MCP App Store
by KeenEthics

Overview

Social media discovery for legal, claims, and SIU teams. ChatGPT assesses your file and builds the intake; analysts deliver a Deep Report with aliases and hard-to-find accounts across 500+ platforms. SMI Aware delivers defensible social media discovery built for legal scrutiny. Our analysts search 500+ social and online platforms to surface aliases, hard-to-find accounts, and the online activity that changes how a matter is valued. Findings are documented in a court-ready Deep Report, complete with metadata source code to protect the digital chain of custody. Trusted by 47 of the Am Law 100, plus insurance carriers, SIU teams, and government agencies. SOC 2 compliant, ISO 27050 aligned, and built to support FRE 901(b) authentication. This plugin brings that process into ChatGPT. Paste or connect in case notes, a matter summary, or a claim file. ChatGPT runs a gap analysis: scoring the matter against five relevance signals, returning a RECOMMEND / REVIEW / NO ACTION verdict with plain-English reasoning, recommending the right product, and pre-filling the order. From there, place the order conversationally or open a pre-filled portal form. No new portal to learn, no new UI. Paired with our skill files, the result is an AI that behaves like a trained intake specialist. It encodes our intake standards, applies consistent relevance scoring, and respects our guardrails: no legal advice, no case strategy, no pricing speculation. Every order arrives complete, consistent, and ready for our analysts. What you can do: Assess whether a matter warrants social media discovery, with a scored, reasoned recommendation Compare Research Bundle, Deep Report, and Export, and get a fit recommendation for the matter Place an order conversationally, or hand off to a pre-filled order form Receive your report within 2 business days Orders are fulfilled by certified, full-time human analysts, not AI. ChatGPT handles the assessment and the intake. Our team does the discovery and stands behind the report. Questions, or interested in a workflow tailored to your practice? Reach us at support@smiaware.com or 888.299.9921.

Tools

fetch

ChatGPT
Fetches the full SMI record for a typed reference ("<type>:<id>") that search returned. Pass only an id that appeared in a search result; do not construct one. If you already have a plain SMI record id, use smi_get_deep_report or smi_get_export to read it, or smi_check_order_complete for its readiness.

onboarding_next_step

ChatGPT
Pre-connection onboarding helper, callable before any SMI token is set. With no input, returns the fork question "Do you already have an SMI token?" — call again with hasToken: "yes" for connect guidance (then verify_access), or hasToken: "no" for prospect-intake guidance. Runs locally; makes no network calls and never reads or requires credentials.

smi_add_subject_address

ChatGPT
Attaches a postal address to an SMI subject.

smi_add_subject_alias

ChatGPT
Attaches an alias to an SMI subject.

smi_add_subject_education

ChatGPT
Attaches an educational institution to an SMI subject.

smi_add_subject_email

ChatGPT
Attaches an email address to an SMI subject.

smi_add_subject_employee

ChatGPT
Attaches an employee to an SMI subject (for COMPANY-type subjects).

smi_add_subject_employee_url

ChatGPT
Attaches a url to an SMI subject employee, referenced by the subjectEmployeeId returned from smi_add_subject_employee.

smi_add_subject_employer

ChatGPT
Attaches an employer to an SMI subject.

smi_add_subject_phone

ChatGPT
Attaches a phone number to an SMI subject.

smi_add_subject_relationship

ChatGPT
Attaches a relationship to an SMI subject, using a relationshipId from smi_list_relationships.

smi_add_subject_relationship_url

ChatGPT
Attaches a url to an SMI subject relationship, referenced by the subjectRelationshipId returned from smi_add_subject_relationship.

smi_add_subject_surname

ChatGPT
Attaches a surname to an SMI subject.

smi_add_subject_url

ChatGPT
Attaches a url to an SMI subject.

smi_analyze

ChatGPT
Scores free-text case notes against 5 weighted gap-analysis signals (no prior SMI order, high-relevance case type, known online presence, date of loss, social media mentioned) and returns a RECOMMEND/REVIEW/NO ACTION verdict, a confidence rating, which signals were/were not detected, a suggested product, and a best-effort orderData prefill (subject, matter id, case type, date of loss, handles/urls, suggested scope) for smi_create_deep_report. Runs entirely locally; makes no network calls.

smi_check_order_complete

ChatGPT
Checks the status of a deep report or export record (by its record id, e.g. from smi_create_deep_report draftIds). Returns state = ready | in_progress | draft | failed | unknown and a terminal flag. Poll with bounded attempts and backoff while in_progress; stop as soon as terminal is true (ready or failed) — a failed record will never become ready. Also stop when state is draft: the record was never submitted, so it will not progress until smi_submit_deep_reports or smi_submit_exports is called on it.

