- Keyfactor Command MCP Server
Keyfactor Command MCP Server
The Keyfactor Command MCP (Model Context Protocol) server provides AI-powered access to Keyfactor Command, a comprehensive Certificate Lifecycle Management (CLM) and Public Key Infrastructure (PKI) automation platform. This server enables natural language interactions with X.509 certificate operations, certificate discovery, and PKI management tasks. When the Risk Intelligence separately licensed add-on is available, the MCP server provides enhanced capabilities to interpret and contextualize certificate risk assessments using AI, making complex security findings more accessible and actionable.
Content
⚠️PREVIEW: Not recommended for production
Command-MCP
MCP server for Command built on the Keyfactor Analytics & AI team's Python SDK. This preview is experimental software and users are discouraged from providing AI tools with access to your production data. This software is provided as-is and no support SLA applies to this MCP server.
Prerequisites
- Keyfactor Command version 11 or higher
- Claude for Desktop
- Python 3
Operations and Required Permissions
- get_license. Retrieves information about functionality license in Keyfactor Command, and serves as a basic connectivity test. Required permissions: None.
- get_certificate_details_by_id. Retrieves a certificate and associated metadata by cert id. If Command Risk Intelligence is enabled, includes risk data. Required permissions: Certificates: Collections: Read.
- enroll_certificate. PFX enrollment using provided subject and DNS SANs. Required Permissions: Certificates: Enrollment: PFX.
- enroll_csr. Enrollment using a CSR provided to the MCP client. Required Permissions: Certificates: Enrollment: CSR.
- revoke_certificate. Revoke a certificate by its certificate id. Required Permissions: Certificates: Collections: Revoke.
- get_metadata_fields. Retrieve a list of all metadata fields and definitions present in Command. Required Permissions: Metadata: Types: Read.
- query_certificates. Run a certificate search query to retrieve any matching certificates, with additional options including sorting. Required Permisisons: Certificates: Collections: Read.
- get_module_info_for_mcp. Does not use Command API. Returns a static definition describing the Command MCP Server.
Installation
- Download this repo. These directions assume a download to "C:\mcp."
- Create or identify an account in Command that has the required permissions to perform any operation you intend to use.
- Put envvars in C:\mcp\mcpenv.txt. One line each, using information from your Command environment and the account you created:
Basic auth:
KEYFACTOR_HOSTNAME='...'
KEYFACTOR_TOKEN='...' KEYFACTOR_TEMPLATE='WebServer'
KEYFACTOR_CA='kftrain.keyfactor.lab\keyfactor-KFTRAIN-CA'
OAuth:
KEYFACTOR_HOSTNAME=...
KEYFACTOR_URLBASE=Keyfactor/API
COMMAND_IDP_TOKENURL=...
COMMAND_IDP_CLIENTID=...
COMMAND_IDP_CLIENTSECRET=...
COMMAND_IDP_AUDIENCE=...
KEYFACTOR_TEMPLATE=Server_tlsServerAuth-1y
KEYFACTOR_CA=http://ejbca-ca.jdk-2025-may.svc.cluster.local:8082/ejbca\\Sub-CA - Run this command (you may need to use "pip3" if pip is pointing at Python 2.x):
pip install requests oauthlib httpx attrs python-dateutil uv - Test that this command will run from CLI and print "Initializing MCP server":
uv --directory C:\\mcp run --env-file=C:\\mcp\\mcpenv.txt commandmcp.py - In Claude, press Ctrl+Comma to open settings, go to developer, and click "edit config". Put this in claude_desktop_config.json in the folder it takes you to:
{ "mcpServers": { "keyfactorCommand": { "command": "uv", "args": [ "--directory", "C:\\mcp", "run", "--env-file=C:\\mcp\\mcpenv.txt", "commandmcp.py" ] } } } - In Claude, go to Settings->Integration and make your desired selections about enabled operations and when Claude should ask for permission. It is recommended to have Claude ask before each use of the enrollment and revocation functions, at minimum.
Notes
- ⚠️ This preview software is considered experimental and is not recommended for production use.
- For security purposes, this MCP server is deployed as a local MCP server to a client like Claude for Desktop.
- Template and CA parameters to be used for enrollment must be specified as environment variables to the MCP server to scope MCP clients to only the intended enrollment types. Permissions and availability must be set on this template and CA.
- See comments in "commandmcp.py" or interrogate your MCP client for additional details on implemented operations.
- See the Keyfactor Command Reference Guide for information on Keyfactor Command and required permissions.
Server Config
{
"mcpServers": {
"keyfactorCommand": {
"command": "uv",
"args": [
"--directory",
"C:\\mcp",
"run",
"--env-file=C:\\mcp\\mcpenv.txt",
"commandmcp.py"
]
}
}
}Recommend Servers
TraeBuild with Free GPT-4.1 & Claude 3.7. Fully MCP-Ready.
AiimagemultistyleA Model Context Protocol (MCP) server for image generation and manipulation using fal.ai's Stable Diffusion model.
MiniMax MCPOfficial MiniMax Model Context Protocol (MCP) server that enables interaction with powerful Text to Speech, image generation and video generation APIs.
Zhipu Web SearchZhipu Web Search MCP Server is a search engine specifically designed for large models. It integrates four search engines, allowing users to flexibly compare and switch between them. Building upon the web crawling and ranking capabilities of traditional search engines, it enhances intent recognition capabilities, returning results more suitable for large model processing (such as webpage titles, URLs, summaries, site names, site icons, etc.). This helps AI applications achieve "dynamic knowledge acquisition" and "precise scenario adaptation" capabilities.
BlenderBlenderMCP connects Blender to Claude AI through the Model Context Protocol (MCP), allowing Claude to directly interact with and control Blender. This integration enables prompt assisted 3D modeling, scene creation, and manipulation.
Howtocook Mcp基于Anduin2017 / HowToCook (程序员在家做饭指南)的mcp server,帮你推荐菜谱、规划膳食,解决“今天吃什么“的世纪难题;
Based on Anduin2017/HowToCook (Programmer's Guide to Cooking at Home), MCP Server helps you recommend recipes, plan meals, and solve the century old problem of "what to eat today"
WindsurfThe new purpose-built IDE to harness magic
ChatWiseThe second fastest AI chatbot™
MCP AdvisorMCP Advisor & Installation - Use the right MCP server for your needs
Visual Studio Code - Open Source ("Code - OSS")Visual Studio Code
Context7Context7 MCP Server -- Up-to-date code documentation for LLMs and AI code editors
EdgeOne Pages MCPAn MCP service designed for deploying HTML content to EdgeOne Pages and obtaining an accessible public URL.
Playwright McpPlaywright MCP server
Jina AI MCP ToolsA Model Context Protocol (MCP) server that integrates with Jina AI Search Foundation APIs.
TimeA Model Context Protocol server that provides time and timezone conversion capabilities. This server enables LLMs to get current time information and perform timezone conversions using IANA timezone names, with automatic system timezone detection.
Amap Maps高德地图官方 MCP Server
Baidu Map百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
DeepChatYour AI Partner on Desktop
Tavily Mcp
Serper MCP ServerA Serper MCP Server
CursorThe AI Code Editor