Metadata-Version: 2.4
Name: mcp-devtools
Version: 1.2.7
Summary: A short description of your project.
Author-email: daoch4n <daoch4n@gmail.com>
License: MIT
Project-URL: Homepage, https://github.com/daoch4n/mcp-devtools
Project-URL: Bug Tracker, https://github.com/daoch4n/mcp-devtools/issues
Classifier: Programming Language :: Python :: 3
Classifier: Operating System :: OS Independent
Requires-Python: >=3.12
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: fastapi
Requires-Dist: uvicorn
Requires-Dist: mcp-server-git
Requires-Dist: httpx
Requires-Dist: python-dotenv
Requires-Dist: PyYAML
Dynamic: license-file

# multi-functional MCP-devtools server over SSE <br> [🌸 リードミー](https://github.com/daoch4n/mcp-devtools/blob/main/%E3%83%AA%E3%83%BC%E3%83%89%E3%83%9F%E3%83%BC.MD) [🏮 读我](https://github.com/daoch4n/mcp-devtools/blob/main/%E8%AF%BB%E6%88%91.MD)

https://github.com/user-attachments/assets/d0b7b41b-c420-4b84-8807-d8a00300bd3e

[![MCP Badge](https://lobehub.com/badge/mcp/daoch4n-zen-ai-mcp-devtools?style=plastic)](https://lobehub.com/mcp/daoch4n-zen-ai-mcp-devtools)
[![GitHub repository](https://img.shields.io/badge/GitHub-repo-blue?logo=github)](https://github.com/daoch4n/mcp-devtools)
[![GitHub Workflow Status](https://img.shields.io/github/actions/workflow/status/daoch4n/mcp-devtools/python-package.yml?branch=main)](https://github.com/daoch4n/mcp-devtools/actions/workflows/python-package.yml)
[![PyPI](https://img.shields.io/pypi/v/mcp-devtools)](https://pypi.org/project/mcp-devtools)

- 🔧 `mcp-devtools` offers a comprehensive suite of software development tools: [ℹ️ Available Tools](#%E2%84%B9%EF%B8%8F-available-tools)
  -  🤖 AI-assisted file operations (`ai_edit`(uses [Aider](https://github.com/Aider-AI/aider)) [ℹ️ Aider Configuration](docs/aider_config.md)
  -  📁 Git-assisted file operations (`git_read_file`, `git_apply_diff`)
  -  📂 Direct file operations (`search_and_replace`(uses `sed` with fallback to direct mode), `write_to_file`) [ℹ️ Direct vs AI-assisted](#-direct-code-editing-vs--ai-assisted-editing)
  -  🎋 Git management operations (`git_diff_all`(compares to HEAD, `git_diff`(compares to specific commits/branches), `git_show`, `git_stage_and_commit`, `git_status`, `git_log`, `git_create_branch`, `git_checkout`, `git_reset`)
  -  🖥️ Terminal commands execution (`execute_command`) [⚠️ Automation-Related Security](#-automation-related-security-considerations)

### [⬇️ Skip to Downloads](#1%EF%B8%8F%E2%83%A3-prerequisites)

## ♒ Agentic Flows

ℹ️ To enforce strict adherence to following rules, enable `power steering` in Roo Code's `experimental` settings.  

https://github.com/user-attachments/assets/4d218e5e-906c-4d24-abc3-09ab0acdc1d0

### 😻 Vibe-Driven Dev Flow: inspired by [pure vibes](https://github.com/RooCodeInc/Roo-Code) 🦘, optimized for Vibing human-out-of-loop
- Just connect Roo to `mcp-devtools` server and code as usual but use `❓ Ask` mode instead of `💻 Code`, AI will automatically use the `ai_edit` tool if available to apply all changes. 

