一键在 Manus 中运行任何 Skill

开始使用

add-mcp-server

星标6

分支2

更新时间2026年5月26日 11:54

Add a Model Context Protocol (MCP) server to a genai-tk project — config, credential management, and validation.

安装

用 Codex 或 Claude 帮你安装复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。

在 Manus 中运行

来源

tclatos

tclatos/genai-tk

打开 GitHub 仓库查看创作者相关仓库

下载

在 Manus 中运行

Add an MCP Server

MCP (Model Context Protocol) servers expose tools to agents over a standardized JSON-RPC interface. genai-tk manages them through config/mcp_servers.yaml.

Step 1: Find or Implement the MCP Server

Use an existing server:

@modelcontextprotocol/server-filesystem — file system access
@modelcontextprotocol/server-brave-search — web search
@modelcontextprotocol/server-github — GitHub API
Browse: https://github.com/modelcontextprotocol/servers

Implement your own:
See examples/mcp_server/ for a Python MCP server skeleton.

Step 2: Add to mcp_servers.yaml

Edit config/mcp_servers.yaml:

mcp_servers:
  my_server:                        # ← key used in agent profiles
    transport: stdio                # stdio | sse
    command: npx
    args:
      - "-y"
      - "@modelcontextprotocol/server-brave-search"
    env:
      BRAVE_API_KEY: ${oc.env:BRAVE_API_KEY}  # env var interpolation
    enabled: true

  my_python_server:
    transport: stdio
    command: uv
    args:
      - run
      - python
      - examples/mcp_server/server.py
    enabled: true

Step 3: Reference in Agent Profile

In config/agents/langchain.yaml:

langchain_agents:
  my_agent:
    mcp_servers:
      - my_server
      - my_python_server

Step 4: Add Credentials

Add to .env (never commit this file):

BRAVE_API_KEY=bsk-xxxxx

Add to .env.example (commit this):

BRAVE_API_KEY=              # get from https://api.search.brave.com/

Step 5: Validate

cli mcp list                    # list configured servers
cli mcp test my_server          # verify connection
cli agents langchain -p my_agent "search for: Python MCP"

Transport Types

Transport	Use when	Notes
`stdio`	local process or Docker	default, most reliable
`sse`	remote/HTTP server	requires running server URL

For sse transport:

my_server:
  transport: sse
  url: http://localhost:8080/sse

Code Map

Concern	Path
MCP config	`config/mcp_servers.yaml`
MCP CLI commands	`genai_tk/cli/commands_mcp.py`
MCP docs	`docs/mcp-servers.md`
Example server	`examples/mcp_server/server.py`
Agent profiles	`config/agents/langchain.yaml`

同仓库更多 Skills

同仓库

agent-profiles

tclatos/genai-tk

Build or modify LangChain, DeepAgent, DeerFlow profiles, agent tools, middleware, checkpointing, skills wiring, and the shared harness layer in genai-tk.

2026-07-056

baml-structured-extraction

tclatos/genai-tk

Work on BAML structured extraction, BAML CLI commands, processors, utilities, and Prefect BAML workflow integration in genai-tk.

2026-07-056

browser-and-sandbox

tclatos/genai-tk

Work on browser automation, sandbox browser tools, direct Playwright tools, AioSandbox backend, and sandbox CLI support in genai-tk.

2026-07-056

cli-and-scaffolding

tclatos/genai-tk

Add or modify genai-tk Typer CLI commands, dynamic command registration, project scaffolding, and generated Copilot/agent support files.

2026-07-056

configuration

tclatos/genai-tk

Work on genai-tk OmegaConf configuration, profiles, overrides, env substitution, and config discovery. Use when editing config/*.yaml or genai_tk.config_mgmt.config_mngr.

2026-07-056

core-models

tclatos/genai-tk

Work on core LLM, embeddings, vector store, provider, cache, prompt, and retriever factories in genai-tk. Use when editing genai_tk/core or provider configuration.

2026-07-056

name	add-mcp-server
description	Add a Model Context Protocol (MCP) server to a genai-tk project — config, credential management, and validation.
tags	["mcp","tools","configuration"]
version	1.0

Add an MCP Server

MCP (Model Context Protocol) servers expose tools to agents over a standardized JSON-RPC interface. genai-tk manages them through config/mcp_servers.yaml.

Step 1: Find or Implement the MCP Server

Use an existing server:

@modelcontextprotocol/server-filesystem — file system access
@modelcontextprotocol/server-brave-search — web search
@modelcontextprotocol/server-github — GitHub API
Browse: https://github.com/modelcontextprotocol/servers

Implement your own:
See examples/mcp_server/ for a Python MCP server skeleton.

Step 2: Add to mcp_servers.yaml

Edit config/mcp_servers.yaml:

mcp_servers:
  my_server:                        # ← key used in agent profiles
    transport: stdio                # stdio | sse
    command: npx
    args:
      - "-y"
      - "@modelcontextprotocol/server-brave-search"
    env:
      BRAVE_API_KEY: ${oc.env:BRAVE_API_KEY}  # env var interpolation
    enabled: true

  my_python_server:
    transport: stdio
    command: uv
    args:
      - run
      - python
      - examples/mcp_server/server.py
    enabled: true

Step 3: Reference in Agent Profile

In config/agents/langchain.yaml:

langchain_agents:
  my_agent:
    mcp_servers:
      - my_server
      - my_python_server

Step 4: Add Credentials

Add to .env (never commit this file):

BRAVE_API_KEY=bsk-xxxxx

Add to .env.example (commit this):

BRAVE_API_KEY=              # get from https://api.search.brave.com/

Step 5: Validate

cli mcp list                    # list configured servers
cli mcp test my_server          # verify connection
cli agents langchain -p my_agent "search for: Python MCP"

Transport Types

Transport	Use when	Notes
`stdio`	local process or Docker	default, most reliable
`sse`	remote/HTTP server	requires running server URL

For sse transport:

my_server:
  transport: sse
  url: http://localhost:8080/sse

Code Map

Concern	Path
MCP config	`config/mcp_servers.yaml`
MCP CLI commands	`genai_tk/cli/commands_mcp.py`
MCP docs	`docs/mcp-servers.md`
Example server	`examples/mcp_server/server.py`
Agent profiles	`config/agents/langchain.yaml`