Securely connect a platform credential without exposing the key in chat. Checks environment variables first; if not found, opens a localhost secure input page for the user to paste their key. Call once to get the URL, then call again after the user submits to complete the connection.
AI agents use keychain_secure_connect to create or update resources in UnClick — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your UnClick environment.
| Parameter | Type | Required | Description |
|---|---|---|---|
label | string | — | Optional label to distinguish multiple credentials for the same platform (default: 'default'). |
platform | string | Yes | Platform ID: github, stripe, openai, vercel, cloudflare, etc. |
setup_url | string | — | Optional URL to the platform's API key settings page, shown on the input page. |
Parameters from the server's own tool schema.
The tool creates or stores a credential connection, which is a reversible write operation. It does not execute arbitrary code, delete data, or move money. However, severity is high because misuse could lead to unauthorized credential storage or impersonation via the stored connection, affecting downstream actions.
From the tool's definition Tool description states it 'Securely connect a platform credential' and stores/establishes a connection that persists (requires two calls: first to get URL, second to 'complete the connection').
Attacks that exploit this kind of access
Securely connect a platform credential without exposing the key in chat. Checks environment variables first; if not found, opens a localhost secure input page for the user to paste their key. Call once to get the URL, then call again after the user submits to complete the connection. It is categorised as a Write tool in the UnClick MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
keychain_secure_connect accepts 3 parameters: label, platform, setup_url. Required: platform. The full parameter table on this page comes from the server's own tool schema.
Register the UnClick MCP server in PolicyLayer and add a rule for keychain_secure_connect: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches UnClick. Nothing to install.
keychain_secure_connect is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the keychain_secure_connect rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for keychain_secure_connect. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
keychain_secure_connect is provided by the UnClick MCP server (@unclick/mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →