Dreamwork logo

Dreamwork

Find jobs, tailor application materials, manage preferences, and track applications through Dreamwork.

Install Dreamwork

Pick your client, then add it in one click or paste the config.

Streamable HTTP (Remote)
~/Library/Application Support/Claude/claude_desktop_config.json
claude_desktop_config.json
{
  "mcpServers": {
    "dreamwork-2": {
      "command": "npx",
      "args": [
        "-y",
        "@dreamworkhq/mcp"
      ],
      "env": {
        "DREAMWORK_API_KEY": "YOUR_VALUE_HERE",
        "DREAMWORK_API_URL": "YOUR_VALUE_HERE",
        "DREAMWORK_UNREAD_NOTICES": "YOUR_VALUE_HERE",
        "DREAMWORK_TELEMETRY": "YOUR_VALUE_HERE",
        "DO_NOT_TRACK": "YOUR_VALUE_HERE"
      }
    }
  }
}

Settings → Developer → Edit Config, merge this into mcpServers, then fully quit and reopen Claude Desktop.

Values are written into the snippet above so you can paste it as is. They never leave your browser.

Hosted endpointLive · 3d agoLive Remote EndpointOur automated health check connected to this remote MCP endpoint successfully.Last checked 11/3/2026, 8:45:32 PM

Clients with native remote MCP support can connect directly to this URL.

Remote endpoint
https://mcp.dreamworkhq.com/mcp

Install not yet sandbox-tested— the server itself is confirmed live (we called its tools/list endpoint). The stdio install command is a separate, ongoing check.

Overview

Dreamwork MCP server connects AI assistants to Dreamwork’s job-search platform for discovering roles, preparing application materials, and managing an application pipeline. It runs as a hosted Streamable HTTP service or an on-demand stdio package that calls the Dreamwork API. Use it when an agent needs ranked job matches, tailored resumes and cover letters, preference-aware filtering, or application-status tracking. Public job browsing works without an account key, while personalized matching and account actions require authentication.

Use cases

  • Search and rank roles against a candidate’s preferences
  • Save and organize promising jobs in a pipeline
  • Prepare tailored resumes, cover letters, and application answers
  • Track application materials and board-state changes
  • Import a public job posting into a private application workflow

Key features

  • Ranked job matching with filters and pagination
  • Pipeline management for saved and applied roles
  • Asynchronous resume and cover-letter generation
  • Application document editing, replacement, and restoration
  • Preference and career-record management
  • Stdio and Streamable HTTP transports

Tools71

What Dreamwork lets your agent do. Expand a tool for its parameters.

Verified live~17.0k tokens of context

Security & health

What it can reach and how reliably it runs — from our own checks, not the maintainer’s claims.

ActiveLast checked 3d ago

Recent health check succeeded.

6/6 checks healthy over the last 24d

What it can do

From the 71 tools this server returned when we ran it.

Can delete or modify data · 2Handles credentials · 2Makes network requests · 15Read-only tools · 69
Tool definitions changed on 2026-10-26. Review them if you approved this server earlier.
Network at startup3 connections
Files written at startup1
Install scriptsNone
npm provenanceSigned build
Package age143 days
Maintainers3

Observed 2026-10-26 in an isolated sandbox. A description of reach, not a security audit.

Supply-chain signal

No high-severity advisories surfaced by our automated scan.

Critical 0High 0Medium 0Low 0

Scanned 7d ago via OSV.dev · @dreamworkhq/mcp (npm)

Adoption & maintenance

Factual signals from GitHub, npm, and our automated checks — not a rating.

GitHub stars13Stargazers on the source repository.
npm downloads3.4kPackage downloads in the last 30 days.
Last commit3d agoMost recent push to the default branch.
Availability100%Our rolling endpoint + install checks that succeeded.
Tools exposed71Callable tools this server registers over MCP.
Directory activity4 viewsConfig copies, upvotes, and views on AllMCPs.

How Dreamwork works

What Dreamwork MCP server does

Dreamwork MCP server gives an AI assistant access to job discovery and application-management workflows in the Dreamwork platform. It can retrieve ranked matches, inspect individual listings, save or dismiss roles, restore dismissed matches, and import public job URLs into a private pipeline. Pipeline tools represent saved and applied roles as board cards and let the account holder record state changes without contacting an employer.

