MCPLow riskUnclaimed
TAP
Credential isolation for AI agents: placeholder secrets, policy checks, optional human approval.
human.techhuman.tech/tap
server.json
{
"$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
"name": "tech.human/tap",
"description": "Credential isolation for AI agents: placeholder secrets, policy checks, optional human approval.",
"title": "TAP",
"repository": {
"url": "https://github.com/holonym-foundation/tap-oss",
"source": "github"
},
"version": "0.1.0",
"websiteUrl": "https://tap.human.tech",
"remotes": [
{
"type": "streamable-http",
"url": "https://mcp.tap.human.tech/mcp",
"headers": [
{
"description": "TAP agent API key (create one at tap.human.tech)",
"isRequired": true,
"isSecret": true,
"name": "X-TAP-Key"
}
]
}
]
}Permissions
DeclaredDetected
Runs code—None
Installs—None
Runs install scripts—None
Network
mcp.tap.human.techmcp.tap.human.techNeeds credentials
X-TAP-KeyX-TAP-KeyOutside the workspace—None
Agent tools—None
Checks
Low risk · Nothing worth a warning was found.
Not reviewed by a person · Checked by rules; the model review is not switched on yet.
Versions
- #10.1.0latestOct 7, 2026