AI Skill Hub 强烈推荐:双重MCP工具 是一款优质的MCP工具。AI 综合评分 8.0 分,在同类工具中表现稳健。如果你正在寻找可靠的MCP工具解决方案,这是一个值得深入了解的选择。
双重MCP工具 是一款遵循 MCP(Model Context Protocol)标准协议的 AI 工具扩展。通过 MCP 协议,它可以让 Claude、Cursor 等主流 AI 客户端直接访问和操作外部工具、数据源和服务,实现 AI 能力的无缝扩展。无论是文件操作、数据库查询还是 API 调用,都可以通过自然语言在 AI 对话中直接触发,极大提升生产效率。
双重MCP工具 是一款遵循 MCP(Model Context Protocol)标准协议的 AI 工具扩展。通过 MCP 协议,它可以让 Claude、Cursor 等主流 AI 客户端直接访问和操作外部工具、数据源和服务,实现 AI 能力的无缝扩展。无论是文件操作、数据库查询还是 API 调用,都可以通过自然语言在 AI 对话中直接触发,极大提升生产效率。
# 方式一:通过 Claude Code CLI 一键安装
claude skill install https://github.com/BicameralAI/bicameral-mcp
# 方式二:手动配置 claude_desktop_config.json
{
"mcpServers": {
"--mcp--": {
"command": "npx",
"args": ["-y", "bicameral-mcp"]
}
}
}
# 配置文件位置
# macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
# Windows: %APPDATA%/Claude/claude_desktop_config.json
# 安装后在 Claude 对话中直接使用 # 示例: 用户: 请帮我用 双重MCP工具 执行以下任务... Claude: [自动调用 双重MCP工具 MCP 工具处理请求] # 查看可用工具列表 # 在 Claude 中输入:"列出所有可用的 MCP 工具"
// claude_desktop_config.json 配置示例
{
"mcpServers": {
"__mcp__": {
"command": "npx",
"args": ["-y", "bicameral-mcp"],
"env": {
// "API_KEY": "your-api-key-here"
}
}
}
}
// 保存后重启 Claude Desktop 生效
bicameral-mcp is the MCP transport client for the local bicameral-bot daemon. It exposes agent-friendly tools, maps them into canonical ToolRequest envelopes, sends those requests to the daemon, and returns daemon ToolResponse payloads.
MCP is not the Bicameral daemon, Decision Ledger, code graph, dashboard, integration runtime, setup wizard, telemetry sink, or governance engine.
Set the bot daemon endpoint with:
export BICAMERAL_DAEMON_URL=http://127.0.0.1:37373
Optional context:
export BICAMERAL_ACTOR_ID="$(whoami)"
export BICAMERAL_WORKSPACE="$PWD"
export BICAMERAL_POLICY_SCOPE=default
Run the MCP server:
bicameral-mcp
Print supported tool names without contacting the daemon:
bicameral-mcp tools
MCP stays fail-fast on daemon capability handshake failures. It never starts, installs, upgrades, migrates, or repairs the daemon, and never falls back to legacy MCP-owned handlers. Instead, a failed tool call returns a typed MCP error with an informational recovery payload:
{
"status": "error",
"error_code": "daemon_protocol_mismatch",
"recovery": {
"error_code": "daemon_protocol_mismatch",
"category": "setup",
"retryable": false,
"mcp_protocol_version": "v2",
"daemon_protocol_version": "v1",
"daemon_endpoint": "http://127.0.0.1:37373",
"requested_tool": "bicameral.preflight",
"requested_command": "preflight.run",
"operator_action": "Upgrade bicameral-mcp and bicameral-bot/daemon to matching tags, then retry."
}
}
error_code | Meaning | What to do |
|---|---|---|
daemon_unavailable | MCP cannot reach the configured/local bot daemon. | Start or install the Bicameral bot daemon, then retry. |
daemon_protocol_mismatch | Daemon is reachable but its ToolRequest protocol version is incompatible. | Upgrade bicameral-mcp and bicameral-bot/daemon to matching tags, then retry. |
daemon_capability_error | Daemon answered capabilities but the requested command is unadvertised or deferred. | Use a supported command, or upgrade to a daemon tag that advertises the capability. |
| Wrong daemon URL | Connection target is misconfigured via an env override. | Unset or correct BICAMERAL_DAEMON_URL / BICAMERAL_BOT_DAEMON_URL, then retry. |
When a daemon URL env override is set, the recovery payload adds a daemon_url_override field and calls out the env var in operator_action, so a wrong URL is easy to spot even though it shares the daemon_unavailable transport path.
Remediation such as installing, upgrading, starting, or migrating the daemon is bot-owned or CLI-owned, not MCP-owned.
高质量的开源MCP工具,功能丰富,易于使用
该工具未明确声明开源协议,商业使用前请联系原作者确认授权范围,避免侵权风险。
AI Skill Hub 为第三方内容聚合平台,本页面信息基于公开数据整理,不对工具功能和质量作任何法律背书。
建议在沙箱或测试环境中充分验证后,再部署至生产环境,并做好必要的安全评估。
总体来看,双重MCP工具 是一款质量优秀的MCP工具,在同类工具中具备一定竞争力。AI Skill Hub 将持续追踪其更新动态,建议收藏备用,结合自身场景选择合适时机引入使用。
| 原始名称 | bicameral-mcp |
| Topics | mcpagentic-workflowscodebase-intelligence |
| GitHub | https://github.com/BicameralAI/bicameral-mcp |
| 语言 | Python |
收录时间:2026-06-29 · 更新时间:2026-06-29 · License:未公布 · AI Skill Hub 不对第三方内容的准确性作法律背书。
选择 Agent 类型,复制安装指令后粘贴到对应客户端