The server also handles application preparation. Agents can queue tailored resumes, cover letters, and employer-question answers; check generation status; revise or format materials; strengthen documents against recorded career evidence; restore earlier versions; and retrieve short-lived download links for application documents. A supplied resume or cover letter can replace an application document without model rewriting, subject to revision and lock checks.

How it works

The MCP client is a gateway rather than a standalone job database. It sends requests to Dreamwork’s hosted API over HTTPS. The package can run through stdio, with JSON-RPC frames on stdout, or clients can connect to the Streamable HTTP endpoint at https://mcp.dreamworkhq.com/mcp.

Without credentials, public browsing tools can search and read public listings. An API key enables account-specific functions such as ranked matches, saved roles, application materials, preferences, pipeline records, and application readiness. Consequential actions use Dreamwork’s authorization and receipt flow; some actions require a confirmation token before proceeding.

Preference tools read and update target roles, locations, work modes, compensation, seniority, exclusions, availability, and related settings. Career-record tools keep resume-derived facts, person-stated preferences, and unconfirmed hypotheses separate. Preparation operations are asynchronous, so callers should use status tools before assuming materials are ready.

Setup and configuration

The stdio package can be launched on demand with:

Terminal
npx -y @dreamworkhq/mcp

Point an MCP client at that command and pass DREAMWORK_API_KEY in its environment for account access. Claude Desktop and Cursor use this arrangement. The hosted endpoint can be added as a custom connector in supported clients, where the user signs in to Dreamwork; clients that support request headers can send a bearer API key instead.

DREAMWORK_API_URL changes the API endpoint, which is useful for local development or a self-hosted API. DREAMWORK_UNREAD_NOTICES controls whether tool results include a notice about unread recruiter mail. DREAMWORK_TELEMETRY and DO_NOT_TRACK disable the anonymous install-usage telemetry described by the package.

Tools and capabilities

  • Search ranked matches with pagination, filters, salary, location, remote terms, match scores, and saved or applied state.
  • Inspect job descriptions, eligibility results, source postings, material readiness, and pipeline associations.
  • Save, dismiss, restore, import, and organize roles in the application pipeline.
  • Record applications made outside Dreamwork with person attestation and an application date.
  • Prepare, edit, format, strengthen, replace, restore, and download application materials.
  • Readiness-check onboarding answers, save person-stated answers, and manage job-search preferences.
  • Store and confirm career hypotheses without automatically turning them into profile facts or matching filters.

The server also exposes prompts for recurring workflows including morning updates, finding and preparing roles, applying to prepared roles, interview preparation, and Autopilot setup.

Reviews

No reviews yet — be the first to share how it worked for you.

Frequently Asked Questions about Dreamwork

Dreamwork is an MCP server that connects AI assistants to the Dreamwork job-search platform. Its main tools find and inspect jobs, manage saved and dismissed matches, prepare resumes and cover letters, update application preferences, and track roles in a personal application pipeline. Public browsing works without an API key; account workflows require one.

Run `npx -y @dreamworkhq/mcp` from an MCP client configuration. The package is launched on demand, so there is no separate installation step. Add `DREAMWORK_API_KEY` to the client environment for personalized matching and account tools, or run without it for public job browsing.

Yes, Dreamwork works with Cursor through its stdio MCP configuration. Set the command to `npx -y @dreamworkhq/mcp` and pass `DREAMWORK_API_KEY` in the environment when account access is needed. The hosted Streamable HTTP endpoint is another connection option for clients that support it.

Without an API key, Dreamwork provides free guest access to public, read-only job browsing. An agent can browse and read public listings, while account-specific functions such as ranked personal matches, saved jobs, tailored materials, and pipeline management require a Dreamwork API key.

Use `https://mcp.dreamworkhq.com/mcp` as the Streamable HTTP endpoint. Supported clients can add it as a custom connector and sign in to Dreamwork, or send a bearer API key in the request headers. No local package installation is needed for the hosted connection.

Related MCP servers

Add a badge to your READMEShow it’s listed — live SVG, Markdown or HTML.

AllMCPs Directory Badge

Full Badge Customizer

Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.

Badge Style:
Live Dynamic SVG PreviewDreamwork AllMCPs Directory Badge
Markdown (GitHub README)
[![AllMCPs](https://allmcps.com/api/badge/dreamwork-2?style=directory)](https://allmcps.com/mcp/dreamwork-2)
HTML Embed
<a href="https://allmcps.com/mcp/dreamwork-2"><img src="https://allmcps.com/api/badge/dreamwork-2?style=directory" alt="Dreamwork on AllMCPs" /></a>