AI Agent Runner: Starts a Claude, Codex, Forge, OpenCode, or Antigravity CLI process in the background and returns a PID immediately. Use list_processes and get_result to monitor progress. • File ops: Create, read, (fuzzy) edit, move, copy, delete, list files, analyze/ocr images, file content ana...
AI agents invoke run to trigger actions in Agent Bridge. 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.
This tool launches external processes that execute code and commands whose effects depend entirely on the arguments passed. It can create files, modify git repositories, run arbitrary terminal commands, and perform multi-step workflows. While the description is cut off mid-sentence, the explicit capability to 'Run any CLI cmd' and execute git operations (commit, push, tag) makes this an Execute-category tool.
From the tool's definition Starts a Claude, Codex, Forge, OpenCode CLI process in the background; capabilities include 'Run any CLI cmd', 'Terminal', and 'Git' operations with arbitrary workflow execution.
Attacks that exploit this kind of access
AI Agent Runner: Starts a Claude, Codex, Forge, OpenCode, or Antigravity CLI process in the background and returns a PID immediately. Use list_processes and get_result to monitor progress. • File ops: Create, read, (fuzzy) edit, move, copy, delete, list files, analyze/ocr images, file content analysis • Code: Generate / analyse / refactor / fix • Git: Stage ▸ commit ▸ push ▸ tag (any workflow) • Terminal: Run any CLI cmd or open URLs • Web search + summarise content on-the-fly • Multi-step workflows & GitHub integration IMPORTANT: This tool now returns immediately with a PID. Use other tools to check status and get results. Supported models: ${getSupportedModelsDescription()} Prompt input: You must provide EITHER prompt (string) OR prompt_file (file path), but not both. Prompt tips 1. Be concise, explicit & step-by-step for complex tasks. 2. Check process status with list_processes 3. Get results with get_result using the returned PID 4. Kill long-running processes with kill_process if needed. It is categorised as a Execute tool in the Agent Bridge MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Agent Bridge MCP server in PolicyLayer and add a rule for run: 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 Agent Bridge. Nothing to install.
run 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 run 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 run. 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.
run is provided by the Agent Bridge MCP server (lailai258/agent-bridge-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 →