What is the difference from cloud-based secret managers?
Local Secrets keeps all data on your machine in a local SQLite database, with no cloud services involved.
@Hustada
Basic information
Store and retrieve API keys and secrets locally for Claude Code. No cloud services, no .env files scattered across projects. Secrets are stored in a SQLite database on your machine and accessed via MCP tools. Supports add, get, list, search, update, and delete operations with cat
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"local-secrets": {
"command": "npx",
"args": [
"-y",
"local-secrets-mcp",
"serve"
]
}
}
}Get a specific secret value by its key name
List all available secret keys (values are hidden)
Search for secrets by key name pattern
Get a secret formatted as an environment variable assignment
Add a new secret to the vault
Update an existing secret
Delete a secret from the vault
A local secrets manager for Claude Code that stores API keys and credentials securely on your machine using a SQLite database. It eliminates the need for cloud services or scattered .env files, designed for developers using Claude Code.
Install and manage secrets via CLI with npx local-secrets-mcp init, npx local-secrets-mcp add <key> <value>, and npx local-secrets-mcp list. Secrets can also be accessed through MCP tools such as get_secret, add_secret, and search_secrets.
Local Secrets keeps all data on your machine in a local SQLite database, with no cloud services involved.
Secrets are stored in a local SQLite database on your machine.
Secrets can be accessed via CLI commands (e.g., `npx local-secrets-mcp list`) or through MCP tools like `get_secret` and `list_secrets`.
It requires Node.js and npx to run the CLI and MCP tools.
Yes, you can search by key pattern and filter by category using MCP tools and CLI commands.

SSH MCP server for AI agents: remote commands, file transfer, log search and server audits through OpenSSH.

Catch intent conflicts before code conflicts. The open-source coordination protocol for coding agents, built above Git.
Modelglass turns "which model should I use?" into a lookup instead of a guess. Seven tools give your agent live pricing across image, language, video, and audio models. Sourced and versioned, not scraped once and forgott

Automated codebase documentation for GitHub: searchable docs, MCP context for AI agents, doc drift detection, and Friday Cleanup PRs.

ArtiBot Cloud MCP (Zhijiangyun 智匠云) — cloud MCP server for robot manipulation data & GPU workloads. 15 tools: robot fleet management, data collection & video recording, post-processing pipelines, and benchmark evaluation
Comments