Connect your AI Agents to Ashby in minutes

What is an Ashby MCP?

It's an MCP server that lets your agents access data and functionality from Ashby via tools. Your agents can invoke these tools to pull candidate profiles, advance applications through pipeline stages, post new job openings, submit interview feedback, and more.

Ashby doesn't offer an official MCP server (they plan to release one soon), but you can also use one from a third-party platform, like Merge Agent Handler.

How can I use the Ashby MCP server?

The use cases naturally depend on the agent you've built, but here are a few common ones:

• Pipeline triage: when a new application lands in Ashby, an agent can score the candidate against the job's requirements and advance, reject, or flag it for a recruiter to review

• Candidate sourcing from another system: an agent can take a list of prospects from your CRM or a sourcing tool and create matching candidate records in Ashby, deduplicating against existing profiles

• Recruiting updates in Slack: a recruiter can ask their AI to summarize where every candidate for a role sits in the pipeline and which interviews are still outstanding, without opening Ashby

• Interview feedback rollups: after a panel finishes, an agent can collect each interviewer's scorecard from Ashby and draft a hiring recommendation for the hiring manager

What are popular tools for Ashby's MCP server?

Here are some of the most commonly used tools:

• list_candidates: returns candidate records filtered by job, stage, or source. Useful for agents that need to survey a pipeline before deciding what to act on

• get_application: retrieves a single application with its current stage, linked candidate, and activity history. Call this when an agent needs full context on one applicant

• advance_application_stage: moves an application to a new stage in the interview plan. Use this when an agent automates pipeline progression based on screening results

• create_candidate: creates a new candidate record from external data. Good for workflows that source prospects in another tool and push them into Ashby

• submit_interview_feedback: attaches a scorecard or note to an application. Helpful when an agent compiles structured feedback after an interview

• list_openings: returns active job openings and their requisition details. Useful for agents that match candidates to roles or report on open headcount

What makes Merge Agent Handler's Ashby MCP server better than alternative Ashby MCP servers?

There are several reasons to use Merge Agent Handler's Ashby MCP server over building or using an alternative:

• Enterprise-grade security and DLP: Merge Agent Handler includes built-in data loss prevention controls that let you block or redact sensitive fields before they reach an agent. For Ashby, this means you can keep candidate PII, compensation, and interview scorecards from being exposed even when the agent has broad read access

• Managed authentication and credentials: Merge stores and refreshes Ashby credentials on your behalf. You never expose raw API keys or OAuth tokens to an agent or manage token rotation manually

• Real-time observability and audit trail: Every tool call made against Ashby is logged with timestamp, tool name, input parameters, and response metadata. You can audit exactly which candidates an agent read or updated without instrumenting anything yourself

• Tool Packs and controlled access: Tool Packs let you bundle specific Ashby tools with tools from other connectors into a single MCP endpoint, scoped to a specific use case. An agent gets exactly the tools it needs, nothing more

How can I start using Merge Agent Handler's Ashby MCP server?

You can take the following steps:

1. Create or log into your Merge Agent Handler account.

2. Install the Merge CLI by running pipx install merge-api, then run merge configure to link the CLI to your Merge account and merge login to authenticate your session.

3. Register the Agent Handler MCP server with Claude Code by running claude mcp add --transport http agent-handler https://ah-api.merge.dev/mcp, then open Claude Code and run /mcp to confirm agent-handler appears with a connected status.

4. Select agent-handler from the MCP list. This opens a browser window where you select which integrations to authenticate. Choose Ashby and complete the auth flow. Merge stores and manages the credentials going forward.

5. Open a Claude Code session and start querying Ashby data directly. The first time you use an Ashby tool, a Magic Link may appear to complete connector authentication.

If you want to connect Merge Agent Handler's Ashby MCP with internal or customer-facing agentic products, you can follow the steps in our docs.

Can employees use Merge Agent Handler to connect their AI tools to Ashby?

Yes, Agent Handler for Employees lets your employees connect Claude, ChatGPT, Microsoft Copilot, Cursor, and other MCP-compatible AI tools to Ashby without bypassing IT governance.

Instead of setting up direct connections with personal credentials that IT can't monitor or revoke, each employee authenticates through Agent Handler and gets individual credentials tied to their identity. A recruiter can ask Claude to check where a candidate sits in the pipeline, log interview feedback, or post a new opening, all within the permissions IT has defined.

IT also provisions access by role or group via SCIM. A recruiter, for example, gets Ashby access to advance candidates and log feedback, Gmail to manage candidate outreach, and Slack to coordinate with the hiring panel; while a hiring manager gets Ashby access to review applications and scorecards, Google Calendar to schedule interviews, and Zoom to run them.

Every tool call an employee's AI makes to Ashby is also inspected against your DLP rules and logged to a searchable audit trail, giving security teams full visibility into what data was accessed and by whom.