Documentation Index
Fetch the complete documentation index at: https://docs.getquikly.com/llms.txt
Use this file to discover all available pages before exploring further.
The Quikly MCP server lets AI assistants interact with your Quikly account through the Model Context Protocol (MCP). You can create proposals, analyze briefs, get rate recommendations, and share proposals — all from your AI-powered editor or chat.
What is MCP?
Model Context Protocol is an open standard that connects AI assistants to external tools and data sources. Instead of copy-pasting between Quikly and your editor, you give the assistant direct access to Quikly’s API through structured tool calls.
What is quikly-mcp-server?
quikly-mcp-server is an npm package that exposes Quikly’s API as MCP tools. When you add it to a supported client, the AI assistant can:
- Get your profile information
- Create proposals from a project description
- Analyze a brief and extract structured requirements
- Get AI-powered rate recommendations by role, seniority, and location
- Retrieve proposal details
- Generate share links for clients
Supported clients
| Client | Status |
|---|
| Cursor | Supported |
| Claude Desktop | Supported |
| Claude Code | Supported |
Any MCP-compatible client can use quikly-mcp-server.
Installation
The server runs via npx — no global install required. You need two environment variables:
| Variable | Description |
|---|
QUIKLY_API_BASE_URL | https://api.getquikly.com/api/external/v1 |
QUIKLY_API_KEY | Your Quikly API key (create one in Settings → API Keys) |
Cursor
Add this to your Cursor MCP configuration file (.cursor/mcp.json in your project or global config):
{
"mcpServers": {
"quikly": {
"command": "npx",
"args": ["-y", "quikly-mcp-server"],
"env": {
"QUIKLY_API_BASE_URL": "https://api.getquikly.com/api/external/v1",
"QUIKLY_API_KEY": "qk_your_api_key_here"
}
}
}
}
After saving, restart Cursor or reload the MCP servers. You should see Quikly tools in the MCP panel.
Claude Desktop
Add this to your Claude Desktop configuration file:
- macOS:
~/Library/Application Support/Claude/claude_desktop_config.json
- Windows:
%APPDATA%\Claude\claude_desktop_config.json
{
"mcpServers": {
"quikly": {
"command": "npx",
"args": ["-y", "quikly-mcp-server"],
"env": {
"QUIKLY_API_BASE_URL": "https://api.getquikly.com/api/external/v1",
"QUIKLY_API_KEY": "qk_your_api_key_here"
}
}
}
}
Restart Claude Desktop after saving. The Quikly tools will appear in the tools menu.
Claude Code
claude mcp add quikly -- npx -y quikly-mcp-server \
--env QUIKLY_API_BASE_URL=https://api.getquikly.com/api/external/v1 \
--env QUIKLY_API_KEY=qk_your_api_key_here
Verify the connection
After configuring, ask your AI assistant:
“Use the quikly_me tool to check my Quikly profile.”
If everything is set up correctly, the assistant will return your name, email, and subscription tier.
The MCP server exposes the following tools:
| Tool | Description |
|---|
quikly_me | Get your profile info |
quikly_create_proposal | Create a new proposal |
quikly_analyze_brief | Analyze a brief and extract requirements |
quikly_recommend_rate | Get an AI rate recommendation |
quikly_get_proposal | Get a proposal by ID |
quikly_share_link | Generate a share link |
See the tools reference for parameters, examples, and equivalent API endpoints.
Create a dedicated API key with read,write scope for your MCP server. Label it “Cursor MCP” or “Claude MCP” so you can identify and rotate it easily.