- OpenClaw drives Smithers through the native Smithers plugin and MCP tools.
- Smithers drives OpenClaw through
OpenClawAgentinside workflow tasks.
Install the native plugin
Fastest path:mcp add --agent openclaw. It installs the native Smithers
OpenClaw plugin into ~/.openclaw/extensions/smithers/, enables it in
~/.openclaw/openclaw.json, and registers the Smithers MCP server as a baseline
tool surface:
smithers_create_workflow, smithers_eval,
smithers_optimize, and a bundled smithers-orchestrate skill nudging
OpenClaw toward reusable, eval-backed workflows over repeated one-off turns.
Register MCP by hand
Without the native plugin, OpenClaw stores MCP servers in~/.openclaw/openclaw.json under mcp.servers; add Smithers as a stdio server:
list_workflows, run_workflow, watch_run, resolve_approval,
and the rest) become available to OpenClaw’s agent. Full reference:
MCP Server.
Optional generated skill files
OpenClaw discovers skills from~/.agents/skills/ (among other locations),
exactly where the cross-agent command installs them:
openclaw skills install <slug>);
the generated Smithers CLI skill files install directly into the skills
directory rather than through the hub.
Smithers runs OpenClaw too
Smithers also spawns OpenClaw as a workflow task’s worker viaOpenClawAgent:
bunx smthrs init detects an authenticated OpenClaw runtime and scaffolds it into
.smithers/agents.ts, even without Claude Code or Codex. The adapter shells
out to openclaw agent --message <prompt> --json; pass session or a
per-call resumeSession to route work into a known OpenClaw conversation.
See also
- MCP Server: the full tool reference
- CLI Agents: using OpenClaw inside workflows
- Agent Support: the cross-agent commands