Aptora MCP server
MCP server for the Aptora API: create assessments, invite candidates, pull grading results
Little public usage data yet
Reviews
Write oneNobody has reviewed Aptora yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
Aptora tools (12, 5 write)
write = sends, deletes, buys or postsRead from the package source without running it. The installed server may list more.
create_assessmentwrite actionCreate a new assessment. Call get_authoring_guide first. Pass workspace_directory to give candidates starter files. Dry-run it (get_dry_run_guide) before inviting anyone.
create_interviewwrite actionCreate an interview for a candidate WITHOUT emailing them. Returns the interview including its link, which you can share yourself. Also used for dry runs. Use invite_candidate to have Aptora send the invitation email.
get_assessmentFetch one assessment by id, including its full configuration.
get_authoring_guideHow to write an Aptora assessment: field meanings, the required ProseMirror problem format, environment constraints, setup hooks and black-box services, personas, and grading categories. Call before creating or editing an assessment.
get_dry_run_guidewrite actionStep-by-step QA of an assessment by taking it as a test candidate in a browser: files, setup hook, black-box services, personas, browser preview. Call before dry-running an assessment.
get_grading_resultsFetch the full AI grading report for a completed interview: scorecard, timeline, metrics. Grading runs asynchronously after completion \u2014 the response reports in-progress status when not done yet.
get_workspace_snapshotFetch the candidate's final workspace (file tree with contents) captured when the interview ended. Can be large.
invite_candidatewrite actionCreate an interview AND send the candidate a real invitation email immediately. Only use when the user explicitly wants the invitation sent.
list_assessmentsList all assessments in the user's organization.
list_interviewsList all interviews in the user's organization with status and grading summary (overall score, reviewed flag).
update_assessmentwrite actionUpdate an existing assessment. Only the fields you pass change; everything else is preserved. Pass workspace_directory to replace the starter workspace.
whoamiReturn the Aptora user the configured API key belongs to. Use to verify the connection.
Public scan report
scanner v0.1.9 · 2026-09-27 · same rubric, same numbers if you re-run it
- Code scan2 source files scanned25/25
- –Live reliabilityno gateway calls yet and no remote to proben/a
- –Tool poisoningtools not inspected (local package is not executed); not countedn/a
- Auth qualitystatic API keys via environment variables6/15
- Maintenanceno repository listed3/15
- Maintainer identityverified namespace with website, no repo4/10
Findings (1)
- lowNo source repository listed
maint.no-repo
Install Aptora in Claude Code, Cursor or VS Code
Runs npx -y @aptora/mcp on your machine. Read the scan report first; the gateway never runs local packages.
claude mcp add mcp -- npx -y @aptora/mcp
Aptora: common questions
- Is Aptora MCP server safe?
- With care: it is graded C, so read the findings first (58/100). Read the Aptora safety report
- How do I install Aptora?
- It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
- Does Aptora need an API key?
- Yes. The registry entry asks for
APTORA_API_KEY. - Is Aptora maintained?
- The latest release is v1.0.0.