AI agents use chronica_create_thread to create or update resources in Chronica — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Chronica environment.
Creating a thread is a reversible write operation—threads can be modified, deleted, or abandoned without permanent harm. The blast radius is minimal: a stray thread creation does not corrupt existing data, expose sensitive information, or execute arbitrary operations. Severity is low because the impact is isolated to a single new memory thread with no side effects on external systems or critical data.
From the tool's definition Tool name "chronica_create_thread" and description "新しいスレッドを作成します" (creates a new thread) indicate data creation. The server is a persistent memory system where threads are memory containers.
Attacks that exploit this kind of access
新しいスレッドを作成します。. It is categorised as a Write tool in the Chronica MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Chronica MCP server in PolicyLayer and add a rule for chronica_create_thread: 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 Chronica. Nothing to install.
chronica_create_thread is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the chronica_create_thread 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 chronica_create_thread. 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.
chronica_create_thread is provided by the Chronica MCP server (nic9dev/chronica). 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 →