{"report":{"v":1,"package":"@atlasent/mcp-server","version":"2.21.0","ranAt":"2026-11-16T11:50:45.245Z","install":{"ok":true,"bin":"mcp-server","integrity":"sha512-cnBcgiAdEv+LUuqHU6bnzmtjJR7YNzvGgbMmEdQIxplAMaCLk2j833f859ikkefFYAbxXKU/2e0UgSFJg2jAnw==","deps":95,"scripts":[],"bins":["mcp-server","atlasent-mcp","atlasent-openshell","atlasent-exposure-scan","atlasent-change-sample"],"license":"Apache-2.0","engines":"node >=18","repository":"git+https://github.com/AtlaSent/atlasent-mcp-server.git"},"start":{"ok":true,"ms":175,"serverName":"@atlasent/mcp-server","serverVersion":"2.21.0","protocol":"2025-06-18","stderr":"[atlasent-mcp-server] WARNING: running in LOCAL mode. Local-mode permits are unsigned and forgeable (Date.now() + UUID, no HMAC), and the local engine's default is allow. Local mode is Experimental: use it for development, demos and CI only. To get real, signed permits from your organization's policy, create a free AtlaSent account (https://console.atlasent.io/auth/sign-up?utm_source=mcp&utm_medium=cli), choose \"Connect an AI agent\", and add the ATLASENT_API_KEY it gives you to this MCP server's config; that key alone switches the server to remote mode. See SECURITY.md § 'Maturity classification' for details. Set ATLASENT_SUPPRESS_LOCAL_MODE_WARNING=true to silence this warning in dev/CI scripts.\n{\"ts\":\"2026-11-16T11:50:53.917Z\",\"event\":\"server.gateway_tools_hidden\",\"mode\":\"local\",\"hidden_tools\":{\"_kind\":\"array\",\"count\":26},\"enable_with\":\"h:c97ba6a8:len=33\"}\n{\"ts\":\"2026-11-16T11:50:53.924Z\",\"event\":\"server_started\",\"transport\":\"stdio\"}\n"},"tools":[{"name":"evaluate","description":"Call this BEFORE performing any sensitive action. Returns a Decision: `allow` (verify the returned permit_token at the execution boundary before proceeding), `deny` (you MUST NOT proceed), or `hold` (do not proceed; route for review).","params":["action_type","actor_id","environment","approvals","change_window","target_id","change_plan","target_system"]},{"name":"verify_permit","description":"Call this AFTER `evaluate` returns allow and BEFORE the protected native side effect. It verifies the permit for the presented execution context. Proceed only when `valid` is true; expired, invalid, replayed, mismatched, or error outcomes must block the action.","params":["permit_token","action_type","actor_id","environment","approvals","change_window","target_id","payload_hash"]},{"name":"deploy_service","description":"Example protected tool. Every call is authorized AND its Permit is verified by AtlaSent before the deploy runs. Denied, held, expired, replayed, mismatched, or unverifiable calls are blocked and never touch the target system.","params":["service_name","environment","actor_id","approvals","change_window","change_plan","target_system"]},{"name":"atlasent_evaluate","description":"Evaluate an action against your published AtlaSent policies. Returns allow/deny/hold/escalate with a permitToken on allow. Use this when ATLASENT_MODE=remote and you need to gate an action against your hosted policy engine. For agent.* actions the result may carry bound_payload_hash and bound_actor_id: pass them to verify_permit as payload_hash and actor_id, since the permit is bound to them.","params":["actor_id","action_type","context","explain","execution_payload_hash","target_id","change_plan","target_system"]},{"name":"atlasent_list_policies","description":"List all constraint bundles / policies for this organization.","params":["org_id","status"]},{"name":"atlasent_list_audit_events","description":"Retrieve recent evaluation events from the audit log.","params":["org_id","evaluation_id","from","to","limit"]},{"name":"atlasent_explain_authority","description":"Explain why a principal currently has (or lacks) authority for a scope. Answers 'why may principal P exercise scope/action A in organization O right now?' — strictly read-only, does not change /v1-evaluate, /v1-verify-permit, or any deny/hold/allow semantics; it explains the same facts those paths already read. Every matched authority mechanism (direct_grant, delegation, role_capability) is reported as its own path entry; every excluded or ambiguous relationship is reported as