AI agents call get_ai_tool_documentation to retrieve information from Devon without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a retrieval operation to fetch existing documentation. It does not create, modify, delete, or execute anything—it simply queries and returns informational content about DEVONthink's AI tools. There are no side effects or state changes, making it a straightforward Read category tool with low severity.
From the tool's definition The tool retrieves and queries documentation about AI tools. The verb 'Get' combined with 'documentation' indicates data retrieval with no side effects. The description explicitly states it 'Get[s] detailed documentation' which is a read operation.
Attacks that exploit this kind of access
Get detailed documentation for DEVONthink AI tools including examples and use cases. It is categorised as a Read tool in the Devon MCP Server, which means it retrieves data without modifying state.
Register the Devon MCP server in PolicyLayer and add a rule for get_ai_tool_documentation: 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 Devon. Nothing to install.
get_ai_tool_documentation 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 get_ai_tool_documentation 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 get_ai_tool_documentation. 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.
get_ai_tool_documentation is provided by the Devon MCP server (mnott/devon). 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 →