Skip to main content
Glama
Sai-Adarsh

Coyote MCP Server

by Sai-Adarsh
OverviewSchemaRelated ServersScoreDiscussions

Coyote MCP Server

A Model Context Protocol (MCP) server that enables AppleScript execution on macOS through the run_applescript tool.

Quick Start

git clone https://github.com/Sai-Adarsh/coyote-mcp-server.git
cd coyote-mcp-server
npm install
npm run build
npm run setup-claude-cli  # or setup-claude, setup-vscode, setup-windsurf, setup-cursor

Related MCP server: MCP Complete Implementation Guide

Usage Commands

Interactive Mode (Recommended):

claude --mcp-config ~/.config/claude-cli/mcp.json

Then type any command like:

  • Use AppleScript to show a dialog with 'Hello World'

  • Use AppleScript to open Calculator

  • Use AppleScript to open Safari and go to google.com

Quick Commands:

# Test the setup
claude --mcp-config ~/.config/claude-cli/mcp.json --print "Use AppleScript to show a dialog with 'Hello World'"

# Open applications
claude --mcp-config ~/.config/claude-cli/mcp.json --print "Use AppleScript to open Calculator"
claude --mcp-config ~/.config/claude-cli/mcp.json --print "Use AppleScript to open Safari"

# Navigate websites
claude --mcp-config ~/.config/claude-cli/mcp.json --print "Use AppleScript to open Safari and go to google.com"

# Create notifications
claude --mcp-config ~/.config/claude-cli/mcp.json --print "Use AppleScript to show a notification with title 'Test' and message 'Hello from MCP'"

Note: Claude CLI will ask for permission before executing AppleScript commands. Grant permission when prompted to allow automation.

Quick Setup Commands

Client

Setup Command

Claude CLI

npm run setup-claude-cli

Claude Desktop

npm run setup-claude

VS Code

npm run setup-vscode

Windsurf

npm run setup-windsurf

Cursor

npm run setup-cursor

All clients

npm run setup-all

After Setup

Once setup is complete, you'll see the MCP server listed as coyote-use in your client:

  • Claude CLI/Desktop: Server appears in MCP configuration

  • VS Code: Available in MCP extension as coyote-use

  • Windsurf: Available in Cascade → Plugins as coyote-use

  • Cursor: Server appears in MCP configuration as coyote-use

The server provides the run_applescript tool for executing AppleScript commands on macOS.

Uninstall

To completely remove Coyote MCP Server and all configurations:

npm run uninstall
# or
./uninstall.sh

This will:

  • Remove coyote-use server from all MCP client configurations

  • Uninstall the global npm package

  • Clean up binary files from system PATH

  • Create backup copies of modified configurations

  • Clean npm cache and old backup files

Troubleshooting

Command not found error after update:

hash -r

Development

npm run build    # Build the server
npm start        # Start manually for testing

References

Available Tools

1 tool
run_applescriptRun AppleScriptC

Executes an AppleScript command using osascript on macOS.

ParametersJSON Schema
NameRequiredDescriptionDefault
scriptYesAppleScript code to execute.

TDQS

C2.9/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It states the action ('executes') but does not describe what happens during execution—such as whether it runs synchronously, returns output, handles errors, requires specific permissions, or has side effects. For a tool that executes scripts with potential system impact, this is a significant gap in transparency.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, efficient sentence: 'Executes an AppleScript command using osascript on macOS.' It is front-loaded with the core action, has zero wasted words, and appropriately sized for the tool's simplicity. Every part of the sentence earns its place by specifying what, how, and where.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the complexity of executing system scripts and the lack of annotations and output schema, the description is incomplete. It does not address behavioral aspects like error handling, output format, or security implications, which are critical for such a tool. The description alone is insufficient for safe and effective use by an AI agent.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has 100% description coverage, with one parameter ('script') documented as 'AppleScript code to execute.' The description does not add any meaning beyond this, as it only repeats that it executes an AppleScript command without detailing parameter syntax or constraints. With high schema coverage, the baseline score of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: 'Executes an AppleScript command using osascript on macOS.' It specifies the verb ('executes'), resource ('AppleScript command'), and implementation detail ('using osascript on macOS'), making it unambiguous. However, since there are no sibling tools, the distinction aspect is not applicable, preventing a perfect score of 5.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

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 the implementation ('using osascript on macOS'), which implies platform specificity, but does not explicitly state when this tool is appropriate or what prerequisites might be needed (e.g., macOS requirement, permissions). No exclusions or alternatives are mentioned.

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.

  1. 1 tool update
    • First observedrun_applescript
Install Server
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

B3/5.0
Disambiguation5/5

With only one tool, there is no possibility of confusion or overlap between tools, as there are no other tools to compare it to. The tool's purpose is clearly defined and distinct by default.

Naming Consistency5/5

Since there is only a single tool, naming consistency is inherently perfect; there are no other tool names to compare it against, so no inconsistencies can arise.

Tool Count2/5

A single tool is generally too few for most server purposes, as it limits functionality and suggests a very narrow scope. While it might be appropriate for a minimal utility, it often feels thin and incomplete for broader use cases.

Completeness1/5

The server's domain appears to be AppleScript execution on macOS, but with only one tool, there are significant gaps; for example, there are no tools for validating scripts, handling errors, or managing script files, making the surface severely incomplete for typical workflows.

Maintenance

ActivityInactive
ResponsivenessNo issues

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

Related MCP Servers

  • SAGE-MCP

    david-strejc
    F
    license
    Not graded
    quality
    D
    maintenance
    A universal AI assistant MCP server that transforms Claude into a multi-talented development assistant with intelligent mode selection, conversation continuity, and smart file handling. Automatically adapts to different tasks like debugging, code analysis, planning, and testing while supporting multiple AI providers and maintaining context across conversations.
    11
    -

  • MCP Complete Implementation

    saksham0712
    F
    license
    B
    quality
    D
    maintenance
    Provides a complete end-to-end MCP server implementation with file system tools, web scraping capabilities, and system information access. Includes ready-to-use configuration files and integration examples for Claude Desktop, ChatGPT, and other AI models.
    6
    -

  • jlbloomer-mcp-server

    jared-bloomer
    A
    license
    B
    quality
    D
    maintenance
    A personal MCP server for AI assistant integration that provides custom tools, resources, and prompts for use with Claude Desktop and other MCP-compatible clients.
    2
    MIT

Latest Blog Posts

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/Sai-Adarsh/coyote-mcp-server'

If you have feedback or need assistance with the MCP directory API, please join our Discord server