AI agents call get_error_history to retrieve information from Mcp Freecad without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool merely queries and returns past error information from FreeCAD. Reading error logs is a non-destructive, informational operation that does not alter system state, create artifacts, execute commands, or incur financial costs. Severity is low because error history is typically non-sensitive operational data with minimal blast radius if misused by an AI agent.
From the tool's definition Tool name 'get_error_history' and description 'Get recent error history' indicate retrieval of historical error logs without modification. No side effects, creation, deletion, or execution of operations.
Documented attack patterns abuse exactly the kind of access get_error_history gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Mcp Freecad, and nothing reaches the server without passing your rules. This is the rule we recommend for get_error_history:
{
"version": "1",
"default": "deny",
"tools": {
"get_error_history": {}
}
}get_error_history is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Get recent error history. It is categorised as a Read tool in the Mcp Freecad MCP Server, which means it retrieves data without modifying state.
Register the Mcp Freecad MCP server in PolicyLayer and add a rule for get_error_history: 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 Mcp Freecad. Nothing to install.
get_error_history 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_error_history 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_error_history. 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_error_history is provided by the Mcp Freecad MCP server (jango-blockchained/mcp-freecad). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Mcp Freecad, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
34 Mcp Freecad tools catalogued and risk-classified — across an index of 43,000+ MCP servers.