context? +

init_project_context is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit init_project_context? +

Yes. Add a rate_limit block to the init_project_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.

How do I block init_project_context completely? +

Set action: deny in the PolicyLayer policy for init_project_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.

What MCP server provides init_project_context? +

init_project_context is provided by the Claude Session Continuity MCP server (leesgit/claude-session-continuity-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.