### 🙀 Spec-Driven Dev Flow: inspired by [spooky vibes](https://kiro.dev) 👻, optimized for Agile human-in-the-loop
-  To experience agile spec-driven flow, place the [.kiroomodes](https://github.com/daoch4n/mcp-devtools/blob/main/.kiroomodes) file and [.kiroo/](https://github.com/daoch4n/mcp-devtools/tree/main/.kiroo) folder into your repo root and rename them to `.roomodes` and `.roo/`:
   -  Start writing Epic Specs and User Stories with `✒️ Agile Writer`
   -  After your confirmation, it will auto-switch to `✏️ Agile Architect` and write Epic Design
   -  After next confirmation, it will auto-switch to `🖊️ Agile Planner` and write Epic Tasks
   -  After final comfirmation, it will auto-switch to `🖋️ Agile Dev` and orchestrate Epic Code writing, followed by Epic Review of each commit (you might want to direct native `💻 Code` to commit results before task completion).

### 😼 Plan-Driven Dev Flow: inspired by [minimal vibes](https://github.com/marv1nnnnn/rooroo) ♾️, optimized for Waterfall human-out-of-loop
 -  To experience structured waterfall flow, place the [.rooroomodes](https://github.com/daoch4n/mcp-devtools/blob/main/.rooroomodes) file and [.rooroo/](https://github.com/daoch4n/mcp-devtools/tree/main/.rooroo) folder into your repo root and rename them to `.roomodes` and `.roo/`:
    - `🧭 Rooroo Navigator` agent is your Advanced Flow manager. Responsible for project coordination and task orchestration, lifecycles, delegation. Provides `context.md` files to tasks, either the ones generated by `🗓️ Rooroo Planner`, or self-generated ones if Planner wasn't deemed neccessary for the task.
    - `👩🏻‍💻 Rooroo Developer` agent: <br> Delegates all code changes to subagent then reviews Aider work results, or just codes itself if `ai_edit` tool unavailable.
    - `📊 Rooroo Analyzer` agent acts as a researcher and analyzes the code.
    - `🗓️ Rooroo Planner` agent decomposes complex goals requiring multi-expert coordination into clear, actionable sub-tasks for other agents to do. It is also the main supplier of `context.md` files for them.
    - `💡 Rooroo Idea Sparker` agent is your brainstorming copilot and innovation catalyst, talk to it if you'd like some creative thinking and assumption challenging done, or just explore something new with it.

## 1️⃣ Prerequisites

- Python 3.12, [uv](https://github.com/astral-sh/uv)

### 🐧 Linux/macOS

```bash
curl -LsSf https://astral.sh/uv/install.sh | sh
```

### 🪟 Windows

```powershell
powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"
```

## 2️⃣ Usage

### 🐍 Running from PyPi

```bash
uvx mcp-devtools -p 1337
```

### 🐈‍⬛ Running from GitHub

#### 🐧 Linux/macOS

```bash
git clone "https://github.com/daoch4n/mcp-devtools/"
cd mcp-devtools
./server.sh -p 1337
```

#### 🪟 Windows

```powershell
git clone "https://github.com/daoch4n/mcp-devtools/"
cd mcp-devtools
.\server.ps1 -p 1337
```

## 3️⃣ MCP Server Configuration

To integrate `mcp-devtools` with your AI assistant, add the following configuration to your MCP settings file:

```json
{
  "mcpServers": {
    "devtools": {
      "url": "http://127.0.0.1:1337/sse"
    }
  }
}
```

