跳到正文
cccskills
免费在 GitHub 公开

managing-mcp-servers

Manage MCP server settings in ThinkRail when servers need to be added, changed, enabled, or troubleshot. It explains user and repository configuration, safe credential references, approval and sign-in steps, and how to load deferred tools.

中文简介正在准备中。当前显示英语简介。

原文查看原文说明

Use when the user asks to add, change, remove, enable or disable an MCP server, or when an MCP tool is missing, needs sign-in, fails, or was blocked. ThinkRail runs pi in-process, so there is no `pi` command to call.

集成工具GitHub

实测评分 未实测

查看安装方法

适用场景

  • Adding or removing an MCP server
  • Changing server settings or exposure
  • Troubleshooting missing or failing MCP tools
  • Preparing a server that requires sign-in
  • Explaining repository server approval

包含的文件(1)

  • SKILL.md3.3 KB

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

Managing MCP servers in ThinkRail

ThinkRail uses pi's built-in MCP support but has no pi executable. Never run pi mcp add, pi mcp login or other pi commands; edit the configuration files and point the user at Settings › MCP servers for everything that needs them.

Where servers are configured

  • User level — pi's agent directory, usually ~/.pi/agent/mcp.json: available in every project.
  • This repository — .pi/mcp.json in the worktree, tracked in git. A server defined here does not run until the user approves it in Settings, and any later change to its entry needs approval again. It only loads when the user trusts the project.

Both files use pi's format:

{
  "mcpServers": {
    "docs": { "url": "https://example.com/mcp" },
    "browser": { "command": "npx", "args": ["-y", "@playwright/mcp@0.0.83"] }
  }
}
  • Pin package versions in args; never @latest.
  • Never write a secret into either file. Reference it as ${ENV_VAR} (from the host's environment) or !command (the command's output, for example !gh auth token), or let the user sign in.
  • exposure: deferred (the default here — load the server's tools with tool_search first), direct (a few always-useful tools), or hidden. codemode is treated as deferred.
  • Prefer the user-level file for personal servers; only put a server in .pi/mcp.json when the user wants it shared with the repository.

GitHub

GitHub is a recipe, not a preset: its hosted server, authenticated with the user's GitHub CLI sign-in. Add it to the user-level file (Settings › MCP servers offers the same entry under Paste JSON):

{
  "mcpServers": {
    "github": {
      "url": "https://api.githubcopilot.com/mcp/readonly",
      "headers": { "Authorization": "!t=$(gh auth token) && echo \"Bearer $t\"" }
    }
  }
}
  • /readonly is GitHub's documented read-only mode (same as an X-MCP-Readonly: true header). Use https://api.githubcopilot.com/mcp/ only when the user asks for tools that change data.
  • The header command runs each time a chat connects. While gh is logged out it fails instead of sending an empty token; the user runs gh auth login in a terminal.
  • Unverified: whether GitHub accepts the GitHub CLI token's scopes for every toolset. If the server rejects it, ask the user for a token in an environment variable: "Authorization": "Bearer ${GITHUB_TOKEN}".

After editing

The host reloads idle chats on its own and a busy chat picks the change up when it is idle. Tell the user when a step is theirs: approving a repository server, or Sign in for a server that uses OAuth (both in Settings › MCP servers). Do not ask them to restart ThinkRail.

Using MCP tools

  • Tools are named mcp__<server>__<tool>. For a deferred server, call tool_search to load them.
  • Subagents cannot call MCP tools: call them yourself and put what the subagent needs in its task.
  • ThinkRail asks the user before a call that may change data. A denied or cancelled call is final for that call; do not retry it without asking the user first.

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

Helps an agent ask focused questions when a workflow needs user decisions. It groups independent questions into rounds, frames choices as visible outcomes, and explains how to continue when answers are skipped or interactive questions are unavailable.

中文简介正在准备中。当前显示英语简介。

  • Gathering scope and behavior decisions for a feature
  • Clarifying choices that depend on earlier answers
  • Confirming an inference with clear options
JetBrains/thinkrail17652026年10月26日 更新

Clarify the product goal and technical choices before a feature, behavior change, or bug fix is built. The workflow records an agreed task specification, guides implementation against it, and updates durable project specs when the work lands.

中文简介正在准备中。当前显示英语简介。

  • Clarifying goals before building a feature
  • Agreeing on behavior changes before coding
  • Investigating and planning a bug fix
JetBrains/thinkrail17652026年10月26日 更新

Route new project setup, pull request lifecycle work, and product changes such as features or bug fixes to the workflow that governs them. It also identifies when a request needs no workflow, so routine questions and nonbehavioral edits can proceed directly.

中文简介正在准备中。当前显示英语简介。

  • Choosing a workflow for a new project
  • Routing a feature or bug fix
  • Handling pull request checks or review feedback
JetBrains/thinkrail17652026年10月26日 更新

Build a draft specification graph for an existing codebase that has no specs. Survey its guidance files, documentation, manifests, and code; infer project purpose and module boundaries, adopt suitable existing design documents, and validate the resulting graph for review.

中文简介正在准备中。当前显示英语简介。

  • Creating initial specs for an undocumented codebase
  • Mapping modules and their dependencies
  • Turning existing architecture documents into specs
JetBrains/thinkrail17652026年10月26日 更新

Routes project setup to the appropriate workflow by checking whether specs and source code already exist. It sends an empty workspace with a new idea toward a requirements document, or an existing codebase toward an initial spec graph, and offers review when specs are already present.

中文简介正在准备中。当前显示英语简介。

  • Setting up a project with no existing specifications
  • Routing a new idea to a requirements workflow
  • Preparing initial specs for an existing codebase
JetBrains/thinkrail17652026年10月26日 更新

Create and maintain pull requests for finished work. The workflow can sync a branch, update PR details or screenshots, report checks, monitor CI when asked, and address review comments while confirming the latest Git and GitHub state.

中文简介正在准备中。当前显示英语简介。

  • Opening a pull request for finished changes
  • Syncing a PR branch with its base
  • Updating a PR title, body, or screenshots
JetBrains/thinkrail17652026年10月26日 更新

查看 JetBrains 的全部技能

报告此技能的问题