UseKeen Documentation MCP Server
Enables searching Docker documentation to find implementation details, examples, and specifications
Provides access to Node.js documentation search for finding implementation details, examples, and specifications
Allows searching React documentation to find implementation details, examples, and specifications
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., "@UseKeen Documentation MCP Server search for React documentation on hooks"
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.
UseKeen MCP Server
MCP Server for the UseKeen API, enabling Claude and other AI assistants to search documentation.
Tools
usekeen_package_doc_search
Search documentation of packages and services to find implementation details, examples, and specifications
Required inputs:
package_name(string): Name of the package or service to search documentation for (e.g. 'react', 'aws-s3', 'docker')
Optional inputs:
query(string): Search term to find specific information within the package/service documentation (e.g. 'file upload example', 'authentication methods')
Returns: Documentation search results with relevant matches, URLs, and snippets
Related MCP server: Apidog MCP Server
Prerequisites
UseKeen API Key: Get a UseKeen API key from the UseKeen service
Node.js (for NPX installation) or Docker (for Docker installation)
Claude Desktop or VS Code with MCP extension
Installation
Option 1: NPX (Recommended)
The easiest way to use this MCP server is via NPX:
npx usekeen-mcpOption 2: Docker
You can also run the server using Docker:
docker run -e USEKEEN_API_KEY=your_api_key_here mcp/usekeenOption 3: Local Development
For local development or manual installation:
# Clone the repository
git clone <repository-url>
cd usekeen-mcp
# Copy environment file and add your API key
cp .env.example .env
# Edit .env and add your USEKEEN_API_KEY
# Install dependencies
npm install
# Build and run
npm run build
npm startConfiguration
Usage with Claude Desktop
Add the following to your claude_desktop_config.json:
NPX
{
"mcpServers": {
"usekeen": {
"command": "npx",
"args": [
"-y",
"usekeen-mcp"
],
"env": {
"USEKEEN_API_KEY": "your_api_key_here"
}
}
}
}Docker
{
"mcpServers": {
"usekeen": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"-e",
"USEKEEN_API_KEY",
"mcp/usekeen"
],
"env": {
"USEKEEN_API_KEY": "your_api_key_here"
}
}
}
}Usage with VS Code
For manual installation, add the following JSON block to your User Settings (JSON) file in VS Code. You can do this by pressing Ctrl + Shift + P and typing Preferences: Open Settings (JSON).
Optionally, you can add it to a file called .vscode/mcp.json in your workspace. This will allow you to share the configuration with others.
Note that the
mcpkey is not needed in the.vscode/mcp.jsonfile.
NPX
{
"mcp": {
"inputs": [
{
"type": "promptString",
"id": "usekeen_api_key",
"description": "UseKeen API Key",
"password": true
}
],
"servers": {
"usekeen": {
"command": "npx",
"args": ["-y", "usekeen-mcp"],
"env": {
"USEKEEN_API_KEY": "${input:usekeen_api_key}"
}
}
}
}
}Docker
{
"mcp": {
"inputs": [
{
"type": "promptString",
"id": "usekeen_api_key",
"description": "UseKeen API Key",
"password": true
}
],
"servers": {
"usekeen": {
"command": "docker",
"args": ["run", "-i", "--rm", "mcp/usekeen"],
"env": {
"USEKEEN_API_KEY": "${input:usekeen_api_key}"
}
}
}
}
}Manual Setup
Using the Helper Scripts
We provide two helper scripts to make it easier to run the server:
Local Execution:
# Make the script executable (first time only) chmod +x run-local.sh # Run the server locally ./run-local.shDocker Execution:
# Make the script executable (first time only) chmod +x run-docker.sh # Run the server in Docker ./run-docker.sh
Both scripts will check for a .env file containing your USEKEEN_API_KEY. You can create this file based on the provided .env.example.
Running with npm
Set the USEKEEN_API_KEY environment variable and run the server:
# Install dependencies
npm install
# Build the TypeScript code
npm run build
# Run the server
USEKEEN_API_KEY=your_api_key npm startRunning with Docker
Build and run the Docker container with the API key:
# Build the Docker image
docker build -t mcp/usekeen .
# Run the container
docker run -e USEKEEN_API_KEY=your_api_key mcp/usekeenEnvironment Variables
USEKEEN_API_KEY: Required. Your UseKeen API key for authentication.
Troubleshooting
If you encounter errors, verify that:
Your UseKeen API key is valid and correctly set in your configuration
You have an active internet connection to reach the UseKeen API
The UseKeen service is currently available
MCP result shape errors
The server always returns MCP-compliant tool results as
result.content(array of content blocks). Some clients display a generic error if a custom object is returned instead ofcontent. This server normalizes API responses and also setsisError: truefor failures so clients render them correctly. If integrating new tools, ensure they return{ content: [{ type: "text", text: "..." }] }and never wrap results under custom keys like{ result: { results: [...] } }.
Build
Docker build:
docker build -t mcp/usekeen .License
This MCP server is licensed under the MIT License. This means you are free to use, modify, and distribute the software, subject to the terms and conditions of the MIT License.
Available Tools
1 toolusekeen_package_doc_searchB
Search documentation of packages and services to find implementation details, examples, and specifications. The user's query should be as specific as possible to get the best results.
Inputs: package_name (required), query (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 1 tool
With only one tool, there is no possibility of ambiguity or overlap between tools. The single tool has a clear and distinct purpose focused on searching documentation.
A single tool inherently has perfect naming consistency, as there are no other tools to compare it against. The name 'usekeen_package_doc_search' follows a descriptive pattern.
One tool is too few for a server that appears to cover documentation search for packages and services. This minimal set limits functionality and suggests an incomplete or narrow implementation for the domain.
The tool set is severely incomplete for a documentation server. It only provides search functionality, lacking essential operations like browsing documentation categories, retrieving specific documents, or managing documentation updates, which are typical for such domains.
Maintenance
Related MCP Connectors
Versioned documentation registry and semantic search for AI tools and coding assistants.
Docsy gives AI assistants current, version-specific documentation for libraries, frameworks and SDKs. Resolve library IDs and versions, then search and fetch focused official documentation with original source links using five read-only MCP tools. Hosted Streamable HTTP with OAuth 2.1 sign-in.
Publish your API docs so AI assistants can look up endpoints and call your API correctly.
Search @imqueue docs and scaffold typed services & clients from your AI coding agent.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceEnables AI assistants to search documentation of packages and services to find implementation details, examples, and specifications.MIT
- AlicenseNot gradedqualityDmaintenanceEnables AI tools to search and explore API documentation from Apidog projects or OpenAPI/Swagger specifications, providing endpoint details, schemas, and project statistics through natural language queries.1,398 npm1ISC
- AlicenseAqualityCmaintenanceProvides AI assistants with access to design documentation across multiple code libraries, enabling discovery of existing utilities and patterns to avoid reimplementation.32MIT
- FlicenseNot gradedqualityDmaintenanceProvides AI assistants with live, searchable documentation for any programming library, eliminating hallucinated APIs by returning current, structured API references.-