mcp-server-text-editor
Claude 文本编辑器 MCP 服务器
Claude 内置文本编辑器工具的开源实现,作为模型上下文协议(MCP) 服务器。此软件包提供与Claude 内置文本编辑器工具相同的功能,允许您通过标准化 API 查看、编辑和创建文本文件。
特征
与 Claude 文本编辑器相同的 API :实现与 Claude 内置文本编辑器工具完全相同的界面
MCP 服务器实现:遵循 AI 工具集成的模型上下文协议标准
文件操作:
使用可选的行范围规范查看文件内容
创建新文件
替换现有文件中的文本
在特定行号处插入文本
撤消之前的编辑
Related MCP server: MCP Text Editor Server
支持的 Claude 文本编辑器版本
该软件包实现了与内置 Claude 文本编辑器工具版本等效的工具:
text_editor_20241022(克劳德 3.5 十四行诗)text_editor_20250124(克劳德 3.7 十四行诗)
但使用工具名称“text_editor”可以避免与内置的Claude工具发生名称冲突。
安装
# Install from npm
npm install mcp-server-text-editor
# Or with pnpm
pnpm add mcp-server-text-editor用法
启动服务器
# Using npx
npx -y mcp-server-text-editor
# Or if installed globally
mcp-server-text-editor在 Claude Desktop 中配置
{
"mcpServers": {
"textEditor": {
"command": "npx",
"args": ["-y", "mcp-server-text-editor"]
}
}
}工具命令
看法
查看文件或目录的内容。
{
"command": "view",
"path": "/path/to/file.js",
"view_range": [1, 10] // Optional: Show lines 1-10 only
}创造
创建具有指定内容的新文件。
{
"command": "create",
"path": "/path/to/file.js",
"file_text": "console.log('Hello, world!');"
}字符串替换
替换文件中的文本。
{
"command": "str_replace",
"path": "/path/to/file.js",
"old_str": "console.log('Hello, world!');",
"new_str": "console.log('Hello, Claude!');"
}插入
在特定行插入文本。
{
"command": "insert",
"path": "/path/to/file.js",
"insert_line": 5,
"new_str": "// This line was inserted by Claude"
}撤消编辑
恢复对文件所做的最后编辑。
{
"command": "undo_edit",
"path": "/path/to/file.js"
}发展
先决条件
Node.js 18+
下午
设置
# Clone the repository
git clone https://github.com/bhouston/mcp-server-text-editor.git
cd mcp-server-text-editor
# Install dependencies
pnpm install
# Build the project
pnpm build脚本
pnpm build:构建 TypeScript 项目pnpm lint:运行带有自动修复功能的 ESLintpnpm format:使用 Prettier 格式化代码pnpm clean:删除构建工件pnpm clean:all:删除构建工件和 node_modulespnpm test:运行测试pnpm test:coverage:运行带有覆盖率报告的测试
测试
本项目采用Vitest进行测试。
运行测试:
# Run all tests
pnpm test
# Run tests with coverage report
pnpm test:coverage测试覆盖率报告将在coverage目录中生成。
执照
麻省理工学院
贡献
欢迎贡献代码!欢迎提交 Pull 请求。
分叉存储库
创建你的功能分支(
git checkout -b feature/amazing-feature)提交您的更改(
git commit -m 'Add some amazing feature')推送到分支(
git push origin feature/amazing-feature)打开拉取请求
Available Tools
1 tooltext_editorB
View, create, and edit files with persistent state across command calls. This tool is identical with Claude's built in text editor tool called text_editor_20241022
| Name | Required | Description | Default |
|---|---|---|---|
| command | Yes | The commands to run. Allowed options are: `view`, `create`, `str_replace`, `insert`, `undo_edit`. | |
| description | Yes | The reason you are using the text editor (max 80 chars) | |
| file_text | No | Required parameter of `create` command, with the content of the file to be created. | |
| insert_line | No | Required parameter of `insert` command. The `new_str` will be inserted AFTER the line `insert_line` of `path`. | |
| new_str | No | Optional parameter of `str_replace` command containing the new string (if not given, no string will be added). Required parameter of `insert` command containing the string to insert. | |
| old_str | No | Required parameter of `str_replace` command containing the string in `path` to replace. | |
| path | Yes | Absolute path to file or directory, e.g. `/repo/file.py` or `/repo`. | |
| view_range | No | Optional parameter of `view` command when `path` points to a file. If none is given, the full file is shown. If provided, the file will be shown in the indicated line number range, e.g. [11, 12] will show lines 11 and 12. Indexing at 1 to start. Setting `[start_line, -1]` shows all lines from `start_line` to the end of the file. |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden. It mentions 'persistent state across command calls,' which is a useful behavioral trait not evident from the schema. However, it lacks details on permissions, error handling, file system interactions, or what 'persistent state' entails operationally. The description adds some value but leaves significant behavioral aspects unexplained.