axom_mcp_exec
AI agents invoke axom_mcp_exec to trigger actions in Axom MCP Server. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
The 'exec' suffix is a strong conventional indicator of code or command execution. The server context explicitly mentions automated code analysis and file operations, suggesting this tool likely runs code or shell commands.
From the tool's definition Tool name 'axom_mcp_exec' — 'exec' strongly implies execution of code or commands. Server description mentions 'automated code analysis, file operations, and environment discovery' and 'complex tool chaining'.
Attacks that exploit this kind of access
axom_mcp_exec. It is categorised as a Execute tool in the Axom MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Axom MCP Server MCP server in PolicyLayer and add a rule for axom_mcp_exec: 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 Axom MCP Server. Nothing to install.
axom_mcp_exec is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the axom_mcp_exec 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 axom_mcp_exec. 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.
axom_mcp_exec is provided by the Axom MCP Server MCP server (pugzui/axom-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 →