Clerk enables AI agents to manage application authentication, user accounts, organizations, sessions, and access permissions, including inspecting user profiles and configuring authentication workflows.
Hermes is Nous Research's command-line agent. MCP servers are declared in its YAML config and reloaded without a restart.
This guide connects Clerk MCP to Hermes through MewCP, so Hermes can use Clerk MCP's 19 tools, like clerk_sdk_snippet, list_clerk_sdk_snippets and whoami, without your Clerk MCP credentials ever reaching the app.
Clerk MCP signs in through managed OAuth. MewCP stores the token encrypted, refreshes it before it expires and injects it only at call time. Your agent never holds it, so it can never leak it.
More apps
Manage repositories, pull requests, issues, branches and development workflows on GitHub. Automate software delivery and collaborate across engineering projects.
Connect to external APIs, webhooks and internet services through standard HTTP requests. Build integrations with virtually any platform that exposes a web-based interface.
Give AI coding agents access to a curated library of real-world website designs, screenshots, design systems, and reusable UI components. Search visual references, find similar designs, analyze layouts, extract colors and typography, compare websites, and retrieve copy-ready JSX components for building better interfaces
HotAPI provides a unified API for AI-powered image, video, and audio generation, image editing, and conversational AI. Developers can access multiple models through a single API key, track asynchronous generation tasks, and retrieve results with polling or webhooks.
Other clients
Clerk MCP works the same way in every client below. Pick yours for its own guide.
Free to start.
Scope access to the exact Clerk MCP tools and accounts you allow, work and personal side by side. Anything outside that scope is refused at call time, even when the model asks for it.
Each call is logged: what ran, on which account, and whether it worked. Failures come back structured, so the agent knows whether to retry instead of guessing.
Every app sits behind one secure MCP URL, and there is no server for you to deploy or keep running. Add an integration in the dashboard and it is live on the next call, with no config to change and no new credentials to wire up. Tools load only when a task needs them, so your agent stays fast and focused however many apps you connect.
Edit config.yaml in your Hermes config directory (~/.hermes).
Put this under the top-level "mcp_servers:" key.
Run /reload-mcp in Hermes, or start a fresh session. Sign in when the browser window opens.
Start a new chat and ask: "List the tools you can use from MewCP." You should see your connected apps.
Get Clerk SDK code snippets and patterns.
List all available Clerk SDK snippets and bundles. Filter by tag to find specific functionality.
Show the connected Clerk account, its active workspace, and the granted scopes (like `clerk whoami`).
Send feedback to the Clerk team about a problem you hit while working with Clerk for the user. Call this when a Clerk task fails, needed a workaround, a Clerk tool returned a confusing or wrong result, documentation was missing, or the user asks you to report a problem. Never include secrets, API keys, tokens, or personal data about end users. Reports are read by the Clerk team and used to improve Clerk.
List the applications in the connected workspace (like `clerk apps list`).
Get one Clerk application that the connected account can access.
Create a new application in the connected workspace (like `clerk apps create`).
Read instance configuration (like `clerk config pull`). Sensitive values are redacted. Pass keys to limit the top-level sections returned.
Read the JSON schema for instance configuration (like `clerk config schema`). Pass keys to limit the top-level sections returned.
Partially update instance configuration (like `clerk config patch`). Use dry_run first to validate without applying.
Replace the entire instance configuration (like `clerk config put`). config must include every top-level key, so start from get_instance_config. Use dry_run first.
List users of an instance (like `clerk users list`). Filters match the Backend API list-users query.
Create a user in an instance (like `clerk users create`). Named fields are merged over body, the raw Backend API create-user request.
List an application's domains, including the DNS records each one needs (dns_targets).
List OAuth providers enabled on the development instance, the credential fields each needs in production, and whether production already has them (the OAuth step of `clerk deploy`).
Create the production instance for an application on a domain you own, cloned from development (the first step of `clerk deploy`). Irreversible; requires confirm: true. Returns the DNS records to add and the next steps.
Read DNS, SSL, and email verification status for an application domain.
Ask Clerk to re-check DNS records for an application domain now, then read status with get_domain_status.
Check for additional tools whenever your task might benefit from specialized capabilities - even if existing tools could work as a fallback.
