get_document_by_title
ChatGPTUse this to read a compliance policy or procedure in the connected workspace when its title is known. Returns the full content of matching documents. Not for general framework explanations or unrelated writing. Do not retrieve patient records, payment card data, government identifiers or access credentials.
screenata_assess
ChatGPTUse this when the user asks how their cloud and code infrastructure scores on automated checks, or which provider to connect or scan next. Returns the pass rate over automatable checks, verdict, per-provider counts, top gaps, the repository section, plus progress (each provider: not_connected | connected | scanning | scanned | token_expired | skipped, and next in the order to offer), history snapshots and previous for the delta. Not a readiness score: use screenata_status for that.
screenata_assess_state
ChatGPTRecord the user's choice to skip (or reconsider) a provider in the assessment loop. Only after the user said so; it is remembered on the workspace so a resumed session does not ask again.
screenata_assign_task
ChatGPTAssign a test to a team member by email. Supports dry_run for preview.
screenata_audit_check
ChatGPTUse this when the user asks what blocks their audit or whether they are ready for the auditor. Runs a pre-flight check on one audit cycle (the active one by default) and returns blockers, warnings, and a readiness summary with pass/fail per category. Not for the overall readiness score (screenata_status) or failing checks (screenata_tests).
screenata_controls
ChatGPTList a framework's implementing Controls by display code, e.g. GOV-01, with Test and policy counts. Pass cycle to include each Control's current auditor reviewStatus, latest auditorReview (assessment, reviewer, timestamp, stale), and cycle-wide controlReview counts. Missing or stale conclusions are PENDING_REVIEW; catalog Controls outside the selected engagement are OUT_OF_SCOPE. Without cycle, review fields are null. Company approval and historical Test verdicts do not sign off a Control. Not for failing checks (screenata_tests).
screenata_evidence_import_create
ChatGPTCreate a ZIP evidence import. Upload raw bytes to uploadUrl with Authorization: Bearer uploadToken, then start. Hosted MCP cannot open local paths; use screenata evidence import --file=archive.zip when the host cannot upload. Requires workspace ADMIN. Does not approve tests.
screenata_evidence_import_items
ChatGPTRead per-file mappings, confidence, reasons, scope issues and outcomes.
screenata_evidence_import_resolve
ChatGPTResolve reviewed mappings. decision_batch contains planRevision and decisions [{itemId, action: attach|keep_unmatched, testIds, acknowledgeScope}]. Refresh status after each batch.
screenata_evidence_import_start
ChatGPTStart processing a ZIP after its upload receipt is committed.
screenata_evidence_import_status
ChatGPTRead import progress, counts, errors, versions and next action. Completed does not mean tests passed.
screenata_evidence_import_transition
ChatGPTPause, resume, retry or cancel an import using current stateVersion. Cancel stops future writes; existing documents and attachments remain.
screenata_evidence_mapping_status
ChatGPTRead automatic evidence mapping state and matched tests/controls, confidence, reasoning, and attachment results. A completed mapping does not mean the tests passed.
screenata_gaps
ChatGPTUse this when the user asks which tests still need evidence. Lists gaps in an audit cycle: tests not started or with stale evidence, tests no policy claim links to, and policy claims no test verifies. Not for failing automated checks (screenata_tests) or audit blockers (screenata_audit_check).
screenata_next_actions
ChatGPTUse this when the user asks what to work on next. Returns prioritized actions for the audit cycle, each with a title and the reason it comes first. Not for the readiness score (screenata_status) or a full list of blockers (screenata_audit_check).
screenata_policies
ChatGPTList all compliance policies with approval status, version, and staleness (days since last update).
screenata_policy_answer
ChatGPTRecord the user's answer to one policy question as their attestation. Only pass an answer the user actually gave in this conversation — never infer one. Committed immediately so a following screenata_policy_draft reads it.
screenata_policy_detail
ChatGPTGet full policy content including claims and linked test counts. Use the policy slug (e.g., "incident-response"). Set include_content=false to skip the full document.
