mcp-keyward
Enables secure, authenticated HTTP requests to OpenAI's API by injecting stored API keys server-side, preventing exposure of credentials to the AI agent.
π mcp-keyguard
Your AI agent should never see your API keys. Now it won't.
mcp-keyguard is a local MCP server that acts as a secure proxy between your AI agent (Claude, Cursor, Windsurf...) and any external API.
Instead of pasting your OpenAI, Stripe or GitHub keys into the chat context, you store them encrypted on your machine. The agent calls mcp-keyguard, which injects the real key server-side and returns the result.
The key never leaves your machine. The agent never sees it.
Why this matters
In 2025, a vulnerability in a popular MCP hosting platform exposed thousands of API keys from over 3,000 servers. The root cause? Keys passed through infrastructure the user didn't control.
mcp-keyguard is the opposite: fully local, zero external dependencies, your keys encrypted at rest with AES-128.
Related MCP server: aarifmms/keyblind
How it works
Your prompt β Claude β mcp-keyguard β [injects real key] β External API
β
Key never leaves hereInstallation
Requirements: Python 3.10+
pip install mcp httpx cryptography
git clone https://github.com/ggc180820/mcp-keyguard.git
cd mcp-keyguardAdd to your claude_desktop_config.json:
{
"mcpServers": {
"mcp-keyguard": {
"command": "python",
"args": ["/path/to/mcp-keyguard/main.py"]
}
}
}Restart Claude Desktop. Done.
Usage
1. Store a key (you do this once per key)
"Use add_key to store my OpenAI key with alias 'openai',
header_name 'Authorization', header_prefix 'Bearer '"
2. Make authenticated requests (Claude does this automatically)
"Use make_request with alias 'openai' to call
https://api.openai.com/v1/models"
3. Check what's stored
"Use list_keys"
β Shows aliases and headers. Never the real values.
Tools
Tool | What it does |
| Store an API key encrypted in the vault |
| List stored aliases β values are never shown |
| Make an authenticated HTTP request, key injected server-side |
| Remove a key from the vault |
Security model
Keys are encrypted with Fernet (AES-128-CBC + HMAC-SHA256)
The encryption key lives in
vault.keyon your machine onlyAll HTTP requests are made locally with a 30s timeout
Never commit
vault.keyorvault.jsonto git (already in.gitignore)
mcp-keyguard Pro
Need more control? Pro adds:
Feature | Free | Pro |
Encrypted local vault | β | β |
Unlimited keys | β | β |
Multiple vaults (per project/client) | β | β |
Audit log (who used which key, when, where) | β | β |
Key rotation alerts | β | β |
License
MIT β free forever for personal use.
This server cannot be deployed
Maintenance
Related MCP Connectors
A secret store for AI agents: the agent never sees the plaintext.
Secrets for developers and agentsβsecure context and workflows without exposing secret values.
Encrypted store for API keys and database URLs your code needs. Use them without reading them.
Give your AI hands. Identity, credential vault, and API gateway for autonomous agents.
Related MCP Servers
- AlicenseAqualityDmaintenanceLocal AES-256-GCM encrypted vault for AI agents. Resolve {{PLACEHOLDER}} secrets in prompts at runtime β LLMs never see real API keys. Argon2id key derivation, zero cloud.258 npm2MIT
- AlicenseAqualityDmaintenanceEncrypted secrets vault that blinds AI agents to API keys. Stores secrets in AES-256-GCM encrypted SQLite vault, resolves them at runtime via MCP values never appear in LLM conversation transcripts. Sandbox .env files with deterministic fakes.739 npm3MIT
- AlicenseNot gradedqualityCmaintenanceEnables LLM agents to securely use credentials like passwords and API keys without exposing them in the context window, through encrypted storage and proxy-based injection.3 npm2MIT
- AlicenseNot gradedqualityBmaintenanceBounded egress gateway & secret proxy for AI agents and applications, enabling safe credential injection into upstream requests while keeping raw secrets out of LLM prompt contexts.8 npmMIT