接入你的智能体
The publisher's own command. Not a PlugMCP endpoint.
用我们的密钥与日志托管一份副本。
npx -y @didwork/[email protected]Claude Code has no install link for a local command. Copy the command below and run it in a terminal.
DIDWORK_API_KEY=<secret> DIDWORK_BASE_URL=<value> claude mcp add sh.didwork-didwork -- npx -y @didwork/mcp@0.1.1Run in a terminal.
{ "mcpServers": { "sh.didwork-didwork": { "command": "npx", "args": [ "-y", "@didwork/[email protected]" ], "env": { "DIDWORK_API_KEY": "<secret>", "DIDWORK_BASE_URL": "<value>" } } }}claude_desktop_config.json
Remote URL or a command on your machine? How the two installs differ
Tools
No tool list yet. Remote servers get one after the first health check.
FAQ
Verify that an agent's claimed outcome actually happened, using independently gathered evidence
{ "mcpServers": { "sh.didwork-didwork": { "command": "npx", "args": [ "-y", "@didwork/[email protected]" ], "env": { "DIDWORK_API_KEY": "<secret>", "DIDWORK_BASE_URL": "<value>" } } }}Copy the stdio config for Cursor, Claude Desktop, Claude Code, or VS Code on this page. It uses the publisher's install, not a PlugMCP proxy.
The publisher lists these environment variables: DIDWORK_API_KEY, DIDWORK_BASE_URL.
DidWork runs locally over stdio.
Last checked 2026-10-26. Verify that an agent's claimed outcome actually happened, using independently gathered evidence
From the publisher
README is not crawled yet. No repository on file.
Verify that an agent's claimed outcome actually happened, using independently gathered evidence