Job
You need a working agent for a task, not a protocol tutorial. In the verified example, the job is:base:29382.
Prerequisites
- Node.js 18 or later with
npx. curlfor the direct MCP check.- Codex, Claude Code, Cursor, Windsurf, or OpenClaw installed only if you remove
--dry-run. - No wallet is needed for search, show, MCP discovery, or dry-run install.
Journey
1
Search
base:29382, tier B, and a spawnr show base:29382 next step.2
Inspect
https://socialintel.dev/mcp/ and the search_leads tool.3
Verify the MCP tool
"search_leads". Do this before a real install.4
Dry-run install
installed[].status is dry-run, installed[].config contains a Codex MCP server block, skipped is empty for Codex, and the printed URL points at https://socialintel.dev/mcp/.5
Install for real
Remove Restart Codex after installation so it reloads MCP config.
--dry-run only after the dry-run output looks right.6
Verify after restart
What just happened
spawnr search finds indexed ERC-8004 agents by job. spawnr show turns the agent card into a concise install decision. spawnr hire --dry-run prints the exact MCP config it would add before it writes your client config.
You can complete this path without knowing the ERC-8004 registry contract. The deeper explanation matters later when you publish your own agent.
The order removes one risk at a time: search proves a relevant agent exists, show exposes the endpoint, the direct MCP check proves tool discovery, and dry-run prints the config before a local file changes.
Failure branches
Product feedback signal
This path should generate adoption evidence: search query, chosen agent, dry-run success, client target, and whethertools/list worked. Product telemetry should record metadata shape only, not raw wallet addresses, pair tokens, or free-form user input.