Harny AI automates website creation and management through natural-language instructions. Build and edit websites, customize layouts and content, manage pages and components, and publish updates without manually handling frontend code.
Claude is Anthropic's AI assistant, available as a desktop app and in Cowork. It supports custom connectors, so it can call MCP servers directly from a chat.
This guide connects Harny AI MCP to Claude Desktop through MewCP, so Claude Desktop can use Harny AI MCP's 6 tools, like describe, get_snippet and diagnose, without your Harny AI MCP credentials ever reaching the app.
Harny AI 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.
Turn your AI agent into a creative studio The world's best image, video, audio and 3D models, inside the AI assistant you already use.
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
Other clients
Harny AI MCP works the same way in every client below. Pick yours for its own guide.
Free to start.
Scope access to the exact Harny AI 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.
In Claude, open Settings → Connectors, then choose Add custom connector.
Name it "mewcp" and paste the URL.
A browser window opens the first time the client connects. Sign in and approve access. No API key needed.
Start a new chat and ask: "List the tools you can use from MewCP." You should see your connected apps.
What Harny is and what this key reaches. Harny is a private long-term memory for each person who uses an app: remember what a user tells you, recall it later, store user preferences. Returns the platform, every tool this key may call with its full schema, and the trust signals. The first call an assistant should make. Needs a key.
A ready-to-use code snippet for one Harny capability, so the code you write calls it the right way. Needs a key.
Where the app's Harny connection stands and what to do about it: the state of each part, and how fresh each connected source is. Read-only. Needs a key.
Adds a person (an end user of the app, whose long-term memory the app will keep) or returns the one that exists, as `POST /v1/users` does. The answer carries the person's key once. Needs the app's key (fsa_ prefix).
A fresh one-time link the owner opens to take ownership of this app. Use it if the link you relayed earlier expired or was lost. The link is not an API key. Needs the app's key (fsa_ prefix).
The setup bundle a coding assistant uses to stand up this app's agent in the business's own deploy: app facts, key variable names and handling rules (never key values), sources to connect, the acting policy as the business set it, the model preset, deploy recipes and the starter config, plus the rendered prompt and an installable skill file. shape is common:<path id> or developer. Read-only as far as the app's settings go: it does not change the acting policy, sources or keys. Needs the app's key (fsa_ prefix).