## 4️⃣ [AI System Prompt](https://github.com/daoch4n/research/tree/ai/prompt-engineering/google-whitepaper) Example
<details>
<summary> <h3> ℹ️ Show Prompt </h3> </summary>
  
```
# ROLE AND DIRECTIVE

**You are a Senior Software Architect.** Your primary function is to architect software solutions by delegating all code implementation to a stateless coding agent via the `ai_edit` tool. Your expertise lies in meticulous planning, atomic delegation, and rigorous code review, not direct implementation.

---

# STANDARD OPERATING PROCEDURE (SOP)

You must adhere to the following five-step, iterative workflow:

1.  **Analyze & Plan:** Thoroughly analyze the user's request and formulate a clear, high-level implementation plan. Break the problem down into the smallest possible, logical, and incremental steps.
2.  **Delegate ONE Step:** Translate **only the very next step** of your plan into a precise, actionable, and fully self-contained prompt for the `ai_edit` tool. **Never bundle multiple steps into a single delegation.**
3.  **Provide Full Context:** Because the agent is stateless, you must include all necessary context (e.g., file paths, relevant code snippets, class/function definitions) within your `ai_edit` prompt. (See "Agent Memory & Context Protocol" below).
4.  **Review & Verify:** Critically evaluate the diff generated by `ai_edit` after every execution. This is a **mandatory code review**.
    * Does the code correctly implement the single step you delegated?
    * Is the code quality acceptable?
    * Are there any errors or edge cases missed?
5.  **Iterate & Guide:**
    * **If Approved:** The step is complete. Proceed to delegate the *next* incremental step in your plan.
    * **If Revision is Needed:** The implementation is flawed. Provide corrective feedback in a new `ai_edit` prompt, again ensuring all context is provided, to guide the agent to the correct solution for that specific step.

---

# AGENT MEMORY & CONTEXT PROTOCOL (CRITICAL)

**The coding agent is STATELESS.** It has no memory of previous instructions, file contents, or chat history.

* **Your Responsibility:** You must treat every call to `ai_edit` as if you are speaking to a brand-new developer who has zero knowledge of the project.
* **Actionable Rule:** In every prompt to `ai_edit`, you are required to provide all the immediate context the agent needs to complete that *one specific task*. This includes, but is not limited to:
    * The full path to the file(s) being edited.
    * The specific function, class, or block of code to be modified.
    * Any dependencies or related code snippets from the same or other files that are necessary for the agent to understand the task.

---

# CONSTRAINTS & TOOL PROTOCOL

**Primary Constraint:**
* You are **strictly prohibited** from writing or modifying application code directly. All code implementation must be delegated.
* **Forbidden Tools for Coding:** `apply_diff`, `search_and_replace`, `write_to_file`, and `{your_native_tool_slug}` must NOT be used to modify code.

**Permitted Exception:**
* You MAY use file editing tools to create or modify non-code assets, such as documentation.

**`ai_edit` Tool Usage Rules:**
* `repo_path`: Always pass the full, absolute path of the current working directory.
* `model` / `diff_format`: Do not include these parameters unless explicitly instructed by the user.

```

</details>

## 🎧 Audio Overview

https://github.com/user-attachments/assets/05670a7a-72c5-4276-925c-dbd1ed617d99

## 🙈 Automation-Related Security Considerations

- 🛡️ For automated workflows, always run MCP Servers in isolated environments (🐧[Firejail](https://github.com/netblue30/firejail) or 🪟[Sandboxie](https://github.com/sandboxie-plus/Sandboxie))
- 🗃️ Filesystem access boundaries are maintained via passing `repo_path` to every tool call, so AI assistant only has read/write access to files in the current workspace (relative to any path AI decides to pass as `repo_path` , make sure system prompt is solid on cwd use).
- ⚠️ `execute_command` doesn't have strict access boundaries defined, while it does execute all commands with cwd set to `repo_path` (relative to it), nothing is there to stop AI from passing full paths to other places it seems fit; reading, altering or deleting unintended data on your whole computer, so execise extreme caution with auto-allowing `execute_command` tool or at least don't leave AI assistant unattended while doing so. MCP server is not responsible for your AI assistant executing rm -rf * in your home folder.

## ⁉️ Known Issues and Workarounds

### 💾 Direct Code Editing vs 🤖 AI-assisted Editing

**Issue:**

*    🔍 When using the `write_to_file` tool for direct code editing with languages like JavaScript that utilize template literals, you may encounter unexpected syntax errors. This issue stems from how the AI assistant generates the `content` string, where backticks and dollar signs within template literals might be incorrectly escaped with extra backslashes (`\`).

**Mitigation:** 

*    🔨 The `write_to_file`,`search_and_replace` and `git_apply_diff` tools are dynamically integrated with `tsc` (TypeScript compiler) for conditional type checking of `.js`, `.mjs`, and `.ts` files on edit. The output of `tsc --noEmit --allowJs` is provided as part of the tool's response. AI assistants should parse this output to detect any compiler errors and *should not proceed with further actions* if errors are reported, indicating a problem with the written code.

