Agent Skills
› rcarmo/piclaw
› mcp-adapter
mcp-adapter
GitHub通过 pi-mcp-adapter 连接 MCP 服务器,提供统一的 mcp 工具及 /mcp 命令,支持本地与全局配置管理、工具搜索调用及状态交互。
Trigger Scenarios
需要连接或管理 MCP 服务器
使用 mcp 工具调用外部服务
查看或搜索 MCP 工具列表
Install
npx skills add rcarmo/piclaw --skill mcp-adapter -g -y
SKILL.md
Frontmatter
{
"name": "mcp-adapter",
"description": "Use the bundled pi-mcp-adapter to connect MCP servers through .pi\/mcp.json.",
"distribution": "public"
}
MCP Adapter
Use pi-mcp-adapter to expose MCP servers to the agent through one mcp tool plus /mcp commands.
Config locations
Preferred project-local config:
/workspace/.pi/mcp.json
Starter example:
cp /workspace/.pi/mcp.json.example /workspace/.pi/mcp.json
The adapter also understands the global Pi config at:
/config/.pi/agent/mcp.json
Use the project-local file when you want MCP servers tied to the current workspace.
Minimal example
{
"mcpServers": {
"filesystem": {
"command": "bunx",
"args": ["-y", "@modelcontextprotocol/server-filesystem", "."],
"lifecycle": "lazy"
}
}
}
Common workflows
List MCP status / tools
mcp({})
Search for a tool
mcp({ search: "read file" })
Describe a tool
mcp({ describe: "filesystem_read_file" })
Call a tool
mcp({ tool: "filesystem_read_file", args: "{\"path\":\"./README.md\"}" })
args must be a JSON string.
Interactive commands
/mcp
/mcp tools
/mcp reconnect
/mcp reconnect filesystem
/mcp-auth <server>
Notes
- MCP servers are lazy by default and connect on first use.
- After editing
.pi/mcp.json, restart the session or reload Pi so the adapter re-reads config. - Prefer
directToolsonly for small, high-value tool sets. Keep large MCP servers behind themcpproxy.
Version History
- 5fa0ce5 Current 2026-07-25 10:25