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences: the first is front-loaded with core functionality, but the second sentence about being identical to another tool adds no value for tool selection and wastes space. It could be more concise by omitting the redundant second sentence.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity (8 parameters, no annotations, no output schema), the description is somewhat incomplete. It covers basic purpose and a behavioral trait (persistent state), but lacks details on usage context, error cases, or output expectations. For a multi-command tool with no output schema, more guidance would be helpful.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the schema already documents all parameters thoroughly. The description adds no parameter-specific information beyond what's in the schema. According to the rules, with high schema coverage, the baseline is 3 even with no param info in the description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: 'View, create, and edit files with persistent state across command calls.' It specifies the actions (view, create, edit) and resource (files), and mentions the persistent state feature. However, it doesn't distinguish from siblings since there are none, and the second sentence about being identical to another tool adds no functional clarity.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives. It mentions it's 'identical with Claude's built in text editor tool,' but this doesn't help an agent decide between this and other file manipulation tools. There are no explicit when/when-not scenarios or prerequisites described.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
1 tool update
v1.0.0- First observed
text_editor
TDQS
Scored across 1 tool
With only one tool, there is no possibility of confusion or overlap between tools. The tool has a single, clear purpose for file editing with persistent state, making disambiguation trivial.
A single tool named 'text_editor' follows a clear and consistent naming pattern. There are no other tools to compare against, so no inconsistency can exist.
A single tool for a text editor server feels thin and under-scoped. While it covers basic file operations, typical text editors would benefit from additional tools for tasks like search/replace, formatting, or managing multiple files, making this count borderline inadequate.
The tool surface is severely incomplete for a text editor domain. It lacks essential operations such as search within files, undo/redo functionality, file management (e.g., rename, delete), or formatting options, which are core to text editing workflows.
Maintenance
Related MCP Connectors
Read and write your Fresh Jots notes from Claude, Cursor, and any MCP client.
Read, edit, publish, and preview your pepita websites from Claude.
Creative workspace. Public MCP: outline previews for Codex and Claude Code; media in the web app.
Collaborative word processor you can use with your agent.
Related MCP Servers
- FlicenseBqualityDmaintenanceMulti-mode MCP server supporting both Claude Desktop (STDIO) and OpenAI (HTTP/SSE) integrations with file operations including read, write, delete, and search capabilities.3-
- AlicenseNot gradedqualityDmaintenanceA Model Context Protocol (MCP) server that provides line-oriented text file editing capabilities through a standardized API. Optimized for LLM tools with efficient partial file access to minimize token usage.MIT
- FlicenseNot gradedqualityDmaintenanceTurns Claude Desktop into a Cursor-like assistant for code browsing, editing, searching, linting, formatting, and version control.-
- AlicenseNot gradedqualityDmaintenanceEnables sandboxed file operations via MCP tools, resources, and prompts, with a Claude CLI client and Groq-powered web UI for file CRUD, search, code review, and documentation generation.MIT