Devto MCP Server

DevTo MCP server — AI work management for Claude Code

Local serverstdio

What is the Devto MCP server?

If you already use Devto, the devto mcp server is the piece that lets your assistant work with it directly. DevTo MCP server — AI work management for Claude Code.

What the server does

DevTo lives inside Claude Code as an MCP server. It manages your sprint, your tickets, and your project tracker — without you ever leaving your terminal. Status updates, ambient comments on transitions, plan generation from natural language, semantic ticket matching. All from your editor.

Available tools

The toolset is worth reading before you wire it up, because it tells you what the integration is really for:

  • get_project_summary — lightweight snapshot of active work + epic progress (called at session start)
  • get_status — aggregate project metrics
  • list_epics — epic progress bars
  • get_epic — deep dive into a single epic
  • create_plan — AI-generated epic + stories + subtasks (preview only)
  • confirm_plan — execute a previously-previewed plan
  • delete_issue — destructive, asks for confirmation
  • get_tasks — list open tasks, optionally filter by epic
  • search_issues — full JQL support

Installation

devto-mcp on npm is all you need. Most clients run it directly, so configuration is a few lines and a restart.

Where it fits

Plenty of developer tooling servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. Devto's toolset — get_project_summary, get_status, list_epics and 6 more — is a fair guide to whether it matches your workflow. It is maintained by kelvyn02; worth a glance at recent repository activity before you build anything load-bearing on it.

We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.

Worth knowing first

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • With 9 tools registered it takes up a noticeable share of the context window; turn it off in projects that never touch Devto.
  • Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.

Available tools

ToolWhat it does
get_project_summarylightweight snapshot of active work + epic progress (called at session start)
get_statusaggregate project metrics
list_epicsepic progress bars
get_epicdeep dive into a single epic
create_planAI-generated epic + stories + subtasks (preview only)
confirm_planexecute a previously-previewed plan
delete_issuedestructive, asks for confirmation
get_taskslist open tasks, optionally filter by epic
search_issuesfull JQL support

How to install the Devto MCP server

{
  "mcpServers": {
    "devto-1": {
      "command": "npx",
      "args": ["-y", "devto-mcp"]
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Example prompts to try

  • Use Devto to get project summary.
  • Use Devto to get status.
  • Use Devto to list epics.

Frequently asked questions

It connects Devto to MCP-compatible AI assistants such as Claude and Cursor, exposing 9 tools (get_project_summary, get_status, list_epics, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Devto directly.