**Workarounds:**

*    🤖 Instruct your AI assistant to delegate editing files to MCP-compatible coding agent by using `ai_edit` tool instead, as it is more suitable for direct code manipulation, automatically commits changes and produces resulting diff as tool output, and let AI assistant act as task orchestrator that will write down plans and docs with `write_to_file` tool then delegate actual coding to specialized agent, get its report (diff) as tool call result, use `git_read_file` tool to double check agent's work, and manage commits and branches (`ai_edit` tool basically integrates `Aider` via some logic ported from [its MCP bridge](https://github.com/sengokudaikon/aider-mcp-server)).

### ❔ Aider limitations due to its commit-first nature

**Issue:**

*    🔍 When using `ai_edit` tool in a dirty repo state, e.g. during merge or rebase active, it will probably get stuck trying to apply commit.
  
**Workarounds:**

*    ⚙️ Temporarily disable auto commiting functions in your `.aider.conf.yml` configuration file.

## ℹ️ Available Tools

### `git_status`
- **Description:** Shows the current status of the Git working tree, including untracked, modified, and staged files.
- **Input Schema:**

  ```json
  {
    "type": "object",
    "properties": {
      "repo_path": {
        "type": "string",
        "description": "The absolute path to the Git repository's working directory."
      }
    },
    "required": [
      "repo_path"
    ]
  }
  ```


### `git_diff_all`
- **Description:** Shows all changes in the working directory, including both staged and unstaged modifications, compared to the HEAD commit. This provides a comprehensive view of all local changes.
- **Input Schema:**
  ```json
  {
    "type": "object",
    "properties": {
      "repo_path": {
        "type": "string",
        "description": "The absolute path to the Git repository's working directory."
      }
    },
    "required": [
      "repo_path"
    ]
  }
  ```

### `git_diff`
- **Description:** Shows differences between the current working directory and a specified Git target (e.g., another branch, a specific commit hash, or a tag).
- **Input Schema:**
  ```json
  {
    "type": "object",
    "properties": {
      "repo_path": {
        "type": "string",
        "description": "The absolute path to the Git repository's working directory."
      },
      "target": {
        "type": "string",
        "description": "The target (e.g., branch name, commit hash, tag) to diff against. For example, 'main', 'HEAD~1', or a full commit SHA."
      }
    },
    "required": [
      "repo_path",
      "target"
    ]
  }
  ```

### `git_stage_and_commit`
- **Description:** Stages specified files (or all changes if no files are specified) and then commits them to the repository with a given message. This creates a new commit in the Git history.
- **Input Schema:**
  ```json
  {
    "type": "object",
    "properties": {
      "repo_path": {
        "type": "string",
        "description": "The absolute path to the Git repository's working directory."
      },
      "message": {
        "type": "string",
        "description": "The commit message for the changes."
      },
      "files": {
        "type": "array",
        "items": {
          "type": "string"
        },
        "description": "An optional list of specific file paths (relative to the repository root) to stage before committing. If not provided, all changes will be staged."
      }
    },
    "required": [
      "repo_path",
      "message"
    ]
  }
  ```

### `git_reset`
- **Description:** Unstages all currently staged changes in the repository, moving them back to the working directory without discarding modifications. This is equivalent to `git reset` without arguments.
- **Input Schema:**
  ```json
  {
    "type": "object",
    "properties": {
      "repo_path": {
        "type": "string",
        "description": "The absolute path to the Git repository's working directory."
      }
    },
    "required": [
      "repo_path"
    ]
  }
  ```

### `git_log`
- **Description:** Shows the commit history for the repository, listing recent commits with their hash, author, date, and message. The number of commits can be limited.
- **Input Schema:**
  ```json
  {
    "type": "object",
    "properties": {
      "repo_path": {
        "type": "string",
        "description": "The absolute path to the Git repository's working directory."
      },
      "max_count": {
        "type": "integer",
        "default": 10,
        "description": "The maximum number of commit entries to retrieve. Defaults to 10."
      }
    },
    "required": [
      "repo_path"
    ]
  }
  ```

### `git_create_branch`
- **Description:** Creates a new Git branch with the specified name. Optionally, you can base the new branch on an existing branch or commit, otherwise it defaults to the current active branch.
- **Input Schema:**
  ```json
  {
    "type": "object",
    "properties": {
      "repo_path": {
        "type": "string",
        "description": "The absolute path to the Git repository's working directory."
      },
      "branch_name": {
        "type": "string",
        "description": "The name of the new branch to create."
      },
      "base_branch": {
        "type": "string",
        "nullable": true,
        "description": "Optional. The name of the branch or commit hash to base the new branch on. If not provided, the new branch will be based on the current active branch."
      }
    },
    "required": [
      "repo_path",
      "branch_name"
    ]
  }
  ```

