Skip to main content
MCP server CX Codex

TAP — Claude Code MCP server: credential isolation for AI agents

Keeps API keys and passwords out of agent prompts: the agent sees a placeholder, TAP swaps in the real secret before the tool call.

Install into Claude Code · Platform CLI: remote server All methods and platforms ↓
claude mcp add --transport http tap https://mcp.tap.human.tech/mcp
Open on GitHub

What TAP does

When the agent calls a tool, TAP checks the request against policy, asks for human approval if configured, and injects the secret from storage. The placeholder looks like {{credential:stripe-key}}. The agent never sees the real value and cannot log it or send it elsewhere.

Inside: proxy, policy engine, Telegram and Matrix approval bots, CLI, and MCP server. The remote endpoint is https://mcp.tap.human.tech/mcp. Self-hosting needs Postgres; the source includes enclave key-management modules.

The repository is Apache-2.0. The managed version stores secrets in a hardware enclave developers cannot read. Self-hosting puts key hardening and policy correctness on you.

What it helps with

  • isolate API credentials from the agent context
  • require human approval before a risky tool call
  • check requests against policy before execution
  • replace a placeholder with the real secret before sending it to the tool
  • run a credential proxy without putting secrets in the prompt

Example prompts for the agent

  • Make a Stripe request with {{credential:stripe-key}}
  • Send email via SendGrid using {{credential:sendgrid-token}}

How to install TAP

Platform CLI: remote server

claude mcp add --transport http tap https://mcp.tap.human.tech/mcp

Step by step, with commands for each platform: How to add an MCP server to Claude Code, Codex, Cursor, VS Code, Gemini CLI and more

Questions about TAP

How to install TAP in Claude Code?

Run claude mcp add --transport http tap https://mcp.tap.human.tech/mcp. The server connects remotely; credentials are configured in the TAP dashboard.

What does TAP do?

Swaps placeholders like {{credential:key-name}} with real secrets before tool invocation. The agent works with fake values; real keys stay in the proxy.

Why use TAP?

Keeps secrets out of agent context. Without TAP the key goes into the prompt and the agent can log it or pass it to another tool. With TAP the agent only sees a placeholder.

Similar MCP servers

Everything for Security →

Project sponsors

Companies that keep this analytics open
Gold sponsor

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor