Update the active context for a project. Use this to persist your current working state.
AI agents use set_active_context to create or update resources in Mnehmos Synch — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mnehmos Synch environment.
This tool creates or modifies data (the active context state for a project) in a reversible manner. It does not execute arbitrary operations, delete data irreversibly, or move money.
From the tool's definition Tool description states 'Update the active context for a project' and 'persist your current working state', indicating modification of stored project state data.
Attacks that exploit this kind of access
Update the active context for a project. Use this to persist your current working state. It is categorised as a Write tool in the Mnehmos Synch MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Mnehmos Synch MCP server in PolicyLayer and add a rule for set_active_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 Mnehmos Synch. Nothing to install.
set_active_context 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 set_active_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.
Set action: deny in the PolicyLayer policy for set_active_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.
set_active_context is provided by the Mnehmos Synch MCP server (mnehmos/mnehmos.synch.mcp). 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 →