Agent Proxy

The Infisical Agent Proxy is a credential broker for AI agents and untrusted code execution environments. It sits between your AI agents and the APIs they call including LLM providers, GitHub, Slack, and more.

Agents like Claude Code or OpenClaw route HTTP requests through the proxy, which swaps dummy credentials for real ones (or replaces auth headers entirely), before forwarding the request to the target service.

            Your private network                                Public internet

+----------+                 +-------------+                  +------------------+
| AI agent | --------------> | Agent Proxy | ---------------> |  api.slack.com   |
+----------+  request with a +-------------+ request with the |  api.github.com  |
             placeholder key        |        real credential  |  ...             |
                                    |                         +------------------+
                                    |  fetches the real
                                    |  credential values
                                    v
                             +-------------+
                             |  Infisical  |
                             +-------------+

Why Agent Proxy

Traditional secrets management involves returning credentials back to applications and services.

This is not suitable for AI agents because they are vulnerable to credential exfiltration via prompt injection; an attacker could craft a malicious prompt or payload and exfiltrate credentials from an agent back to the attacker.

Enter Infisical Agent Proxy - a proxy service backed by Infisical that prevents credential exfiltration by brokering access to credentials stored in Infisical at the network boundary.

How it works

Start by configuring the resources Agent Proxy needs within Infisical to broker your agent access to an external service.

1. Add a credential as a secret in Infisical; this can be a static secret or a dynamic secret.

2. Configure a proxied service in Infisical. This defines the external service (e.g. api.anthropic.com, api.github.com, slack.com, etc.) that Agent Proxy can broker access to using the credential.

3. Configure a machine identity for Agent Proxy using Universal Auth and another one for your agent.

Next, set up an instance of Agent Proxy on a separate host machine:

4. Start up an Agent Proxy server using the Infisical CLI with the infisical secrets agent-proxy start command here with INFISICAL_UNIVERSAL_AUTH_CLIENT_ID and INFISICAL_UNIVERSAL_AUTH_CLIENT_SECRET set in the environment.

Finally, configure your AI agent to route requests through Agent Proxy:

5. Bootstrap your AI agent’s environment to automatically route all outbound HTTP and HTTPS traffic through Agent Proxy. This can be done with the Infisical CLI and setting INFISICAL_PROJECT_ID, INFISICAL_ENVIRONMENT, INFISICAL_SECRET_PATH, and INFISICAL_AGENT_PROXY_ADDRESS in the agent’s environment.

6. Launch your agent with the infisical secrets agent-proxy connect command to start routing requests through Agent Proxy.

What you work with

- The [Infisical Agent](/integrations/platforms/infisical-agent) fetches secrets to disk for applications.
- The [Infisical Proxy](/integrations/platforms/infisical-proxy) caches the Infisical API.
- [Gateways](/documentation/platform/gateways/overview) let Infisical reach into private networks.

Next steps