### `git_checkout`
- **Description:** Switches the current active branch to the specified branch name. This updates the working directory to reflect the state of the target branch.
- **Input Schema:**
  ```json
  {
    "type": "object",
    "properties": {
      "repo_path": {
        "type": "string",
        "description": "The absolute path to the Git repository's working directory."
      },
      "branch_name": {
        "type": "string",
        "description": "The name of the branch to checkout."
      }
    },
    "required": [
      "repo_path",
      "branch_name"
    ]
  }
  ```

### `git_show`
- **Description:** Shows the metadata (author, date, message) and the diff of a specific commit. This allows inspection of changes introduced by a particular commit.
- **Input Schema:**
  ```json
  {
    "type": "object",
    "properties": {
      "repo_path": {
        "type": "string",
        "description": "The absolute path to the Git repository's working directory."
      },
      "revision": {
        "type": "string",
        "description": "The commit hash or reference (e.g., 'HEAD', 'main', 'abc1234') to show details for."
      }
    },
    "required": [
      "repo_path",
      "revision"
    ]
  }
  ```

### `git_apply_diff`
- **Description:** Applies a given diff content (in unified diff format) to the working directory of the repository. This can be used to programmatically apply patches or changes.
- **Input Schema:**
  ```json
  {
    "type": "object",
    "properties": {
      "repo_path": {
        "type": "string",
        "description": "The absolute path to the Git repository's working directory."
      },
      "diff_content": {
        "type": "string",
        "description": "The diff content string to apply to the repository. This should be in a unified diff format."
      }
    },
    "required": [
      "repo_path",
      "diff_content"
    ]
  }
  ```

### `git_read_file`
- **Description:** Reads and returns the entire content of a specified file within the Git repository's working directory. The file path must be relative to the repository root.
- **Input Schema:**
  ```json
  {
    "type": "object",
    "properties": {
      "repo_path": {
        "type": "string",
        "description": "The absolute path to the Git repository's working directory."
      },
      "file_path": {
        "type": "string",
        "description": "The path to the file to read, relative to the repository's working directory."
      }
    },
    "required": [
      "repo_path",
      "file_path"
    ]
  }
  ```


### `search_and_replace`
- **Description:** Searches for a specified string or regex pattern within a file and replaces all occurrences with a new string. Supports case-insensitive search and line-range restrictions. It attempts to use `sed` for efficiency, falling back to Python logic if `sed` fails or makes no changes.
- **Input Schema:**
  ```json
  {
    "type": "object",
    "properties": {
      "repo_path": {
        "type": "string",
        "description": "The absolute path to the Git repository's working directory."
      },
      "file_path": {
        "type": "string",
        "description": "The path to the file to modify, relative to the repository's working directory."
      },
      "search_string": {
        "type": "string",
        "description": "The string or regex pattern to search for within the file."
      },
      "replace_string": {
        "type": "string",
        "description": "The string to replace all matches of the search string with."
      },
      "ignore_case": {
        "type": "boolean",
        "default": false,
        "description": "If true, the search will be case-insensitive. Defaults to false."
      },
      "start_line": {
        "type": "integer",
        "nullable": true,
        "description": "Optional. The 1-based starting line number for the search and replace operation (inclusive). If not provided, search starts from the beginning of the file."
      },
      "end_line": {
        "type": "integer",
        "nullable": true,
        "description": "Optional. The 1-based ending line number for the search and replace operation (inclusive). If not provided, search continues to the end of the file."
      }
    },
    "required": [
      "repo_path",
      "file_path",
      "search_string",
      "replace_string"
    ]
  }
  ```

