File Opener MCP Server
Provides tools for opening files and directories with system default or specified applications, and revealing items in Finder on macOS.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@File Opener MCP Serveropen my presentation slides in Keynote"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
File Opener MCP Server
A Model Context Protocol (MCP) server that provides file opening capabilities for Claude AI.
Features
open_file: Open any file or directory with the system's default application
reveal_in_finder: Reveal a file or directory in macOS Finder
Optional application specification (e.g., open with Preview, TextEdit, etc.)
Cross-platform support (primarily macOS focused)
Full error handling and validation
Related MCP server: Python MCP Custom Server
Installation
Quick Install
npm install -g file-opener-mcpFrom Source
Clone the repository:
git clone https://github.com/TIMBOTGPT/file-opener-mcp.git cd file-opener-mcpInstall dependencies:
npm installTest the server:
npm start
Usage with Claude Desktop
Add this server to your Claude Desktop MCP configuration (claude_desktop_config.json):
{
"mcpServers": {
"file-opener": {
"command": "npx",
"args": ["-y", "file-opener-mcp"],
"description": "Open files with system applications"
}
}
}Or if installed locally:
{
"mcpServers": {
"file-opener": {
"command": "node",
"args": ["/path/to/file-opener-mcp/index.js"],
"description": "Open files with system applications"
}
}
}Available Tools
open_file
Opens a file or directory with the system's default application, or optionally with a specified application.
Parameters:
path(required): Full path to the file or directoryapplication(optional): Specific application to use (e.g., "Preview", "TextEdit")
Example:
{
"name": "open_file",
"arguments": {
"path": "/path/to/documents/report.pdf",
"application": "Preview"
}
}reveal_in_finder
Reveals a file or directory in macOS Finder.
Parameters:
path(required): Full path to the file or directory
Example:
{
"name": "reveal_in_finder",
"arguments": {
"path": "/path/to/documents/report.pdf"
}
}Requirements
macOS (uses
opencommand)Node.js 16+
Claude Desktop with MCP support
Security
File existence is validated before opening
Only executes safe system
opencommandsProper error handling and reporting
No network access required
License
MIT License - see LICENSE file for details
Contributing
Fork the repository
Create a feature branch
Make your changes
Add tests if applicable
Submit a pull request
Support
For issues and questions, please use the GitHub Issues page.
Available Tools
2 toolsopen_fileA
Open a file or directory using the system default application (macOS open command)
| Name | Required | Description | Default |
|---|---|---|---|
| path | Yes | Full path to the file or directory to open | |
| application | No | Optional: specific application to open the file with (e.g., "Preview", "TextEdit") |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden. It discloses the implementation detail ('macOS open command') which is valuable behavioral context, but doesn't mention potential side effects like launching applications, system permissions needed, or error conditions. It adequately describes the core behavior but lacks comprehensive operational details.
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 a single, efficient sentence that front-loads the core purpose and includes implementation detail without unnecessary elaboration. Every word serves a purpose, making it appropriately sized and well-structured.
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 tool's moderate complexity (2 parameters, no output schema, no annotations), the description provides sufficient context for basic usage. It explains what the tool does and how it's implemented, though it could benefit from mentioning typical use cases or limitations. The absence of output schema means return values aren't documented, but this is acceptable for this type of system operation.
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 fully documents both parameters. The description doesn't add any parameter-specific information beyond what's in the schema, such as path format examples or application compatibility details. This meets the baseline for high schema coverage.
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 specific action ('Open') and resource ('a file or directory') using the system default application, with explicit mention of the macOS 'open' command implementation. It distinguishes from the sibling 'reveal_in_finder' by focusing on opening rather than revealing.
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 implies usage for opening files/directories with default applications, but provides no explicit guidance on when to use this tool versus alternatives like 'reveal_in_finder' or when not to use it. The context is clear but lacks comparative or exclusionary statements.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
reveal_in_finderB
Reveal a file or directory in Finder
| Name | Required | Description | Default |
|---|---|---|---|
| path | Yes | Full path to the file or directory to reveal in Finder |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It states the action ('Reveal') but doesn't explain what this entails operationally—such as whether it opens Finder windows, selects files, requires specific permissions, or has side effects. This leaves significant gaps in understanding the tool's behavior.
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 a single, clear sentence with zero wasted words. It's front-loaded with the core action and resource, making it highly efficient and easy to parse for an AI agent.
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?
For a simple tool with one parameter and no output schema, the description is minimally adequate but incomplete. It lacks behavioral details and usage guidelines, which are crucial given the sibling tool 'open_file' and the absence of annotations. The description covers the basic purpose but misses contextual depth needed for optimal agent decision-making.
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?
The input schema has 100% description coverage, with the 'path' parameter fully documented. The description doesn't add any additional semantic context beyond what the schema provides, such as path format examples or constraints. Given the high schema coverage, a baseline score of 3 is appropriate.
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 verb ('Reveal') and resource ('a file or directory in Finder'), making the purpose immediately understandable. However, it doesn't differentiate from the sibling tool 'open_file', which might have overlapping functionality for opening files versus revealing them in the file system browser.
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 the sibling 'open_file' or other alternatives. It lacks context about specific use cases, prerequisites, or exclusions, leaving the agent to infer usage based on the tool name alone.
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. Dates show when Glama detected each change.
2 tool updates
v1.0.0- First observed
open_file - First observed
reveal_in_finder
TDQS
The two tools have clearly distinct purposes: open_file opens files with the default application, while reveal_in_finder shows files in Finder without opening them. There is no overlap or ambiguity between these functions, making tool selection straightforward.
Both tools follow a consistent verb_noun pattern (open_file, reveal_in_finder) with clear, descriptive names. The naming style is uniform and predictable across the tool set.
With only two tools, the server feels thin for a 'File Opener' domain. While the tools cover basic macOS file operations, the scope suggests potential gaps (e.g., no tools for editing, copying, or managing files), making the set appear underdeveloped.
The tool set is severely incomplete for file operations. It lacks core functionalities like creating, deleting, moving, or editing files, and is limited to macOS-specific actions. This will cause agent failures for common file management tasks beyond opening or revealing.
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Connectors
Let ChatGPT, Claude & Cursor use your Mac: email, calendar, iMessage, Teams, files. Local, free.
Give Claude only the Google Drive files you choose. Every action logged.
Search, read, and write your Apple Notes from ChatGPT/Claude via a local Mac agent + MCP relay.
- platform7nOAuthtech.p7n
Connect Claude to your Platform7n workspaces — chat, links, and tasks. One-click OAuth.
Related MCP Servers
- AlicenseAqualityDmaintenanceAllows Claude to execute terminal commands on your computer and perform file system operations including surgical code editing with diff-based replacements.1948,6087MIT
- FlicenseNot gradedqualityNot gradedmaintenanceExtends Claude Desktop with custom tools for file management, system operations, and command execution. Supports creating/reading/deleting files, directory listing, system information retrieval, and file searching capabilities.-
- FlicenseBqualityDmaintenanceExposes macOS system controls and Apple apps as structured tools for Claude, enabling control of volume, music, files, browser tabs, and more via natural language with configurable permissions and rate limiting.311-
- FlicenseNot gradedqualityDmaintenanceEnables Claude to perform file operations, retrieve system information, run calculations, and generate timestamps on the local system.-
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/TIMBOTGPT/file-opener-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server