What is AgentSecrets?
The Zero-Knowledge Difference
How AgentSecrets Works
Installation
Quick Start
Migrating from .env Files
Migrating from Vault / AWS
Migrating from dotenv-vault
Production Checklist
Credential Exposure
What Zero-Knowledge Means
The Proxy Model
The Three-Layer Model
Environments
Agent Identity
Storage Modes
The No get() Principle
Secret-Level Policies
Cloud Overview & Architecture
The Dual-Engine Model
Cloud Resolver Data Plane
Workload & Agent Tokens
Egress Allowlists & Audit Streams
Cloud REST API Reference
Account (init / login)
Server & Self-Hosting (server)
Docs
Shell Autocompletion
Keychain Auth
Secrets
Environments
Credential Proxy
env Injection
Workspaces & Teams
Projects
Agent Identity
Audit & Governance
Integrations Overview
Claude Desktop
Cursor
OpenClaw
HTTP Proxy (Any)
LangChain (Soon)
CrewAI (Soon)
CI/CD Pipeline
SDK Overview
Python SDK
Python API Reference
Python SDK Manual Testing
JavaScript SDK (Soon)
Ecosystem Overview
Zero-Knowledge MCP Server
Server Overview
5-Layer Architecture
Self-Hosting Guide
Authentication & Keys
Workspaces & Teams
Projects & Scope
Environments
Secrets & Sync Protocol
Agent Identity Resolution
Telemetry & Metrics Engine
Audit Log Sync
API Endpoint Reference
Security Overview
Anti-Impersonation & Process Verification
Encryption Model
Zero-Knowledge Sync
Proxy Security Layers
Threat Model
OWASP Top 10 Mitigation
Security FAQ
Third-Party Audit
Reporting Vulnerabilities
Guides Overview
Building on the SDK
Stripe Integration
OpenAI Integration
Multi-Agent Setup
Onboarding Team
CI/CD Pipeline
Publishing ZK MCP
Rotating Credentials
Auditing Team Activity
Dev to Production
Kubernetes Deployment
Monorepo Setup
Production Proxy Hardening
vs .env Files
vs HashiCorp Vault
vs AWS Secrets Manager
vs dotenv-vault
vs Infisical
When Not to Use
Proxy Not Starting
Proxy Not Resolving
Domain Blocked
Sync Conflicts
MCP Not Connecting
Session Token Errors
Proxy Session Authorization
Keychain Storage & Backends
SSRF & Destination Rules
Installation Issues
Error Codes Reference
Frequently Asked Questions
v3.1.x
v3.0.0
v2.1.0
v2.0.0
v1.4.0
v1.3.x
v1.2.0
v1.1.x
v1.0.x
IntegrationsCursor

Using AgentSecrets with Cursor

Cursor has native support for the Model Context Protocol (MCP). By using the native AgentSecrets MCP server, you can allow Cursor's agent to execute tools that require authenticated API access without ever pasting your API keys into Cursor or exposed configuration files.


Setup Instructions

1Store Credentials

Ensure you have stored your credentials in your local OS Keychain via the AgentSecrets CLI:

agentsecrets secrets set STRIPE_KEY=sk_live_...

2Auto-Configure Cursor

Run the native mcp install command to automatically register AgentSecrets with your local Cursor editor:

agentsecrets mcp install

This automatically detects your Cursor configuration directory and adds the AgentSecrets MCP definition to your Cursor mcp.json file.

3Restart Cursor

Restart the Cursor application to load the new MCP server configurations.


Verifying the Connection

Once Cursor restarts, verify the connection status:

  1. Open Cursor Settings (Cmd/Ctrl + Shift + J or click the gear icon in the top right).
  2. Navigate to Features > MCP.
  3. You should see agentsecrets listed as an active MCP server with a green status indicator, showing that the stdio server is running and ready.

How it Works in Cursor

You can test the integration directly within Cursor Chat or Cursor Composer. For example, ask Cursor:

"Can you retrieve my Stripe balance?"

Cursor's agent will run the built-in api_call tool, passing "STRIPE_KEY" as the key reference:

  1. The built-in MCP server receives the request and calls the local proxy layer.
  2. The proxy verifies the target domain (api.stripe.com) against the allowlist.
  3. The proxy resolves the key value securely from your OS Keychain, injects it into the outbound request's headers, and executes the call.
  4. The proxy scans the API response, redacts any echoes of the credential, and returns only the clean response body to Cursor.

Cursor receives the data it needs to continue working, but the actual key value never enters the Cursor process space or logs.

Was this helpful?
Thanks for your feedback!
Your feedback helps us improve the platform.