The real catalog of tools for AI agents

Execute bash commands with background job support.

Sandboxed shell exec for MCP clients: run untrusted agent commands in a gVisor container.

Injects secrets into shell commands at exec time; plaintext never reaches the LLM context

Spawns an ephemeral Ubuntu VM with project clone, shell exec, file I/O, and auto-destroy on TTL.

Persistent Docker/SSH sandbox for AI agents: shell exec, file ops, audit log.

Accountless pay-per-use sandbox, storage, locks, attestation and handoff. Paid over MCP with x402.

Accountless pay-per-use sandbox execution, storage, locks, attestation and handoff; pay via x402.

Weekly 5-15 reports for executive teams: submit reports, fetch the Friday briefing.

POSIX shell quote shape, input discarded

Single exec tool running caller Python in a network-isolated locked-down sandbox.

Turns vague automation requests into tool stacks, prompts, QA checks, and human boundaries.

Sandboxed Python execution for AI agents. PEP 723 inline deps, multi-version Python, zero pollution.

Let agents use the shell like a human.

Execute PowerShell commands securely with controlled timeouts and input validation. Retrieve syste…

A minimal, transparent PowerShell 7 MCP for Windows — one tool: raw exit code, stdout, stderr.

Execute Python code on Google Colab GPU runtimes (T4/L4) from any MCP client

Deduplicated, entity-resolved funding rounds, acquisitions, and exec moves as MCP tools.

Manage Sprites: sandboxed compute environments with exec, services, and checkpoints.

MCP server for Superserve sandboxes: create, exec, and manage Firecracker microVMs

SEC-sourced funding rounds, acquisitions, exec moves, hiring and investor signals. 7 keyless tools.