Load saved project state to restore context (enriched with Memory MCP data)
AI agents call load_project_state to retrieve information from Claude Thread Continuity without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and restores existing project state from storage. It reads data to repopulate context, with no side effects on the underlying state—no creation, modification, deletion, or execution of external operations. The action is non-destructive and reversible by nature (loading a state multiple times yields the same result).
From the tool's definition Tool name contains 'load' and description states 'Load saved project state to restore context', indicating retrieval of previously saved data with no modifications or deletions.
Documented attack patterns abuse exactly the kind of access load_project_state gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Claude Thread Continuity, and nothing reaches the server without passing your rules. This is the rule we recommend for load_project_state:
{
"version": "1",
"default": "deny",
"tools": {
"load_project_state": {}
}
}load_project_state is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Load saved project state to restore context (enriched with Memory MCP data). It is categorised as a Read tool in the Claude Thread Continuity MCP Server, which means it retrieves data without modifying state.
Register the Claude Thread Continuity MCP server in PolicyLayer and add a rule for load_project_state: 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 Thread Continuity. Nothing to install.
load_project_state 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 load_project_state 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 load_project_state. 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.
load_project_state is provided by the Claude Thread Continuity MCP server (peless/claude-thread-continuity). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 6 Claude Thread Continuity tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
6 Claude Thread Continuity tools catalogued and risk-classified — across an index of 42,500+ MCP servers.