litmus
Official hosted Model Context Protocol server for the Litmus hiring platform. Connects Claude Desktop, Claude Code, or Cursor (via Clerk OAuth) and headless/automation clients (via a `litmus_sk_...` API key). All MCP tool calls are audited in the dashboard. Preserve the trailing slash on the server URL to avoid Authorization-header drops (401) during redirects.
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.
Endpoint
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, …):
For stdio-only clients (older Claude Desktop, etc.), bridge with mcp-remote:
If the server requires authentication, add the provider's token/header (e.g. an X-API-Key) per its docs. A quick reachability check:
Tools
list_submissions— Paginated list of submissions in your org, ordered by submitted-at descending.get_submission— Complete details for one submission including candidate, assessment, role, report summary, and artifact URLs (zipUrl, videoUrl, videoTranscript, optional report).get_pipeline_status— Disjoint stage counts for one role (invited, in_progress, pending_review, advanced, rejected, expired).list_candidates— Paginated list of candidates in your org, including those without submissions.get_candidate_status— Full status detail for one candidate with lifecycle timestamps, source, ATS provider, assessment, and role.upload_assessment— Create a new assessment from caller-supplied files; available immediately as a draft.get_assessment_files— Retrieve current assessment files and version information.update_assessment_files— Replace the file set for an existing assessment, with optional version-based concurrency control.
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.
Work with this as data
Every MCP server here is available over the APIs.io API and to AI agents over MCP.