JFSecure MCP
An MCP server that allows AI agents to use secrets like API tokens and database passwords without the agent ever seeing the actual values. It operates by having the agent request secrets by name, triggering an approval window in the JFSecure app for the user to authorize specific commands. The server provides tools to list secret names, run commands with secrets injected as environment variables (with output masking), and render templates with secret values, ensuring sensitive data never enters the model's context or logs.
Package and access
Local package with source-attributed installation metadata. Koskamo does not execute packages during review.
What you can do with it
- List secret names in the vault without exposing values
- Run commands with secrets as environment variables with masked output
- Render templates by filling in secret values into files like .env
Source and maintenance
- Maintenance checked
Packages and installation
Source-provided package data. Koskamo has not executed or live-probed this package.
https://github.com/theone55/jfs/releases/download/v2.7.0/jfs-2.7.0.mcpb
{
"transport": "stdio",
"fileSha256": "55d9d6911db9acbd9470cc28fc601a71c80cf195fd1a798051eb32ada59f2a90",
"identifier": "https://github.com/theone55/jfs/releases/download/v2.7.0/jfs-2.7.0.mcpb",
"registryType": "mcpb"
}Tools
Reported by the attributed source; not independently observed by Koskamo.
Let your agent find its tools
Find servers like JFSecure MCP from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.