Jasper AI

This repository contains a prototype Model Context Protocol (MCP) server for interacting with the Jasper AI API.

To use this Jasper MCP server with Windsurf, add the following configuration to your Windsurfmcp_config.jsonfile:

"jasper": { "command": "npx", "args": ["-y", "https://github.com/latecheckout/jasper-mcp-proto"], "env": { "JASPER_API_KEY": "YOUR_JASPER_API_KEY" } }

ReplaceYOUR_JASPER_API_KEYwith your actual Jasper API key.

Download thejasper-mcp-prototype.dxtfile.

- Ensure you have theClaude Desktop Appinstalled. These instructions are tailored for the desktop app, as browser-based MCP integration might differ.
- You'll needNode.jsandpnpm. If you don't have Node.js, install it fromnodejs.org. You can install pnpm via npm:npm install -g pnpm.

git clone https://github.com/latecheckout/jasper-mcp-proto.git cd jasper-mcp-prototype

which node

{ "mcpServers": { ... "jasper": { "command": "PASTE_YOUR_NODE_EXECUTABLE_PATH_HERE", "args": ["PASTE_YOUR_ABSOLUTE_PATH_TO_DIST/INDEX.JS_HERE"], "env": { "JASPER_API_KEY": "YOUR_JASPER_API_KEY_HERE" } } } }

- Replace"PASTE_YOUR_NODE_EXECUTABLE_PATH_HERE"with the Node executable path you copied in step 3a.
- Replace"PASTE_YOUR_ABSOLUTE_PATH_TO_DIST/INDEX.JS_HERE"with the absolute path todist/index.jsyou copied in step 3b.
- Replace"YOUR_JASPER_API_KEY_HERE"with your actual Jasper API key.
- Ensure the resulting file is valid JSON. If you're addingjasperto an existingmcpServersobject, make sure to add a comma after the preceding server entry if necessary.

- Save the changes to the configuration file.
- Completely close and restart the Claude Desktop App for the new MCP server configuration to take effect.

You should now be able to use the Jasper MCP tools via this local MCP server in Claude.

Once correctly setup in your environment, you can ask the LLM to use jasper to write content for you. For example:

Use jasper to write a blog post about the latest trends in AI. Pick an appropriate tone, and audience.

git clone <your-repository-url> cd jasper-mcp

Install dependencies:This project usespnpmas the package manager.

-

Run in development mode:This command starts the server and uses@modelcontextprotocol/inspector. You can use the inspector to test out the MCP server.

Note:There isn't hot reloading. After making changes to the code, you'll need to runpnpm buildand then click the restart button in the MCP inspector to see your changes.

This MCP server provides the following tools and resources:

- Description: Generate content via Jasper AI. Jasper is a premium generative marketing with the user's styleguide, brand voices and audiences. Jasper can be used to apply styles or generate content for the user that matches their styleguide, brand voices and audiences.
- Seesrc/tools/generateContent.ts.

- Description: Applies a specified styleguide's rules to the provided text content and returns the styled content. This tool can be used to ensure content conforms to the user's styleguide, especially useful when generating content for the public or for specific audiences.
- Seesrc/tools/applyStyleTool.ts.

- Description: Return the style guide id belonging to the user. This style guide id can be passed to jasper's generate-content tool to use that style when creating content. It can also be used in the apply-style tool to apply a style to a given text.
- Seesrc/tools/getStyleGuides.ts.

- Description: Return a list of the brand voices/tones belonging to the user. These brand voices include a description to help the LLM and/or the user pick an appropriate tone, and a toneId that can be passed to jasper's generate-content tool to use that brand voice/tone when creating content.
- Seesrc/tools/getBrandVoices.ts.

- Description: Return a list of the audiences belonging to the user. These audiences include a description to help the LLM and/or the user pick an appropriate audience, and an audienceId that can be passed to jasper's generate-content tool to use that audience when creating content.
- Seesrc/tools/getAudiences.ts.
-

jasper://styles(Registered asjasper-styles):

- Fetches available Jasper AI styles.
- Implementation:src/resources/getStyles.ts

jasper://brandvoices(Registered asjasper-brand-voices):

- Fetches available Jasper AI brand voices (tones).
- Implementation:src/resources/getBrandVoices.ts

jasper://audiences(Registered asjasper-audiences):

- Fetches available Jasper AI audiences.
- Implementation:src/resources/getAudiences.ts

The 1Password MCP server creates a bridge that allows MCP clients such as Codex and Kiro to manage your 1Password Environments with secure authorization prompts.

This is the 1st, easiest, and cheapest PPT, slides, presentation AI generation MCP Server in the world.

Persistent memory for any AI assistant. Zero token cost until recall. Stores memories in local SQLite, ranks by 6-factor scoring, returns results 79% smaller than JSON. Works with Claude, ChatGPT, Grok, Cursor, Windsurf, and any MCP client.

A MCP server that enables AI assistants to interact with Anki, the spaced repetition flashcard application.

Enables LLM clients to interact with macOS applications through AppleScript. Built using the @beyondbetter/bb-mcp-server library, this server provides safe, controlled execution of predefined scripts with optional support for arbitrary script execution.

An MCP server for WordPress plugin audits

Turn your AI assistant into a digital marketing hub that creates, organizes, and analyzes links and QR Codes on demand.

Connect AI clients to Cal.com scheduling through the Model Context Protocol using the hosted server at mcp.cal.com or a local instance.

Sync Calendars, Scheduling Links, AI Executive Scheduling Assistant, Unified Calendar