AgentExec
AgentExecMCP is a FastMCP-based execution server that provides AI assistants with secure sandboxed code execution capabilities across Python, Node.js, and Go environments, along with shell command execution and package management through pip, npm, and Go modules. Built by realugbun using Python with comprehensive safety controls including configurable timeouts (1-300 seconds), process cleanup, input size validation, and workspace isolation, the implementation features automatic temporary file management for code execution, special Go compilation handling with CGO_ENABLED=0, and concurrency controls with semaphore-based resource management. The server supports multiple transport methods (stdio, SSE, streamable HTTP) and runs in a Docker container with pre-installed development environments, making it valuable for AI coding assistants that need to execute user code safely, educational platforms requiring isolated code execution, and development workflows where AI agents need to run scripts, install dependencies, and perform system operations within controlled sandbox environments.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately. Last scanned 2026-09-28.
Scan details: Circle-IR · 2026-09-28 · Appeal
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- cloud-infra
- Source
- PulseMCP
- Repository
- github.com/realugbun/agentexecmcp
- Author type
- human
- Last scanned
- 2026-09-28
- Updated
- 2026-09-28
Use via MCP
Resolve AgentExec from your agent
Streamable HTTP transport at https://api.skillsregistry.net/mcp. No auth for read tools. Discovery: .well-known/mcp.json.
One command in your shell — Claude Code wires it up and verifies the connection. Run /mcp in any session to confirm.
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp--scope user for --scope project to commit it to .mcp.json.