run
10 registry entries were observed exposing a tool named run — none of them flagged as a privileged capability.
Every row is point-in-time scan output, dated below. Forge has an observed tool surface for 8,470 of 26,658 scannable entries (32%) — an entry that has not been scanned cannot appear here, so absence from this list is not evidence that an entry does not expose this tool.
- code-yeongyu/oh-my-openagentverifiedCollectionobserved · static extractionomo/lazycodex: The coding agent for tokenmaxxers;the one and only agent harness for complex codebases. For your Codex, for your OpenCode
- ai-cli-mcpverifiedMCP serverobserved · static extractionRun Claude, Codex, Gemini, Forge, and OpenCode CLIs through MCP with background jobs
- io.github.floomhq/floomverifiedMCP serverobserved · static extractionDeploy Python functions as web apps with auto-generated UI, REST API, and shareable links.
- A2A agentobserved · static extractionAutonomous Agentic Coordination Framework (WIP)
- MCP serverobserved · static extractionThe structured memory layer your AI is missing. Requires the free Wuniq desktop app.
- MCP serverobserved · static extractionMCP server for the BrainFuck programming language
- MCP serverobserved · static extractionSophisticated bash command MCP server that runs and manages shell execution.
- MCP serverobserved · static extractionN-to-1 MCP Orchestration. Unified gateway for multiple MCP servers with intelligent tool discovery.
- MCP serverobserved · static extractionExecute commands in visible VSCode terminal tabs with output capture and session reuse.
- MCP serverobserved · static extractionAI-powered native browser with 12 MCP tools. ~30 tokens per page.