its own unresolved finding.","params":["principal_id","requested_scope","resource_id"]},{"name":"atlasent_integrity_audit","description":"Audit the organization's authority graph for internal inconsistency and return the report verbatim. Strictly read-only; changes no policy, permit, or decision. THIS IS NOT A PASS/FAIL HEALTH CHECK and the tool synthesizes no verdict of its own. Each finding carries a three-way `classification`: `defect` is a genuine inconsistency; `non_exercisable` is frequently the CORRECT, healthy state (e.g. an expired grant that is supposed to be expired) and must not be read as a failure; `unresolved` means the proposition COULD NOT BE VERIFIED and must never be treated as clean. Read `summary.audited_scope` before drawing any conclusion from an empty findings list — a short decision window is not an absence of findings. If the audit cannot complete, the server refuses rather than returning a partial report, and this tool surfaces that as an error — never an empty report.","params":["decision_window_days"]},{"name":"atlasent_list_permits","description":"List issued permit tokens for audit and monitoring.","params":["org_id","limit","status","actor_id","action_type","from","to","cursor"]},{"name":"atlasent_await_approval","description":"Wait for a person to approve or reject a held action in the AtlaSent console. Use the approval_request_id from a 'hold' result. This tool cannot approve anything; it only waits. If approved, it returns a permit_token that you MUST verify with verify_permit before running the action. Any other outcome (rejected, expired, timed out) means the action must not run.","params":["approval_request_id","max_wait_seconds","change_plan","on_plan_mismatch"]},{"name":"atlasent_lookup_action","description":"Look up canonical action specifications from the Authorization Intelligence Library. Returns the permanent canon_id, gate flags (requires_human_approval, requires_mfa, requires_verified_actor, requires_state_snapshot), authorization pattern, risk posture, AI risk classification, regulatory mappings, evidence requirements, and the action's knowledge-graph relationships (what it requires and produces, and which frameworks / control objectives it satisfies) for every governed action type in the Canon. Use `slug` for an exact match (e.g. 'production.deploy') or `query` to describe what you want to do in plain language (e.g. 'deploy the api service to prod', 'grant admin access', 'close the books'). `query` is ranked offline against the vendored Canon and returns a `retrieval` block with `confidence` = confident | ambiguous | none — act only on `confident`; the tool never invents an action type, and a `none` result means the Canon has no such action (see the hint). Omit both to list the full Canon.","params":["slug","query"]},{"name":"atlasent_atlas_lookup","description":"Look up a canonical AtlaSent concept from the Knowledge Atlas — the compiled graph of the system's own vocabulary (Caller, Authority, Policy, Decision, Permit, Verification, Evidence, Audit Chain, Gate, Trust Root, ...). Returns the concept's canonical definition (its source-of-truth doc), its relationships (what it depends on and what depends on it), the surfaces that realize it, and its ADR / API / SDK / implementation anchors — so every AI host reasons from the same canonical knowledge instead of guessing. Use `id` for an exact concept id (e.g. 'permit', 'audit-chain', 'gate') or `query` for a case-insensitive substring search across id, term, and definition. Omit both to list every concept.","params":["id","query"]},{"name":"atlasent_evaluate_many","description":"Evaluate up to 100 actions in a single request against your published AtlaSent policies. Returns decisions in input order. Optional batch_id (UUID) provides idempotency. Closed-by-default: 404 surfaces as a `feature_not_enabled` error tagged with the `v2_batch` tenant flag.","params":["items","batch_id"]},{"name":"atlasent_evaluate_stream","description":"Evaluate up to 100 actions via the streaming endpoint. The tool buffers the SSE stream and returns the complete result set (same shape as atlasent_evaluate_many). Per-item RPC failures surface in the items array with `{ error }`; the stream continues. Closed-by-default: 404 surfaces as a `feature_not_enabled` error tagged with the `v2_streaming` tenant flag.","params":["items","batch_id"]},{"name":"atlasent_query","description":"Run a read-only GraphQL query against the AtlaSent V2 GraphQL endpoint. Wave A schema: `recentEvaluations(limit)`, `activeBundle`. Body limit 1MB, depth limit 8, one operation per request (enforced server-side). Closed-by-default: 404 surfaces as a `feature_not_enabled` error tagged with the `v2_graphql` tenant flag.","params":["query","variables"]},{"name":"atlasent_get_evidence_export","description":"Retrieve a specific compliance evidence bundle by ID. Includes status, SHA-256 hash for tamper verification, and download URL when complete.","params":["org_id","export_id"]},{"name":"atlasent_vqp_generate","description":"Score a constraint bundle against the 6 VQP criteria (access_control CC6.1, audit_coverage CC7.2, escalation_paths CC7.4, deny_specificity CC8.1, hold_conditions CC6.3, override_governance CC5.2). Stores a tamper-evident snapshot with a SHA-256 prompt_hash in vqp_snapshots. Verdicts: qualified (≥85, no fails), conditionally_qualified (≥60), not_qualified. Requires ATLASENT_SUPABASE_URL and ATLASENT_SUPABASE_SERVICE_ROLE_KEY.","params":["bundle_id","org_id","vqp_context"]},{"name":"atlasent_vqp_verify","description":"Re-derive the VQP prompt from current bundle data and verify it matches the stored SHA-256 prompt_hash. Detects tampering (hash_match: false) and optionally re-runs the AI model to detect score drift (score_delta, verdict_changed). Writes a vqp_audit_log row for SOC 2 CC7.2 / 21 CFR Part 11 evidence. Requires ATLASENT_SUPABASE_URL and ATLASENT_SUPABASE_SERVICE_ROLE_KEY.","params":["snapshot_id","rerun"]},{"name":"atlasent_evidence_gap_report","description":"Scan CI workflow files for steps that change real systems (deploys, package and image publishes, database migrations, terraform/pulumi applies) and report, per step, whether an AtlaSent gate stands in front of it: bound, gated, gated_upstream, weak, or ungoverned. Read the repository's .github/workflows/*.yml files and pass each one's path and full text as `workflows`. Offline and read-only: no network call, no API key, nothing is executed. The report lists what it cannot see (repository settings, deploys outside CI, the inside of deploy scripts) so a clean result is never read as proof.","params":["workflows","gate_actions"]},{"name":"atlasent_exposure_review","description":"The free Authorization Exposure Review: a readable Markdown review of which CI steps can change real systems (deploys, publishes, migrations, infrastructure applies) without an approval gate that can stop them, with the exact fix for each and what the review cannot see. Same analysis as atlasent_evidence_gap_report, written for a person. Read the repository's .github/workflows/*.yml files and pass each one's path and full text as `workflows`. Offline and read-only: no network call, no API key. Show the returned `markdown` to the user as is.","params":["workflows","gate_actions"]}],"toolsHash":"7bc416e13db4e0454e3bba5ec3836a67abac8dda1915336d65a0af92a76152f6","wrote":[],"host":{"commit":"eaaffffaf52255d1b77dc4aacffdfaf353f0c12c","run":"https://github.com/itsHaddad/bragproof/actions/runs/43857070216"},"network":{"names":["registry.npmjs.org"],"conns":[]}},"summary":{"outcome":"started","needs":[],"contacts":[],"flags":[{"kind":"orders","tool":"evaluate","quote":"n at the execution boundary before proceeding), `deny` (you MUST NOT proceed), or `hold` (do not proceed; route for review)."},{"kind":"orders","tool":"atlasent_await_approval","quote":"only waits. If approved, it returns a permit_token that you MUST verify with verify_permit before running the action. Any other outcome (rejected, expired, timed ou"}],"tools":20,"wrote":0,"callsTried":0,"callsAnswered":0,"callContacts":[]},"history":[{"package":"@atlasent/mcp-server","version":"2.21.0","ranAt":"2026-11-16T11:50:45.245Z","outcome":"started","tools":20,"contacts":0,"flags":2,"serious":0,"toolsHash":"7bc416e13db4e0454e3bba5ec3836a67abac8dda1915336d65a0af92a76152f6"}],"page":"https://bragproof.smaverk.com/r/%40atlasent/mcp-server"}