Force refresh cached docs for all tracked libraries.
AI agents use refresh_all_docs to create or update resources in OmniDocs MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your OmniDocs MCP environment.
This tool overwrites/updates cached documentation for all tracked libraries. It's a bulk write operation that modifies stored cache data. While not destructive in the sense of permanent data loss (it refreshes rather than deletes), it does overwrite existing cached content for all libraries simultaneously, which could disrupt ongoing operations or introduce unexpected changes at scale.
From the tool's definition Force refresh cached docs for all tracked libraries
Attacks that exploit this kind of access
Force refresh cached docs for all tracked libraries. It is categorised as a Write tool in the OmniDocs MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the OmniDocs MCP server in PolicyLayer and add a rule for refresh_all_docs: 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 OmniDocs MCP. Nothing to install.
refresh_all_docs 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 refresh_all_docs 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 refresh_all_docs. 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.
refresh_all_docs is provided by the OmniDocs MCP server (yogesh-g-3468/omnidocs-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 →