herdr-mesh
Related Servers
Alternatives to herdr-mesh
No user-submitted related servers found.
Related Servers
- FlicenseAqualityAmaintenanceEnables coding agents to perform workspace-confined file operations, read-only Git inspection, and structured shell commands, while requiring out-of-band human approval for mutations and external executions and maintaining an audit trail.143-
- AlicenseNot gradedqualityBmaintenanceEnables provider-neutral durable coordination for coding agents sharing Git work, including peer discovery, durable messaging, job progress tracking, and FIFO integration authority with fenced leases.MIT
- AlicenseNot gradedqualityBmaintenanceEnables AI agents to safely run bounded, sandboxed tasks on remote machines with persistent state and reviewable artifacts.Apache 2.0
- AlicenseNot gradedqualityBmaintenanceEnables controlled delegation of tasks to local coding-agent CLIs and the Manus API, with strict sandboxing, approval tracking, and remote-egress safeguards.5 npmMIT
- AlicenseBqualityCmaintenanceA safety-first MCP operations cockpit for Hermes Agent installations, exposing typed, evidence-producing management primitives.73MIT
- FlicenseNot gradedqualityCmaintenanceEnables controlled AI-agent access to enterprise-shaped tools with a deny-by-default gated write path, human approval, dry-run execution, and append-only audit logging.1-
TDQS
Scored across 44 tools
Most tools target distinct lease, agent, or handoff concerns, but several families overlap: three agent-wait variants, relay/handoff/batch_handoff, agent_read vs pane_read, and multiple cleanup/reconcile tools. The detailed descriptions help, but an agent must read closely to avoid selecting the wrong tool.
The dominant pattern is herdr_<object>_<action> (agent_list, controller_acquire, owned_worker_release), but there are notable exceptions like relay, handoff, batch_handoff, collect_handoffs, and wait_output, plus noun-style names like bridge_status and integration_status. The herdr_ prefix and snake_case keep it readable, but the convention is mixed.
44 tools is well above the threshold for a focused server and feels heavy for what is ultimately one orchestration domain. Many tools could be consolidated, such as the three agent-wait variants, multiple handoff submission/collection modes, and the various list/status/cleanup helpers.
The surface covers the core lifecycle well: controller leases, worker/reviewer leases, handoffs, agent inspection, and pane/tab/workspace discovery all have appropriate operations. Minor gaps exist around general pane writes or workspace/session mutation, but those appear intentionally outside the safety-focused lease model.