smi_confirm_upload

ChatGPT
Confirms a file already PUT to a presigned URL returned by smi_request_upload_url and persists the deep report upload record. Requires the version (the x-amz-version-id response header captured during the PUT).

smi_create_deep_report

ChatGPT
Creates one or more SMI deep report drafts from subject orders. Returns the draft ids for review before submission. All orders in one call are filed under a single project; call once per project.

smi_create_export

ChatGPT
Creates one or more SMI export drafts from profile-url orders. Returns the draft ids for review before submission. All orders in one call are filed under a single project; call once per project.

smi_get_cowork_instructions

ChatGPT
Returns a consolidated, copy-paste-ready Markdown system prompt of SMI Aware house rules and a when-to-call-which-tool routing guide, plus exact paste-in locations for Claude Projects/Cowork/Desktop, Cursor, and other clients, so the assistant calls the right smi_* tools automatically. Runs locally; makes no network calls and takes no case data.

smi_get_deep_report

ChatGPT
Fetches a single SMI deep report by id. Research Bundles are deep-report products, so use this tool for a Research Bundle id too rather than constructing a research_bundle: reference for the generic fetch tool. Accepts product-prefixed ids: RB-11751 (Research Bundle) and DR-11751 (Deep Report) both resolve here.

smi_get_deep_report_releases

ChatGPT
Lists releases for a given SMI deep report, with pagination. Each release links its downloadable deliverable files (report PDF, CSV, JSON) and the findings screenshot archive when available — use this tool to fetch the generated report PDF.

smi_get_export

ChatGPT
Fetches a single SMI export by id. Accepts product-prefixed ids: EX-30001 resolves here, while RB and DR ids belong to smi_get_deep_report.

smi_get_export_releases

ChatGPT
Lists releases for a given SMI export, with pagination.

smi_get_report_findings

ChatGPT
Lists SMI release findings with pagination and optional filtering by report, platform, scope, and confirmation status. Report filters accept the displayed identifier (RB-11751, DR-402) or a bare numeric id, and platform filters accept a platform name (Facebook) or its numeric id. Each finding includes its summary, profile URL, and screenshot/evidence links. Findings are grouped by report and ordered by ascending sequence, so sequence 1 is Finding #1 of that report; refer to a finding by that number rather than by its id, which is an internal record key the reader cannot see. The ordering covers the returned page: SMI decides which findings a page carries, so a report with more findings than take may not begin at Finding #1 on page 1.

smi_get_subject

ChatGPT
Reads a subject's full profile out of a deep report (no standalone GET /subjects/{id} exists upstream, so the input is a deepReportId, not a subject id). Returns the subject as structured JSON — any atomic field (e.g. date of birth via subject.birthDate) can be extracted from it directly.

smi_list_deep_reports

ChatGPT
Lists SMI deep reports with pagination and optional filtering.

smi_list_exports

ChatGPT
Lists SMI exports with pagination and optional filtering.

smi_list_platforms

ChatGPT
Lists the SMI reference set of platforms.

smi_list_products

ChatGPT
Lists the SMI reference set of products.

smi_list_projects

ChatGPT
Lists SMI projects with pagination.

smi_list_relationships

ChatGPT
Lists the SMI reference set of relationships.

smi_list_statuses

ChatGPT
Lists the SMI reference set of statuses.

smi_request_upload_url

ChatGPT
Requests a presigned URL for uploading a large deep-report reference file (csv, doc, docx, gif, jpg, jpeg, pdf, png, txt, webp, xls, xlsx) directly to storage. This server never proxies file bytes: the caller must PUT the file to the returned signedUrl, capture the x-amz-version-id response header from that PUT, and then call smi_confirm_upload with that version to persist the upload record.

smi_submit_deep_reports

ChatGPT
Submits previously created SMI deep report drafts (Draft status only) for processing.

smi_submit_exports

ChatGPT
Submits previously created SMI export drafts (Draft status only) for processing.

smi_update_subject

ChatGPT
Partially updates an SMI subject via PATCH /subjects/:id. type (PERSON or COMPANY) is required on every call — the SMI backend requires it as a discriminator on every subject PATCH. Editable fields match the API contract: firstName/lastName (or companyName for a COMPANY), birthYear/birthMonth/birthDay, and gender. At least one editable field must be provided.

submit_contact_request

ChatGPT
Submits a prospect contact request — first name, last name, email, and organization — to SMI so the sales team can follow up. For prospects who do not yet have an SMI Aware token.

verify_access

ChatGPT
Verifies the session Personal Access Token (PAT) against the SMI identity endpoint and returns the resolved account identity.

Capabilities

Writes

Example Prompts

Click any prompt to copy it.

Similar Apps