About Dutify
Dutify is a hosted MCP server for accessing the Dutify suite from agents and MCP clients. Its tools cover project management, call recordings, a wiki, and feature requests, with API-key scopes and workspace permissions enforced on each data call.
Key features
- 01Project tasks, sprints, and time tracking
- 02Call recordings, transcripts, and search
- 03Wiki spaces, pages, and search
- 04Feature requests, votes, and comments
- 05Workspace and account discovery
Use cases
- 01Manage project tasks and sprints
- 02Search call transcripts and recordings
- 03Find or update wiki pages
- 04Review feature requests and votes
MCP support
The hosted server uses Streamable HTTP and authenticates data calls with an X-API-Key header. It exposes tools across Dutify Cloud, Dutify Hub, Codexum, and Roadmarq.
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://mcp.dutify.aiclaude mcp add --transport http dutifyai-dutify https://mcp.dutify.ai{"mcpServers":{"dutifyai-dutify":{"type":"http","url":"https://mcp.dutify.ai"}}}Open in Cursor{"servers":{"dutifyai-dutify":{"type":"http","url":"https://mcp.dutify.ai"}}}Open in VS Code{"mcpServers":{"dutifyai-dutify":{"type":"http","url":"https://mcp.dutify.ai"}}}{"mcpServers":{"dutifyai-dutify":{"serverUrl":"https://mcp.dutify.ai"}}}Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.
https://mcp.dutify.aiAuth requiredTools
Details
From the project README
Dutify MCP server
One hosted MCP server for the whole Dutify suite. Nothing to install: point your MCP client at the URL and pass an API key.
https://mcp.dutify.ai
Transport: Streamable HTTP. Auth: X-API-Key header.
What your agent can do
189 tools across four products:
| Product | Tools | What they cover |
|---|---|---|
| Dutify Cloud (project management) | pm_* (107) | Tasks, subtasks, comments, sprints, views, custom fields, tags, time tracking, automations, webhooks |
| Dutify Hub (calls) | hub_* (32) | Call recordings, transcripts, summaries, search, Lens chat over your calls, send call items to Jira / ClickUp / Airtable |
| Codexum (wiki) | wiki_* (24) | Spaces, pages, search, attachments, public sharing |
| Roadmarq (feature requests) | fr_* (18) | Feature requests, bugs, votes, comments, statuses |
Plus discovery tools: whoami, list_workspaces, find_my_workspace, list_accounts, list_spaces, list_boards, get_api_catalog, get_endpoint_examples.
The backend enforces your key's scopes and your current workspace permissions on every call. The tool list is visible without a key; every data call needs one.
Get a key
- Sign up free at dutify.cloud (or hub.dutify.ai for Hub).
- Create a personal key (
du_live_…) in your account settings. It works across every product you have access to.
Workspace keys also work: dk_live_… (Cloud, Codexum, Roadmarq only) and dh_live_… (Hub only).
Connect
Claude Code
claude mcp add --transport http dutify https://mcp.dutify.ai --header "X-API-Key: du_live_YOUR_KEY"
Cursor (~/.cursor/mcp.json), Claude Desktop and other JSON-config clients
{
"mcpServers": {
"dutify": {
"url": "https://mcp.dutify.ai",
"headers": { "X-API-Key": "du_live_YOUR_KEY" }
}
}
}
Cline (cline_mcp_settings.json)
{
"mcpServers": {
"dutify": {
"type": "streamableHttp",
"url": "https://mcp.dutify.ai",
"headers": { "X-API-Key": "du_live_YOUR_KEY" }
}
}
}
VS Code (.vscode/mcp.json)
{
"servers": {
"dutify": {
"type": "http",
"url": "https://mcp.dutify.ai",
"headers": { "X-API-Key": "du_live_YOUR_KEY" }
}
}
}
First call
Ask your agent to run whoami, then list_workspaces. Pass the workspace on each data call, or set a default with an X-Dutify-Workspace header (identifier or name).
Related
- dutify-cloud-ai-skill: Claude Code skill for calling the same products over plain HTTP.
- Official MCP Registry:
io.github.dutifyai/dutify
Support
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.