AI agents call accept_divergence to retrieve information from Astrolabe without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Without a description, confidence is reduced. However, the verb 'accept' in a documentation context most plausibly means acknowledging or confirming a divergence state (read-like), not creating/modifying data (Write), executing code (Execute), or destructive operations. The sibling tools are predominantly Read operations (search, list, get, read), supporting a Read classification.
From the tool's definition Tool name 'accept_divergence' suggests acceptance or acknowledgment of a state difference. No description provided.
Attacks that exploit this kind of access
accept_divergence. It is categorised as a Read tool in the Astrolabe MCP Server, which means it retrieves data without modifying state.
Register the Astrolabe MCP server in PolicyLayer and add a rule for accept_divergence: 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 Astrolabe. Nothing to install.
accept_divergence 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 accept_divergence 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 accept_divergence. 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.
accept_divergence is provided by the Astrolabe MCP server (zebrr/astrolabe-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 →