### `write_to_file`
- **Description:** Writes the provided content to a specified file within the repository. If the file does not exist, it will be created. If it exists, its content will be completely overwritten. Includes a check to ensure content was written correctly and generates a diff.
- **Input Schema:**
  ```json
  {
    "type": "object",
    "properties": {
      "repo_path": {
        "type": "string",
        "description": "The absolute path to the Git repository's working directory."
      },
      "file_path": {
        "type": "string",
        "description": "The path to the file to write to, relative to the repository's working directory. The file will be created if it doesn't exist, or overwritten if it does."
      },
      "content": {
        "type": "string",
        "description": "The string content to write to the specified file."
      }
    },
    "required": [
      "repo_path",
      "file_path",
      "content"
    ]
  }
  ```

### `execute_command`
- **Description:** Executes an arbitrary shell command within the context of the specified repository's working directory. This tool can be used for tasks not covered by other specific Git tools, such as running build scripts, linters, or other system commands.
- **Input Schema:**
  ```json
  {
    "type": "object",
    "properties": {
      "repo_path": {
        "type": "string",
        "description": "The absolute path to the directory where the command should be executed."
      },
      "command": {
        "type": "string",
        "description": "The shell command string to execute (e.g., 'ls -l', 'npm install')."
      }
    },
    "required": [
      "repo_path",
      "command"
    ]
  }
  ```

### `ai_edit`
- **Description:** AI pair programming tool for making targeted code changes using Aider. Use this tool to:
  1. Implement new features or functionality in existing code
  2. Add tests to an existing codebase
  3. Fix bugs in code
  4. Refactor or improve existing code
  5. Make structural changes across multiple files

  The tool requires:
  - A repository path where the code exists
  - A detailed message describing what changes to make. Please only describe one change per message. If you need to make multiple changes, please submit multiple requests.

  **Edit Format Selection:**
  If the `edit_format` option is not explicitly provided, the default is selected based on the model name:
  - If the model includes `gemini`, defaults to `diff-fenced`
  - If the model includes `gpt`, defaults to `udiff`
  - Otherwise, defaults to `diff`

  Best practices for messages:
  - Be specific about what files or components to modify
  - Describe the desired behavior or functionality clearly
  - Provide context about the existing codebase structure
  - Include any constraints or requirements to follow

  Examples of good messages:
  - "Add unit tests for the Customer class in src/models/customer.rb testing the validation logic"
  - "Implement pagination for the user listing API in the controllers/users_controller.js file"
  - "Fix the bug in utils/date_formatter.py where dates before 1970 aren't handled correctly"
  - "Refactor the authentication middleware in middleware/auth.js to use async/await instead of callbacks"
- **Input Schema:**
  ```json
  {
    "type": "object",
    "properties": {
      "repo_path": {
        "type": "string",
        "description": "The absolute path to the Git repository's working directory where the AI edit should be performed."
      },
      "message": {
        "type": "string",
        "description": "A detailed natural language message describing the code changes to make. Be specific about files, desired behavior, and any constraints."
      },
      "files": {
        "type": "array",
        "items": {
          "type": "string"
        },
        "description": "A list of file paths (relative to the repository root) that Aider should operate on. This argument is mandatory."
      },
      "options": {
        "type": "array",
        "items": {
          "type": "string"
        },
        "description": "Optional. A list of additional command-line options to pass directly to Aider. Each option should be a string."
      },
      "edit_format": {
        "type": "string",
        "enum": [
          "diff",
          "diff-fenced",
          "udiff",
          "whole"
        ],
        "default": "diff",
        "description": "Optional. The format Aider should use for edits. Defaults to 'diff'. Options: 'diff', 'diff-fenced', 'udiff', 'whole'."
      }
    },
    "required": [
      "repo_path",
      "message",
      "files"
    ]
  }
  ```

### `aider_status`
- **Description:** Check the status of Aider and its environment. Use this to:
  1. Verify Aider is correctly installed
  2. Check API keys
  3. View the current configuration
  4. Diagnose connection or setup issues
- **Input Schema:**
  ```json
  {
    "type": "object",
    "properties": {
      "repo_path": {
        "type": "string",
        "description": "The absolute path to the Git repository or working directory to check Aider's status within."
      },
      "check_environment": {
        "type": "boolean",
        "default": true,
        "description": "If true, the tool will also check Aider's configuration, environment variables, and Git repository details. Defaults to true."
      }
    },
    "required": [
      "repo_path"
    ]
  }
