IBON

Showing 25 of 48 from the live probe.

• Get Workflow Guidance

  Return the IBON Runtime Workflow Contract, recommended MCP tool sequences, evidence-first rules, attachment workflow, and human approval gates. Use this as the first MCP call when an agent needs IBON workflow routing, evidence rules, attachment sequence, or human approval gates. The returned workflow_guidance is the same runtime source used to construct MCP tool descriptions and agent-facing markdown.

• Submit Surveillance Job

  Submit a structured trade-surveillance batch to IBON and receive a queued job id.

• Get Surveillance Job

  Fetch an IBON surveillance job, including persisted flagged cases when complete.

• Scrutinize Case

  Fetch an evidence-backed scrutiny packet for a stored IBON case without changing final status.

• List Evidence

  List the evidence registry for a stored case. Use this before making any compliance/regulatory recommendation.

• Generate Investigation Packet

  Generate the proactive IBON investigation packet: why the item exists, source fields, evidence, missing information, next actions, reliability limits, and approval gates.

• List Investigation Tools

  List the governed analyst-work tools IBON can run after human approval. These tools gather and reconcile evidence; they do not close, escalate, or send messages by themselves.

• Plan Investigation

  Create or fetch the read-only IBON investigation plan for a case. This selects governed analyst tools and prepares tasks, but does not close, escalate, or send anything.

• Get Investigation

  Fetch the current investigation state, task results, and report artifacts for a case.

• Run Investigation

  Execute a human-approved investigation-plan proposal. Execute only after a human approved the exact run_investigation_plan proposal_id and that approval is recorded. Do not invent proposal_id, actor_id, rationale, formats, metadata, evidence, or source rows. This may generate investigation artifacts, but it must not close, escalate, or send outbound messages by itself.

• Generate Findings Report

  Regenerate findings report artifacts for a case whose investigation is complete.

• Export Findings Report

  Fetch a generated findings report artifact, including Markdown text or base64 Office-file bytes.

• Plan Next Actions

  Ask IBON to evaluate the audit-ready investigation packet and create or reuse pending action proposals. This may add pending proposals, but it never records a final decision, sends outreach, closes a case, or escalates externally.

• List Action Proposals

  List pending and decided IBON action proposals for a case. Use this before asking a human to approve, deny, edit, or escalate.

• Record Action Decision

  Record a human decision for a specific IBON action proposal. IBON proposes actions; humans decide actions. Do not call this tool unless a human explicitly approved, denied, edited, or escalated the exact proposal_id. Agents must not invent proposal_id, actor_id, rationale, evidence, source rows, policy references, or approval.

• Record Human Decision

  Legacy direct decision recorder. For AI-guided next actions, prefer ibon_plan_next_actions, ibon_list_action_proposals, then ibon_record_action_decision. Legacy direct decision recorder. IBON proposes actions; humans decide actions. Do not call this tool unless a human explicitly approved, denied, edited, or escalated the exact proposal_id. Agents must not invent proposal_id, actor_id, rationale, evidence, source rows, policy references, or approval.

• Export Audit Packet

  Export the audit-ready packet for a stored case as structured JSON or markdown for supervisors, audit, or demo narration.

• Build Case Intelligence Snapshot

  Build or replay the source-backed IBON investigation intelligence snapshot for a stored case. This is read-only intelligence work: it may persist the replayable snapshot, but it never approves, closes, escalates, sends outreach, or changes source data.

• Discover Case Space

  Run bounded same-customer case-space discovery over stored IBON cases. This finds recurring or rare patterns without crossing customer boundaries or taking final action.

• Upload Attachment

  Store and extract a user-provided file or text attachment before asking IBON to reason about it. Use this before reasoning about a user-provided file. After upload, the primary follow-up is ibon_respond_to_conversation with attachment_record_ids. Org-wide promotion is optional and only for policy, WSP, reference, or reusable organization documents.

• Get Attachment

  Fetch a stored attachment record, including extracted text, by attachment_record_id.

• Respond To Conversation

  Ask IBON a natural-language question grounded to stored cases, uploaded attachments, rules, and evidence. Primary natural-language entry point after attachments are uploaded. Use attachment_record_ids returned by ibon_upload_attachment instead of asking the user to paste file contents. IBON grounds the reply to stored cases, uploaded attachments, rules, evidence, and memory that does not override evidence.

• Look Up Compliance Rule

  Look up a specific FINRA or SEC compliance rule by its rule ID from the built-in rule registry. Returns the full rule record including key obligations, common violations, and the canonical rule URL.

• Search Compliance Rules

  Search the IBON built-in FINRA and SEC rule registry by jurisdiction, tag, or keyword query. Returns all matching rules with their obligations, violation patterns, and canonical URLs.

• Check Compliance

  Run a deterministic FINRA/SEC compliance check against structured data and receive a full report with findings, severity ratings, citations, and recommended actions. This tool flags everything suspicious and defaults to checking all 10 registered rules. Pass include_markdown: true (the default) to receive a formatted markdown report alongside the JSON. Read-only compliance check. When customer_id is provided, IBON resolves org-scoped documents promoted through ibon_promote_to_org_scope and can p