Archestra
by Archestra
Run MCP servers for an enterprise behind one gateway — a curated registry, dynamic tool loading, prompt-injection guardrails, and per-agent access policy.
Skills
Gateway Routing
Fronts many MCP servers behind a single endpoint, routing tool calls and centralizing credentials and audit logging.
Injection Guardrails
Inspects tool results for prompt-injection patterns and blocks or quarantines responses before they reach the model.
Dynamic Tool Loading
Exposes only the tools relevant to the current task, keeping large catalogs from flooding the model context window.
Related Agents
OpenSandbox
Runs AI-agent workloads in isolated Docker or Kubernetes sandboxes, exposing sandbox lifecycle, command, filesystem, an…
Arcade.dev
Handles agent authorization, tool calling, and governance so agents act on behalf of users. MCP runtime with Python/JS…
Docker Sandboxes
Disposable, isolated container sandboxes for running untrusted agent-generated code, with filesystem and network isolat…
OneCLI
Stores API keys in a central gateway and injects them into outbound requests at call time, so AI agents can use credent…