
Security News
Anthropic Identifies Biased Reasoning and Recklessness as Drivers of Claude’s PyPI Attack
Anthropic found biased reasoning and recklessness drove Claude Mythos 5 to publish malware on PyPI and compromise a security vendor.
@agentkeys-io/mcp
Advanced tools
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/mcp
Get your workspace API key from app.agentkeys.io/settings.
| Environment Variable | Required | Default | Description |
|---|---|---|---|
AGENTKEYS_API_KEY | ✅ Yes | — | Workspace API key (starts with ak_ws_) |
AGENTKEYS_URL | No | https://app.agentkeys.io | AgentKeys web app URL |
AGENTKEYS_PROXY_URL | No | https://proxy.agentkeys.io | 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 |
|---|---|---|---|
name | string | ✅ | Unique name for this credential |
type | string | ✅ | API_KEY | BASIC_AUTH | CUSTOM_HEADER | QUERY_PARAM | COOKIE |
value | string | For API_KEY | The secret value |
provider | string | No | Provider name (e.g. stripe, resend, github) |
baseUrl | string | No | Provider API base URL (e.g. https://api.resend.com) |
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 |
|---|---|---|---|
name | string | ✅ | Agent name (e.g. marketing-bot) |
description | 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 |
|---|---|---|---|
proxyToken | string | ✅ | Proxy token (starts with pxr_) |
url | string | ✅ | Target URL (e.g. https://api.resend.com/emails) |
method | string | No | HTTP method (default: GET) |
headers | object | No | Additional request headers |
body | 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 token
FAQs
MCP server for managing credentials and agents through AgentKeys
The npm package @agentkeys-io/mcp receives a total of 7 weekly downloads. As such, @agentkeys-io/mcp popularity was classified as not popular.
We found that @agentkeys-io/mcp demonstrated a healthy version release cadence and project activity because the last version was released less than a year ago. It has 1 open source maintainer collaborating on the project.

Security News
Anthropic found biased reasoning and recklessness drove Claude Mythos 5 to publish malware on PyPI and compromise a security vendor.

Research
/Security News
Malicious Chrome and Firefox extensions target Axiom Trade and Padre users, stealing session tokens and wallet data.

Security News
GPT-6 Astra hits 100% on ExploitBench and finds zero-days autonomously, while independent tests reveal scope violations and monitoring gaps.