- Home
- MCP servers
- Jasper
Jasper
- typescript
0
GitHub Stars
typescript
Language
6 months ago
First Indexed
3 months ago
Catalog Refreshed
Documentation & install
Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.
Installation
Add the following to your MCP client configuration file.
Configuration
View docs{
"mcpServers": {
"latecheckout-jasper-mcp-proto": {
"command": "npx",
"args": [
"-y",
"https://github.com/latecheckout/jasper-mcp-proto"
],
"env": {
"JASPER_API_KEY": "YOUR_JASPER_API_KEY"
}
}
}
}This guide walks you through running the Jasper MCP Server locally and connecting it to MCP clients like Windsurf or Claude Desktop. The server exposes Jasper AI capabilities through the Model Context Protocol, letting you generate content, apply styles, and fetch Jasper resources directly from your LLM workflows. You’ll learn how to install, configure, and use the server securely from your workstation.
How to use
You access Jasper through an MCP client by configuring the client to load a local or remote MCP server. The server supports two practical approaches: a quick local session using a package runner, and a fully local build using your own Node executable. Once configured, you can request content generation, style applications, and Jasper-branded resources as part of your conversational workflow.
How to install
Prerequisites: install Node.js and a package manager. You will also need a Jasper API key for full functionality.
Step 1. Install dependencies and build the server.
# Prerequisites
# Ensure Node.js is installed
# If you don’t have pnpm, install it globally
npm install -g pnpm
# Clone the project, then install and build
git clone https://github.com/latecheckout/jasper-mcp-proto.git
cd jasper-mcp-prototype
pnpm install
pnpm run build
Configure and run via MCP client
You can connect the server to MCP clients using either a remote execution approach or a local build. The following configurations show two explicit methods you can apply in your client.
# Method 1: Quick local execution via npx (remote MCP package)
{"mcpServers": {
"jasper": {
"type": "stdio",
"name": "jasper",
"command": "npx",
"args": ["-y", "https://github.com/latecheckout/jasper-mcp-proto"],
"env": {
"JASPER_API_KEY": "YOUR_JASPER_API_KEY"
}
}
}}
# Method 2: Local build using your Node executable
# Replace placeholders with actual paths from your environment
{"mcpServers": {
"jasper_local": {
"type": "stdio",
"name": "jasper_local",
"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"
}
}
}}
Available tools
generate-content
Generate content via Jasper AI, applying style guides, brand voices, and audiences to match your desired tone and constraints.
apply-style
Apply a specific style guide to the provided text to ensure consistency with brand rules and audience expectations.
get-jasper-style-guides
Return the style guide id(s) associated with the user for Jasper-based content generation.
get-jasper-brand-voices
Return a list of Jasper brand voices/tones with descriptions and tone IDs for generation.
get-jasper-audiences
Return the audiences available to the user, including descriptions and IDs for targeting.