Prelim
chat.prelim/prelim
6 toolsHTTPregistry active
Summary
This connects Claude to Prelim's AI screening interview platform, letting you pull candidate data, interview transcripts, and scoring analytics directly into your workflow. You can query roles you're hiring for, review completed screens with per-question breakdowns and overall scores, and pull structured interview data without opening the web app. Useful if you're building recruitment automation, need to surface candidate insights in Slack or internal tools, or want to programmatically filter high-scoring applicants for immediate follow-up. The API surfaces the same scored shortlists and transcripts you'd see in their dashboard, so you can route top candidates to your ATS or notification system as soon as they finish screening.
Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →
Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →Tools
Public tool metadata for what this MCP can expose to an agent.
6 tools
list_jobsList the open hiring roles (jobs) in your Prelim organization. Each job is a role being screened for. Returns lightweight summaries with interview counts; use get_job for full details including screening questions.3 params
List the open hiring roles (jobs) in your Prelim organization. Each job is a role being screened for. Returns lightweight summaries with interview counts; use get_job for full details including screening questions.
Parameters* required
limitintegerMax number of jobs to return. Defaults to 20, max 50.
searchstringCase-insensitive substring match against job title.
statusstringFilter jobs by status. Omit to return all statuses.one of
active · paused · archivedget_jobGet full details of one hiring role: title, description, status, branding, and the list of screening questions the AI will ask candidates.1 params
Get full details of one hiring role: title, description, status, branding, and the list of screening questions the AI will ask candidates.
Parameters* required
jobIdstringUUID of the job. Get this from list_jobs.
list_screensList preliminary phone screens (interviews) for a job. Returns candidate summaries with score and recommendation; use get_screen for per-question scores and get_transcript for the full conversation.4 params
List preliminary phone screens (interviews) for a job. Returns candidate summaries with score and recommendation; use get_screen for per-question scores and get_transcript for the full conversation.
Parameters* required
jobIdstringUUID of the job. Get this from list_jobs.
limitintegerMax number of screens to return. Defaults to 20, max 50.
minScorenumberOnly return screens with overall_score >= minScore (0-100).
statusstringFilter screens by status. Omit to return all.one of
in_progress · completed · expiredget_screenGet one preliminary screen with overall score, recommendation, summary, and per-question scores. Excludes the full transcript to keep responses small; use get_transcript for the conversation messages.2 params
Get one preliminary screen with overall score, recommendation, summary, and per-question scores. Excludes the full transcript to keep responses small; use get_transcript for the conversation messages.
Parameters* required
jobIdstringUUID of the job.
screenIdstringUUID of the preliminary screen. Get this from list_screens.
get_transcriptGet the full back-and-forth between the AI screener and the candidate for one preliminary screen. Returns the ordered list of messages. Use this when the user wants to read what was said; use get_screen for just the score and summary.2 params
Get the full back-and-forth between the AI screener and the candidate for one preliminary screen. Returns the ordered list of messages. Use this when the user wants to read what was said; use get_screen for just the score and summary.
Parameters* required
jobIdstringUUID of the job.
screenIdstringUUID of the preliminary screen. Get this from list_screens.
get_job_analyticsJob-level analytics: completion rate, average score, status breakdown, and weekly trends over the last 30 days. Requires a Pro plan — free-tier users receive an upgrade message.1 params
Job-level analytics: completion rate, average score, status breakdown, and weekly trends over the last 30 days. Requires a Pro plan — free-tier users receive an upgrade message.
Parameters* required
jobIdstringUUID of the job.
Featured
Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →Registryactive
TransportHTTP
UpdatedMay 23, 2026
