HeyRole

Search remote jobs, read full postings and get application links. Free remote MCP with no account or API key required.

Hosted MCP Server

npx add-mcp 'https://heyrole.ai/mcp'

Installs into Claude Code, Codex, Cursor and more

Documentation

Remote jobs for your app.And your AI assistant.

Search remote roles, read the details and get application links from the HeyRole catalog. One read-only source, two ways to connect.

No account. No API key. No OAuth setup.

Bring jobs into the conversation.

Add HeyRole as a remote MCP server in a compatible client. Your assistant can search the catalog and read postings before helping you decide what to explore.

Let your AI assistant help you connect

For Claude, Codex, Cursor, VS Code and other remote MCP clients. Paste the prompt into your assistant: it can configure the connection when permitted, or guide you through the manual steps.

Read the prompt

Help me connect HeyRole's public remote-job MCP server to the AI client I am using (Claude, Codex, Cursor, VS Code or another compatible client).

Server name: heyrole
URL: https://heyrole.ai/mcp
Transport: Streamable HTTP
Authentication: none. No HeyRole account, API key or OAuth is needed.
Reference: https://heyrole.ai/developers.md
Tools: search_jobs, get_job, get_filters (read-only).

Identify the current client first; ask me if unclear. Configure only that client. Inspect its existing configuration and preserve other servers. Reuse an identical heyrole entry; ask before replacing a conflicting entry. Respect client approval and workspace-trust requirements.

Use the appropriate setup method when you have permission:
- Claude Code: run claude mcp add --transport http --scope local heyrole https://heyrole.ai/mcp for the current project; inspect with claude mcp get heyrole.
- Codex: run codex mcp add heyrole --url https://heyrole.ai/mcp and inspect with codex mcp get heyrole. This uses the shared user configuration. If I want project-only setup, merge [mcp_servers.heyrole] with url = "https://heyrole.ai/mcp" into .codex/config.toml in a trusted project instead.
- Cursor: merge {"mcpServers":{"heyrole":{"url":"https://heyrole.ai/mcp"}}} into the project's .cursor/mcp.json, preserving existing entries.
- VS Code with GitHub Copilot: guide me through MCP Servers > Add Server in the active agent's customization settings, using this HTTP URL and the appropriate configuration destination for my installed version.
- Claude web/desktop chat: guide me through adding a custom remote connector named HeyRole with this URL and no authentication.
- Other clients: use their documented remote Streamable HTTP setup. Do not guess configuration keys.

If you cannot configure this client, give me the exact manual steps. Do not claim to have changed settings you cannot access.

Once the tools are available, call get_filters to verify the connection. If a reconnect or new session is needed, give me the next step. If the endpoint is unavailable, report the error without claiming success. Then ask which roles and locations I want to search. Missing location or salary data stays unknown; remote does not imply worldwide eligibility.
https://heyrole.ai/mcp

Transport

Streamable HTTP

Authentication

None

In your client’s MCP settings, add a remote server, paste this URL and select no authentication if asked. Setup varies by client; it must support remote Streamable HTTP.

“Find remote backend jobs that explicitly list the US or worldwide. Show me the location requirements and application links.”

Start with one request.

Use a simple GET request to fetch JSON. No credentials or cookies are needed. This example returns up to 10 active jobs explicitly listing the US or worldwide.

curl 'https://heyrole.ai/api/v1/jobs?locations=us,worldwide&limit=10'

Read the jobs array, then pass next_cursor as cursor with the same filters for the next page. Use an ID from the results to fetch a full posting.

The same catalog. Three capabilities.

Full reference

Search jobs

Find active remote roles by location, category, skills and seniority. Filter for listings with pay information.

MCP search_jobs

GET /api/v1/jobs

Read a posting

Get the description, catalog status, source and direct application link for a job.

MCP get_job

GET /api/v1/jobs/{id}

Explore filters

Discover supported filter keys and skills observed in the catalog.

MCP get_filters

GET /api/v1/filters

A few things to know.

What does “remote” mean here?

Remote does not always mean worldwide. Location and pay come from the posting’s own fields; missing information stays unknown. Check each posting’s requirements before presenting it as a suitable role.

Are there usage limits?

Yes. The initial limit is approximately 60 requests per minute per connecting IP, shared across REST and MCP. Hosted assistants may share an IP. A separate limit protects uncached reads. Back off on rate-limit errors and follow the retry guidance in the reference.

Search, job details, and filters are cached for five minutes. Requests return up to 50 jobs per page, with cursor pagination.

Can it apply to jobs or access my account?

No. These interfaces only read the public job catalog. They do not access resumes, saved jobs or application history, and cannot submit applications. Application links lead to the original hiring site.

Will I need to log in later?

The public catalog tools are designed to stay anonymous. If account features are added later, they will require separate authorization. Existing public searches will not require migrating to OAuth.