Home › Other › wundervault-mcp
wundervault-mcp
Zero-knowledge MCP secrets vault for AI agents: secrets injected at runtime, never seen by the model
Topics: Other Tools and Integrations
Connect
Review any command before running it. Package names and URLs come from the server's own registry entry.
Package (npm 1.7.2)
npx -y @wundervault/[email protected]
Or add to your MCP client config:
{
"mcpServers": {
"wundervault-mcp": {
"command": "npx",
"args": [
"-y",
"@wundervault/[email protected]"
],
"env": {
"WUNDERVAULT_AGENT_NAME": "<YOUR_VALUE>",
"WUNDERVAULT_AGENT_TOKEN": "<YOUR_VALUE>"
}
}
}
}
WUNDERVAULT_AGENT_NAMErequired — Agent name registered with the local wundervault-agent daemon (run onboard.py to register).WUNDERVAULT_AGENT_TOKENsecret — Optional daemon auth token. Defaults to ~/.wundervault/agents/<agentName>.token.
Related servers
servers
MCP server that exercises all the features of the MCP protocol
screenpipe
Search your local screen recordings, audio transcripts, and computer activity from screenpipe.
apify-mcp-server
Extract data from any website with thousands of scrapers, crawlers, and automations on Apify Store ⚡
klavis
MCP server for progressive tool usage at any scale (see https://klavis.ai)
mcp-obsidian
Interacting with Obsidian via REST API
metorial
Connect AI agents to 600+ integrations with a single interface - OAuth, scaling, and monitoring included
Listed in punkpeye/awesome-mcp-servers (MIT)
Data from the Official MCP Registry