MonkeyType MCP Server
Integrates with Codeium's Windsurf through MCP configuration at ~/.codeium/windsurf/mcp_config.json, enabling MonkeyType API access.
Project is hosted on GitHub with repository information provided for accessing source code and contributing.
Provides access to all MonkeyType API endpoints, allowing interaction with user data, test results, leaderboards, and server configuration. Features include retrieving personal bests, user stats, test results, leaderboard data, and checking username availability.
Provides installation methods via npm, including using npx to run the server directly or installing the package globally.
Enables integration with OpenAI's LLM platforms by configuring them to use the MonkeyType MCP server as a tool provider.
Click on "Deploy 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., "@MonkeyType MCP Server show me my typing stats from last week"
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.
MonkeyType MCP Server
This is a Model Context Protocol (MCP) server that provides access to all endpoints of the MonkeyType API. The server exposes MCP tools that allow Large Language Models (LLMs) to interact with the MonkeyType API.
Features
Exposes all MonkeyType API endpoints as MCP tools
Compatible with any LLM that supports the Model Context Protocol
Simple API key-based authentication per tool call
Comprehensive error handling
Rate limit awareness (respects MonkeyType's rate limits)
Related MCP server: Strava MCP Server
Installation
Using npx (Recommended)
The easiest way to run the server is using npx:
npx monkeytype-mcpThis will download and run the latest version of the server directly.
Global Installation
You can also install the package globally:
npm install -g monkeytype-mcp
monkeytype-mcpManual Installation
If you prefer to clone the repository:
git clone https://github.com/CodeDreamer06/MonkeytypeMCP.git
cd MonkeytypeMCP
npm install
npm startAvailable Tools
The server exposes the following MonkeyType API endpoints as MCP tools:
User Tools
check_username- Check if a username is availableget_personal_bests- Get user's personal bestsget_tags- Get user's tagsget_stats- Get user's statsget_profile- Get user's profilesend_forgot_password_email- Send forgot password emailget_current_test_activity- Get current test activityget_streak- Get user's streak
Test Results Tools
get_results- Get up to 1000 test resultsget_result_by_id- Get result by IDget_last_result- Get last result
Public Tools
get_speed_histogram- Get speed histogramget_typing_stats- Get typing stats
Leaderboards Tools
get_leaderboard- Get leaderboardget_leaderboard_rank- Get leaderboard rankget_daily_leaderboard- Get daily leaderboardget_weekly_xp_leaderboard- Get weekly XP leaderboard
PSAs Tools
get_psas- Get PSAs
Quotes Tools
is_submission_enabled- Check if quote submission is enabled
Server Configuration Tools
get_configuration- Get server configuration
How to Get Your MonkeyType API Key (ApeKey)
To get your own MonkeyType API key (ApeKey), follow these steps:
Sign in to your MonkeyType account
Click on your profile icon in the top right corner
Select "Account" from the dropdown menu
Navigate to the "Ape Keys" tab
Click "Generate New" to create a new API key
Give your key a name (e.g., "MCP Server")
Select the appropriate scopes based on what endpoints you need to access
Click "Generate"
Copy the generated key
Important: Keep your API key secure and never share it publicly.
Using the MCP Server with LLMs
To use this server with an LLM, you'll need to configure the LLM to use this server for MCP tool calls. You must provide your MonkeyType API key (ApeKey) by setting the MONKEYTYPE_API_KEY environment variable in your MCP server configuration.
Environment Variables
MONKEYTYPE_API_KEY: (Required) Your MonkeyType API key. You can obtain this from your account settings on monkeytype.com.MONKEYTYPE_USERNAME: (Optional) Your MonkeyType username or UID. This can be used by certain tools (likeget_profile) as a default or when specific keywords are used.
Example Tool Call
{
"name": "get_configuration",
"arguments": {}
}Integration with LLM Platforms
To integrate this server with LLM platforms like OpenAI, Anthropic, or others:
Start the MCP server using one of the installation methods above
Configure your LLM platform to use this server as an MCP tool provider
Pass the server's stdio as the communication channel
IDE Integration
MCP Configuration
To add MonkeyType MCP to your IDE, add this to your IDE's MCP config file:
{
"mcpServers": {
"monkeytype": {
"command": "sh",
"args": ["-c", "cd $(mktemp -d) && npm install monkeytype-mcp && npx monkeytype-mcp"],
"env": {
"MONKEYTYPE_API_KEY": "YOUR_APE_KEY_HERE"
}
}
}
}Config file locations:
Cursor:
~/.cursor/mcp.jsonWindsurf:
~/.codeium/windsurf/mcp_config.jsonCline:
~/.cline/mcp_config.jsonClaude:
~/.claude/mcp_config.json
VS Code Integration
To use this MCP server in VS Code:
Open VS Code settings
Search for "MCP Server"
Add a new MCP server with the following configuration:
Name: MonkeyType MCP
Command:
npx monkeytype-mcpType: Standard Input/Output (stdio)
Available Tools
The server exposes the following MonkeyType API endpoints as MCP tools:
User Tools
check_username- Check if a username is availableget_personal_bests- Get user's personal bestsget_tags- Get user's tagsget_stats- Get user's statsget_profile- Get user's profilesend_forgot_password_email- Send forgot password emailget_current_test_activity- Get current test activityget_streak- Get user's streak
get_profile
Fetches a user's public profile.
Parameters:
uidOrName(string, optional): The UID or username of the user whose profile is to be fetched.If you provide a specific username or UID, that user's profile will be fetched.
