Agent tool / platformFree source toolLiveFrom public docs
ToolHive
Stacklok
Run and manage MCP servers in isolated containers, with access policy and audit logs.
Overview
ToolHive runs every MCP server in an isolated container and, with an authentication source configured, enforces identity and access policy per request. It emits audit logs and OpenTelemetry traces, and includes a Kubernetes operator for servers and registries.
Production criteria
| Approval gatesCan a person or policy hold an action until it is approved? | Not claimed Not documented by the vendor or not yet reviewed. |
|---|---|
| Restart recoveryDoes work resume after a crash or redeploy without repeating finished steps? | Not claimed Not documented by the vendor or not yet reviewed. |
| Evidence trailCan you inspect what ran, with what inputs, and who approved it? | Built in Audit logging and OpenTelemetry traces. |
| Kill switchCan an operator withdraw permission or stop further actions? | Not claimed Not documented by the vendor or not yet reviewed. |
| Policy controlsDo declared rules decide which tools and actions are allowed? | Built in Identity and access policy per request when an auth source is configured. |
| Sandbox isolationDoes code or tool execution run inside an isolated boundary? | Built in Each MCP server runs in an isolated container. |
Marks reflect the documentation linked below as of 2026-10-29. How we mark criteria.
Limits and scope
- Per-request policy requires an authentication source to be configured.
Also in MCP gateways & tool policy
- Docker MCP Gateway — The Docker CLI plugin behind MCP Toolkit: containerized MCP servers with tool allowlists.
- agentgateway — Open-source proxy for agent and tool traffic over MCP and A2A, with CEL policy.
Free tools, a product pilot, or a focused paid diagnosis.
Choose a tool from the directory, explore Mothership’s technical pilot path, or check fit for a software diagnosis when one issue needs investigation.