AI agents call session_load to retrieve information from Dobbe without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves previously stored context and scan results for use in subsequent commands. It performs a query/fetch operation with no side effects, no code execution, and no data modification. The primary purpose is to read and restore state from a prior session, fitting squarely in the Read category.
From the tool's definition Tool name 'session_load' and description 'Load cross-command context (e.g., prior scan results for use in resolve)' indicate retrieval of stored session data without modification or destructive action.
Attacks that exploit this kind of access
Load cross-command context (e.g., prior scan results for use in resolve). It is categorised as a Read tool in the Dobbe MCP Server, which means it retrieves data without modifying state.
Register the Dobbe MCP server in PolicyLayer and add a rule for session_load: 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 Dobbe. Nothing to install.
session_load 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 session_load 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 session_load. 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.
session_load is provided by the Dobbe MCP server (nareshnavinash/dobbe-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 →