You can use keywords like "me", "self", "current", or "my". If one of these keywords is used, the tool will use the
MONKEYTYPE_USERNAMEenvironment variable (if set).If this parameter is omitted entirely, the tool will also attempt to use the
MONKEYTYPE_USERNAMEenvironment variable (if set).If the
uidOrNameparameter is omitted (or a keyword is used) and theMONKEYTYPE_USERNAMEenvironment variable is not set, an error will occur.
Test Results Tools
get_results- Get up to 1000 test resultsget_result_by_id- Get result by IDget_last_result- Get last result
Public Tools
get_speed_histogram- Get speed histogramget_typing_stats- Get typing stats
Leaderboards Tools
get_leaderboard- Get leaderboardget_leaderboard_rank- Get leaderboard rankget_daily_leaderboard- Get daily leaderboardget_weekly_xp_leaderboard- Get weekly XP leaderboard
PSAs Tools
get_psas- Get PSAs
Quotes Tools
is_submission_enabled- Check if quote submission is enabled
Server Configuration Tools
get_configuration- Get server configuration
Publishing
If you're making changes to this server and want to publish your own version:
npm login
npm publishGitHub Repository
This project is hosted on GitHub at https://github.com/CodeDreamer06/MonkeytypeMCP.
License
This project is licensed under the MIT License - see the LICENSE file for details.
Acknowledgements
MonkeyType for providing the API
Model Context Protocol (MCP) for the server architecture
Disclaimer
This project is not officially affiliated with MonkeyType. Use at your own risk and ensure you comply with MonkeyType's terms of service and API rate limits.
Available Tools
20 toolscheck_usernameC
Check if a username is available on MonkeyType
Inputs: name (required).
get_configurationC
Get server configuration
Inputs: no named parameters.
get_current_test_activityB
Get user's current test activity
Inputs: no named parameters.
get_daily_leaderboardC
Get daily typing test leaderboard
Inputs: language, mode, mode2, skip, +1 more.
get_last_resultB
Get user's last typing test result
Inputs: no named parameters.
get_leaderboardC
Get typing test leaderboard
Inputs: language (required), mode (required), mode2 (required), page, +1 more.
get_leaderboard_rankC
Get user's rank on the leaderboard
Inputs: language (required), mode (required), mode2 (required).
get_personal_bestsB
Get user's personal best typing scores
Inputs: mode, mode2.
get_profileC
Get user's profile information
Inputs: uidOrName.
get_psasC
Get public service announcements
Inputs: no named parameters.
get_result_by_idC
Get a specific typing test result by ID
Inputs: resultId (required).
get_resultsC
Get user's typing test results
Inputs: timestamp, offset, limit.
get_speed_histogramC
Get speed histogram data
Inputs: language (required), mode (required), mode2 (required).
get_statsC
Get user's typing statistics
Inputs: no named parameters.
get_streakB
Get user's typing streak information
Inputs: no named parameters.
get_tagsC
Get user's tags
Inputs: no named parameters.
get_typing_statsC
Get global typing statistics
Inputs: no named parameters.
get_weekly_xp_leaderboardC
Get weekly XP leaderboard
Inputs: skip, limit.
is_submission_enabledB
Check if quote submission is enabled
Inputs: no named parameters.
send_forgot_password_emailC
Send a forgot password email to a user
Inputs: email (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 20 tools
Most tools have distinct purposes focused on different aspects of MonkeyType (leaderboards, results, stats, profile), but there is some overlap between tools like get_stats and get_typing_stats, get_leaderboard and get_daily_leaderboard, and get_results and get_last_result/get_result_by_id that could cause confusion. The descriptions help differentiate them, but the boundaries aren't always clear.
Tool names follow a highly consistent verb_noun pattern throughout, using snake_case uniformly. All tools start with verbs like 'get', 'check', 'send', or 'is' followed by descriptive nouns, making them predictable and readable.
With 20 tools, the count is borderline high for a typing test server, feeling slightly heavy. While many tools cover specific features, some could potentially be consolidated (e.g., multiple leaderboard tools), making the set feel a bit bloated.
The tool set provides comprehensive coverage for reading data from MonkeyType, including user stats, leaderboards, results, and profile info. Minor gaps exist, such as no tools for submitting typing tests or updating user settings, but agents can likely work around these for most common workflows.
Maintenance
Related MCP Connectors
A comprehensive Model Context Protocol (MCP) server that enables AI assistants to interact with yo…
A Model Context Protocol server for Wix AI tools
Enable secure connectivity between Sentry issues and debugging data, and LLM clients, using a Model Context Protocol (MCP) server.
Model Context Protocol server for the Apideck Unified API. Connect any MCP-compatible agent framework to 100+ accounting systems, HRIS platforms, file storage providers, and more through one integration. More information https://www.apideck.com/mcp-server
Related MCP Servers
- AlicenseBqualityDmaintenanceA Model Context Protocol server that provides language models with access to Strava API data, allowing them to query and analyze athlete activities from Strava.425MIT
- AlicenseNot gradedqualityDmaintenanceA Model Context Protocol server that enables language models to interact with Strava data, including activities, athlete statistics, routes, achievements, and social features.6MIT
- AlicenseNot gradedqualityDmaintenanceA Model Context Protocol Server that enables LLMs to interact with and execute REST API calls through natural language prompts, supporting GET/PUT/POST/PATCH operations on configured APIs.6Apache 2.0
- FlicenseNot gradedqualityDmaintenanceA Python server implementing the Model Context Protocol that exposes tools for querying external APIs, compatible with Claude Desktop and ChatGPT Desktop.-