Concord MCP
未认领Live messaging for coding agents
agentic-codingai-agentsclaude-codecode-reviewcodexcoding-agentscursordeveloper-toolsdevtoolsmcpmodel-context-protocol
01 / 选择客户端
03 / 添加配置
claude mcp add --transport stdio 'concord-mcp' -- 'npx' '-y' '@concord-ai/concord-mcp'04 / 在客户端中确认
打开客户端的 MCP 设置，确认服务器已连接并列出工具。复制配置不代表连接成功。
更多AI & ML服务器
浏览完整目录安全概况
已认领和已认证的服务器每周接受一次静态扫描，显示代码能触及的范围（外部服务、环境变量、shell 命令、代理配置目录）以及带有已知公告的依赖。认领此列表即可获得。 安全概况的工作原理
7 个工具中显示 7 个
文档中列出的工具 (7)
内容来自项目文档。服务器握手不会验证每个工具的说明或行为。
accept_task
startwork or transferwork with action: "accept"
finish_work
records evidence and optionally marks a task review-ready, complete, or closed
inspect_work
reads workspace/task state, an agent inbox/outbox, or a durable prompt/reply thread
start_work
registers presence, claims or accepts one task, and reports scope overlaps before editing
transfer_work
assigns, accepts, declines, releases, reassigns, offers handoffs, or reopens versioned work
update_task
updatework
update_work
records task context or immediately prompts/replies to another promptable workspace agent