Refresh the corpus by running fetch → ingest → embed (mirrors
AI agents invoke sync_now to trigger actions in Claude Synergy. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool executes a pipeline of operations (fetch, ingest, embed) to update a local mirror. It runs external operations whose effects depend on what is fetched and ingested. It is not a simple write (it orchestrates processes), not destructive (it updates/refreshes rather than deletes), and not financial.
From the tool's definition 'Refresh the corpus by running fetch → ingest → embed' — triggers a multi-step pipeline execution (fetch, ingest, embed)
Attacks that exploit this kind of access
Refresh the corpus by running fetch → ingest → embed (mirrors. It is categorised as a Execute tool in the Claude Synergy MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Claude Synergy MCP server in PolicyLayer and add a rule for sync_now: 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 Synergy. Nothing to install.
sync_now is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the sync_now 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 sync_now. 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.
sync_now is provided by the Claude Synergy MCP server (mcp-tool-shop-org/claude-synergy). 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 →