list_all_tools
AI agents call list_all_tools to retrieve information from MEOK Governance Engine without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool appears to enumerate available tools within the governance engine, which is a query/discovery operation that retrieves information without modifying, deleting, or executing external actions. This is characteristic of Read category tools. Low severity due to minimal blast radius—listing tools is a standard discovery operation with no destructive potential.
From the tool's definition Tool name is 'list_all_tools' which is a listing/enumeration operation typical of Read category operations. Description is empty, limiting evidence, but the name strongly indicates data retrieval with no side effects.
Attacks that exploit this kind of access
list_all_tools. It is categorised as a Read tool in the MEOK Governance Engine MCP Server, which means it retrieves data without modifying state.
Register the MEOK Governance Engine MCP server in PolicyLayer and add a rule for list_all_tools: 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 MEOK Governance Engine. Nothing to install.
list_all_tools 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 list_all_tools 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 list_all_tools. 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.
list_all_tools is provided by the MEOK Governance Engine MCP server (meok-governance-engine-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 →