MCP server · Ashby

ashby

Ashby's official hosted/remote MCP server connects MCP-compatible AI clients directly to live recruiting data. Tool list below is transcribed from Ashby's MCP docs (Open Beta), grouped by capability area. Names are descriptive of the documented capability rather than exact registered tool identifiers.

Open endpoint → Ashby provider profile

One-click install for Cursor, VS Code, Claude, and 20+ other MCP clients, powered by API Commons MCP Install — visit install.apicommons.org for more information.

Provider: Ashby Type: Hosted endpoint Transport: http Host: mcp.ashbyhq.com

Endpoint

https://mcp.ashbyhq.com/mcp/v1

Hosted endpoint · transport http

Connect

This is a remote MCP server — point an MCP client at the endpoint URL. Clients with native remote support (Claude, Cursor, VS Code, …):

# mcp client config (e.g. .mcp.json / mcp settings) { "mcpServers": { "ashby-hq": { "url": "https://mcp.ashbyhq.com/mcp/v1" } } }

For stdio-only clients (older Claude Desktop, etc.), bridge with mcp-remote:

# Add to claude_desktop_config.json { "mcpServers": { "ashby-hq": { "command": "npx", "args": ["-y", "mcp-remote", "https://mcp.ashbyhq.com/mcp/v1"] } } }

If the server requires authentication, add the provider's token/header (e.g. an X-API-Key) per its docs. A quick reachability check:

curl -i -X POST https://mcp.ashbyhq.com/mcp/v1 \ -H "Content-Type: application/json" -H "Accept: application/json, text/event-stream" \ -d '{"jsonrpc":"2.0","id":1,"method":"tools/list"}'

Tools

search_records — Search records by name across candidates, jobs, applications, and email templates.
filter_records — Filter records with criteria across candidates, applications, jobs, postings, openings, interviews, and offers.
get_record_details — Retrieve the full details of a specific record.
get_candidate_profile — Get candidate profile information.
get_upcoming_interviews — List a user's upcoming interviews.
get_interview_details — Get interview details, including the prep briefing.
get_interview_plan — Get the interview plan and its stages.
get_submitted_feedback — Retrieve submitted interview feedback.
get_job_pipeline — Get the pipeline status for a job.
get_pending_tasks — Get pending tasks (scorecards, approvals, follow-ups).
create_candidate — Create a new candidate record.
add_candidate_note — Add a note to a candidate.
change_application_stage — Move an application to a different interview stage.
consider_candidate_for_job — Consider an existing candidate for an open job.
search_documentation — Search Ashby product documentation.
submit_mcp_feedback — Submit feedback about the MCP server.

About MCP

The Model Context Protocol (MCP) is an open protocol Anthropic introduced for connecting LLM-based agents to external tools and data sources. Providers publish MCP servers that expose their API surface as structured, discoverable tools — an MCP-compatible client (Claude Desktop, Cursor, Cline, Continue, etc.) can connect to the server and call its tools without any per-provider integration code.

Browse every MCP server on the APIs.io network or compare with the broader Agent Skill surfaces of the same providers.