screenata_policy_draft
ChatGPTEnqueue a deterministic draft of the policy from its recorded answers. Blocked (returns the unanswered questions) until every question is answered, unless force=true carries an explicit "draft with what we have". Blocked with reason replace_required on an approved or imported policy, because the draft replaces its current content, unless replace=true carries the user's explicit agreement. Never approves; the draft is reviewed and approved in the portal.
screenata_policy_questions
ChatGPTList the questions a policy is built from (the control blueprints citing it): each with its options, the recommended option, the framework requirement it serves, the claim it produces, and whether it is already answered. Use FIRST when drafting a policy: ask only the unanswered ones, at most 4 per turn, quoting controlRef as the reason.
screenata_risks
ChatGPTList risk register items. Filter by rating (HIGH, CRITICAL, MEDIUM, LOW) and status (OPEN, CLOSED). total counts all matches; repeat with page=nextPage and the same filters/limit until nextPage is null.
screenata_scan
ChatGPTTrigger a cloud or code scan. Provider must be connected in Settings. Supports dry_run for preview.
screenata_status
ChatGPTUse this when the user asks how their compliance program or a framework is doing overall. Returns the workspace readiness score, control coverage, test and policy approval, evidence and open risks, plus one row per enrolled framework: its open audit cycle with the cycle readinessScore (the score shown on the audit cycles page), tests and controls. Pass cycle to pin the header to one audit cycle. Not for automated infrastructure results (screenata_assess) or audit blockers (screenata_audit_check).
screenata_submit_evidence
ChatGPTSubmit text evidence for a test. Provide the test ID (or task code), a title, and the evidence content. Supports dry_run for preview. Binary files (screenshots, PDFs) are CLI-only.
screenata_test_detail
ChatGPTGet one test with why it fails and how to judge it: terminalPath, applyPath (screenata | agent | manual — who applies the fix, decided from the remediation registry and the integration access level; never offer a Screenata apply otherwise) with applyReason and judgmentKit.manualSteps, lastRun (latest check result, errorMessage, failing resources with remediation, remediationSteps), findings (open RemediationTickets with condition / criteria / closureCriteria) and judgmentKit (instructions, requiredElements, auditorAsk, auditorGuidance). Read this before proposing a fix.
screenata_test_remedy_execute
ChatGPTApply a prepared plan after the user explicitly approved it in this conversation. Pass the plan verbatim and the planHash from prepare; a mismatch is rejected. Records a RemediationExecution with before-snapshot and undo, then re-runs the check as its validation run.
screenata_test_remedy_prepare
ChatGPTPrepare a native remediation plan for a failing check-backed test: steps, current and proposed state, side effects, reversibility and planHash. Show every step to the user; nothing is applied.
screenata_test_remedy_undo
ChatGPTRoll back the most recent applied remediation on a test from its before-snapshot.
screenata_test_run
ChatGPTRe-run the native check bound to a test on the server. The only way a fix becomes a pass: a PASS closes the open finding through post-verification; no status is written directly. Set wait=true to block until the run finishes (up to ~60s) and get the result inline.
screenata_test_run_status
ChatGPTGet one run of a test: phase, resultStatus, errorMessage, failing resources and the finding it verified or reopened.
screenata_tests
ChatGPTList tests with their status and terminalPath (which fix shape applies from a terminal). Set fixable=true to keep only tests an agent can act on, ranked rerun → export → record → document → integration_blocked.
screenata_whoami
ChatGPTWho this credential acts as and where: user, workspace (id, slug, title), organization, credential type and scopes. Call it first and name the workspace back to the user before any write.
search_workspace_docs
ChatGPTUse this when answering a question about the connected workspace's compliance policies, procedures or evidence. Search its internal documentation for relevant passages. Not for general framework explanations or unrelated writing. Do not request patient records, payment card data, government identifiers or access credentials.