AI agents call get_neo_console_command_history to retrieve information from Pharo Nc without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool appears to retrieve command history from NeoConsole, which is a passive data retrieval operation with no side effects. The 'get_' prefix strongly indicates a read operation. While the description is uninformative, the sibling tools on this server (various 'evaluate_*' and 'get_*' tools) suggest a pattern where 'get_' tools are informational queries.
From the tool's definition Tool name includes 'get_' and 'history', indicating retrieval of historical command data with no modification capability. Description is empty, but naming convention and context (NeoConsole history retrieval) suggest read-only inspection.
Attacks that exploit this kind of access
get_neo_console_command_history. It is categorised as a Read tool in the Pharo Nc MCP Server, which means it retrieves data without modifying state.
Register the Pharo Nc MCP server in PolicyLayer and add a rule for get_neo_console_command_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 Pharo Nc. Nothing to install.
get_neo_console_command_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_neo_console_command_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_neo_console_command_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_neo_console_command_history is provided by the Pharo Nc MCP server (mumez/pharo-nc-mcp-server). 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 →