Allows AI agents to make API calls to GitHub through the AgentKeys proxy using stored credentials, keeping secrets secure.
Allows AI agents to make API calls to Resend through the AgentKeys proxy using stored credentials, keeping secrets secure.
Allows AI agents to make API calls to Stripe through the AgentKeys proxy using stored credentials, keeping secrets secure.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@agentkeys-mcp Create an agent for email sending, assign my Resend key, and send a test email."
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
An MCP (Model Context Protocol) server that lets AI agents manage credentials and make proxied API calls through AgentKeys.
Store API keys in AgentKeys and let your agent use them safely through the proxy — without ever seeing the raw secrets.
AGENTKEYS_API_KEY=ak_ws_xxxx npx @agentkeys-io/mcpGet your workspace API key from app.agentkeys.io/settings.
Related MCP server: Credential Vault MCP
Environment Variable | Required | Default | Description |
| ✅ Yes | — | Workspace API key (starts with |
| No |
| AgentKeys web app URL |
| No |
| AgentKeys proxy URL |
Add to ~/Library/Application Support/Claude/claude_desktop_config.json:
{
"mcpServers": {
"agentkeys": {
"command": "npx",
"args": ["@agentkeys-io/mcp"],
"env": {
"AGENTKEYS_API_KEY": "ak_ws_your_key_here"
}
}
}
}Add to .cursor/mcp.json in your project:
{
"mcpServers": {
"agentkeys": {
"command": "npx",
"args": ["@agentkeys-io/mcp"],
"env": {
"AGENTKEYS_API_KEY": "ak_ws_your_key_here"
}
}
}
}Same config format — add to your MCP settings:
{
"mcpServers": {
"agentkeys": {
"command": "npx",
"args": ["@agentkeys-io/mcp"],
"env": {
"AGENTKEYS_API_KEY": "ak_ws_your_key_here"
}
}
}
}list_credentialsList all credentials stored in the workspace.
create_credentialCreate a new credential in the workspace.
Parameter | Type | Required | Description |
| string | ✅ | Unique name for this credential |
| string | ✅ |
|
| string | For | The secret value |
| string | No | Provider name (e.g. |
| string | No | Provider API base URL (e.g. |
delete_credentialDelete a credential by ID. Also revokes all associated proxy tokens.
list_agentsList all agents in the workspace.
create_agentCreate a new agent identity.
Parameter | Type | Required | Description |
| string | ✅ | Agent name (e.g. |
| string | No | What this agent does |
assign_credentialAssign a credential to an agent. Returns a proxy token.
⚠️ The proxy token is shown once — store it securely.
proxy_requestMake an API call through the AgentKeys proxy.
Parameter | Type | Required | Description |
| string | ✅ | Proxy token (starts with |
| string | ✅ | Target URL (e.g. |
| string | No | HTTP method (default: |
| object | No | Additional request headers |
| string | No | JSON string body |
1. list_credentials → see what's available
2. create_agent → create agent for this task
3. assign_credential → get proxy token
4. proxy_request → call API using proxy tokenThis server cannot be deployed
Give your AI hands. Identity, credential vault, and API gateway for autonomous agents.
Credential broker for AI agents: scoped, revocable API access with policy enforcement and audit.
Issue, rotate and revoke scoped API-key passes for 25+ providers — the agent never sees a real key
Verified, pay-per-use API tools for AI agents through one authenticated connection.