Searches and filters live jobs, with support for saved roles, company following, and talent-profile management.
Copy the AI prompt to install this server into Claude Code, Cursor, or another agent — or use 1-click editor setup below.
One-click editor setup isn’t available for this listing yet — we don’t have a confirmed install command, and we’d rather show nothing than point your editor at the wrong package or host. Follow the project’s own setup instructions, linked above.
Inspect callable tools, capabilities, and parameters exposed to AI agents by Workway.
The workway MCP server provides access to WorkWay’s job and company discovery backend. The service is intended to support searching a large live-job dataset, narrowing results with filters, saving interesting roles, following companies, and maintaining a talent profile.
The repository describes an Express-based API rather than a standalone MCP implementation. Its routes are grouped under /api and cover companies, jobs, feeds, filters, scheduled ingestion, and sitemap generation. A paginated job-list endpoint returns job records, metadata, applied filters, and available facets. A separate filters endpoint returns facet counts for building or driving a filtering interface.
The application runs on Node.js with Express 5 and uses PostgreSQL through the pg package. Route handlers call service and data-access layers, where SQL queries and business logic manage jobs and companies. The service also includes parsing and classification helpers for assigning domains, seniority levels, and employment types to ingested jobs.
HTTP cron-style endpoints load company and job data from Greenhouse, Ashby, and YC sources. Retrieved records are classified and upserted into PostgreSQL. The repository includes a seed list of Greenhouse namespaces used during this process.
The API uses /api as its base path. Operational endpoints include /health, which returns uptime and a timestamp, and /, which confirms that the server is running. Sitemap routes are also available for the WorkWay site and its indexed resources.
Install dependencies from the repository with npm install. Create a .env file in the project root and provide the PostgreSQL connection settings, application environment, connection-pool limit, and HTTP port. The documented variables are APP_ENV, POSTGRES_DB_HOST, POSTGRES_DB_PORT, POSTGRES_DB_USER, POSTGRES_DB_PASSWORD, POSTGRES_DB_DATABASE, POSTGRES_DB_MAX_CONNECTIONS, and PORT.
Start development mode with npm run dev, or use npm start for the standard start command. The documented default address is http://localhost:3000. The workway MCP server therefore requires a reachable PostgreSQL instance and a running Node.js application before clients can use the backend.
Supported backend capabilities include:
The repository’s detailed endpoint reference is in docs/DETAILED_DOCS.md. The provided material does not define MCP tool names, schemas, transport configuration, or client-specific setup.
The source describes WorkWay’s backend API and its data-ingestion service, but it does not document an MCP adapter, MCP transport, or explicit client configuration. Treat the workway MCP server listing as an agent-facing description of these capabilities, not as evidence of a particular MCP tool schema.
The README also does not specify authentication, rate limits, deployment instructions, or the exact persistence behavior for saved roles, followed companies, and talent profiles. Those details should be confirmed in the application’s route implementations or detailed endpoint documentation before integration.
Factual signals from GitHub, npm, and our automated checks — not a rating.
No reviews yet — be the first to share how this listing worked for you.
Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.
[](https://allmcps.com/mcp/workway)<a href="https://allmcps.com/mcp/workway"><img src="https://allmcps.com/api/badge/workway?style=directory" alt="Workway on AllMCPs" /></a>