AI Integration
MeowPass ships an MCP server. Use it with Claude Code, Cursor, Windsurf, or any MCP-compatible agent.
MCP server vs. the Credential Gateway
This page covers the MCP server: how an agent reads and manages your secrets. To give agents brokered, short-lived access to external providers (OpenAI, GitHub, Slack…) without ever handing over a key, see the AI Credential & Integration Gateway.
Setup
1. Create an API key
2. Add to Claude Code
Or add to Cursor / Windsurf
Available Tools
| Tool | What it does | Env |
|---|---|---|
| meowpass_whoami | Current user, email, plan | None |
| meowpass_list_vaults | List all vaults | None |
| meowpass_list_secrets | List keys (filter by env or all) | optional |
| meowpass_get_secret | Get a secret's value | optional |
| meowpass_set_secret | Create or update a secret | optional |
| meowpass_delete_secret | Remove a secret | optional |
| meowpass_create_vault | Create a new vault | None |
| meowpass_delete_vault | Delete a vault | None |
| meowpass_pull | Pull secrets (filter by env) | optional |
| meowpass_diff | Compare .env with vault env | optional |
| meowpass_init | Scan .env files + detect .meowpass.yaml | None |
| meowpass_run | Run with injected secrets | optional |
| meowpass_run_redacted | Run, scrubbing secrets from output | optional |
Example Workflows
Drift detection
"Is my .env up to date with the vault?"
→ Claude calls meowpass_diff and reports which keys are missing or changed.
Secret scaffolding
"I just added Stripe to this project, set up the secrets."
→ Claude detects Stripe SDK, creates placeholder secrets (STRIPE_SECRET_KEY, STRIPE_PUBLISHABLE_KEY, STRIPE_WEBHOOK_SECRET).
Safe deployment
"Deploy this with production secrets."
→ Claude calls meowpass_run_redacted to inject secrets and run the deploy command. Secret values never appear in the chat.
Redacted Mode
The meowpass_run_redactedtool injects secrets into a subprocess but scrubs all secret values from the output before returning to the LLM. The AI orchestrates the action without ever "seeing" the secret values.
Response:
Security Considerations
- • API keys have scopes: create read-only keys for AI agents
- • Use
meowpass_run_redactedto prevent secrets from leaking into LLM context - • Every MCP access is logged in the audit trail with
source: mcp - • Revoke compromised API keys instantly:
mp apikey revoke <id>