AI agents call check_document_versions to retrieve information from Dynalist without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool appears to retrieve or query version information about documents without modifying data. Even though the description is unavailable (lowering confidence), the name and context from a document management system strongly suggest a read-only data retrieval function. No side effects, no data modification, no execution of external code.
From the tool's definition Tool name 'check_document_versions' combined with server description indicating it 'read[s]...Dynalist documents programmatically'.
Attacks that exploit this kind of access
${INSTRUCTIONS_FIRST_GUIDANCE}. It is categorised as a Read tool in the Dynalist MCP Server, which means it retrieves data without modifying state.
Register the Dynalist MCP server in PolicyLayer and add a rule for check_document_versions: 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 Dynalist. Nothing to install.
check_document_versions 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 check_document_versions 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 check_document_versions. 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.
check_document_versions is provided by the Dynalist MCP server (wawworld/dynalist-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 →