MCP App Store
by KeenEthics
Didit icon

Didit MCP Server for ChatGPT

By Didit Identity, Inc.

Overview

Manage identity verification and customer onboarding with Didit in ChatGPT. Create hosted verification links, build KYC (know your customer) and KYB (know your business) workflows, and track verification progress in your connected Didit workspace. For compliance, operations and development teams: - Create a verification link to send to a customer. - Find verification sessions and check their status. - Build, inspect and update verification workflows and questionnaires. Configure steps such as document verification, liveness and AML (anti-money laundering) screening. - Summarize verification volumes, completion rates and onboarding drop-off with aggregate analytics. - Review case and report statuses, and manage webhook destinations. Start by asking Didit to create a verification link, show your KYC workflows, or summarize the last 30 days of verifications. Sign in with your Didit account to connect your workspace. New to Didit? Create an account at business.didit.me first. Your existing organization roles and permissions apply. Customers complete identity checks on Didit's hosted verification page. Session and case results in ChatGPT contain operational references, statuses, dates and counts. Detailed identity evidence, images, private notes and report contents stay outside this plugin's responses. The plugin does not offer standalone document or face uploads, government ID number inputs, one-time verification code inputs, raw API keys or payment checkout. Requested workspace information is shared with ChatGPT to answer your request. Only request records you are authorized to access and share. Review proposed changes before approving actions.

How to connect

  1. ChatGPT: Open the Didit listing in the ChatGPT app directory and choose Connect. ChatGPT listing Didit exposes 47 tools here.

Tools

didit_analytics

ChatGPT
Aggregate verification analytics ACROSS ALL your apps and organizations in one call - the efficient way to answer questions like "how many people tried phone verification but dropped off in the last 15 days?". Returns summed status counts (request_breakdown), a feature_funnel (how many sessions REACHED each step: OCR, LIVENESS, FACE_MATCH, AML, POA, PHONE, EMAIL, ...), warning_stats by risk code, the previous period's request_breakdown, per-workflow session totals and a recomputed conversion_rate, for a date window. Omit organization_id/application_id to span everything; pass them to narrow.

didit_branding_get

ChatGPT
Get the current branding customization (logos, colors) applied to your verification UI.

didit_case_get

ChatGPT
Get a case reference and its status. Personal-record results contain only record references, statuses, counts and dates needed to locate and review the requested records. Open the Didit console for detailed identity evidence, images, notes or report contents. Do not supply government identifiers or authentication secrets.

didit_compliance_check_workflow

ChatGPT
Deterministically check which regulations a workflow version satisfies or violates. Returns per-obligation status with citations.

didit_compliance_generate_workflow

ChatGPT
Deterministically generate a multi-country verification workflow graph from the org's stored compliance profile: a common trunk plus per-country branches carrying the checks each country requires. Returns {kb_version, graph, branches_summary:[{countries, extra_features, because}], manual_obligations, kyb_obligations, rationale}. rationale.nodes maps every feature node id of the graph to {feature, because:[{obligation_id, regulation_id, regulation_name, citation, source_url, countries}]} — the obligations that require that node, with the citation and the official source to link. It is the ONLY sanctioned source for explaining WHY a node exists: never state a regulation, article or URL that is not in it. A node may also carry promoted_for_branching:true, meaning it sits in the trunk for a structural reason (the document-country branch cannot be decided before a document scan), not because every country's regulation demands it — say so rather than attributing it to a regulation. The graph is validated against Didit's workflow schema. Read-only preview — does NOT persist; use didit_workflow_create/set_graph or the ui_* editor tools to apply it. Can also take partial interview answers to preview the graph mid-onboarding, before the profile is stored.

didit_compliance_interview_next

ChatGPT
Given the accumulated onboarding answers so far, return the next question of the adaptive compliance interview, or done:true when it is complete. Stateless — pass every answer collected so far on each call, starting with {}.

didit_compliance_profile_get

ChatGPT
Read the organization's stored compliance profile: the raw interview answers ({answers}, keyed by profileAttr — subjectType, userCountries, industries, …) plus the attributes derived from them ({derived}). Returns the no_profile error when the application has never completed the compliance onboarding.

didit_compliance_profile_set

ChatGPT
Store the completed interview answers, replacing any existing compliance profile. Subsequent requirements and workflow checks evaluate against this profile. Before calling, show the selected organization/application and proposed profile and obtain explicit user confirmation of the replacement.

didit_compliance_requirements

ChatGPT
Get the organization's applicable regulatory obligations with citations, derived from its stored compliance profile. Each obligation carries its source URLs and the kb_version it was evaluated against.

didit_console_open

ChatGPT
Open the Didit console in ChatGPT, full screen: the verifications that need a decision (the user approves or declines them there), each session's checks and warnings, workflows, questionnaires, analytics, webhooks and cases of the user's organization. Call it when the user wants to see, browse or manage their Didit dashboard or console. Pass page to open a specific page, with session_id for a session or workflow_id for a workflow. Nothing changes in Didit; the console shows no personal data, documents or images.

didit_context_get

ChatGPT
Return ALL organizations you can access with their applications nested, plus the default org/app when unambiguous — in ONE call (replaces didit_org_list + per-org didit_org_list_applications). Call this first to discover ids.

didit_org_get_application

ChatGPT
Get application details (client_id etc.). The api_key is REDACTED — a masked preview + api_key_set flag are returned, never the raw secret.

didit_org_get_balance

ChatGPT
Get current credit balance and auto-refill settings. A 0.00 balance does NOT by itself block verifications, so never answer a "not enough credits" report with "top up" from this result alone: a workflow whose features are all free-tier (ID verification, passive liveness, face match 1:1, device/IP analysis — 500 free each per month) runs fine on a zero balance. Read the failing workflow with didit_workflow_list first — is_white_label_enabled: true adds $0.20/session AND drops the workflow out of the free tier entirely, which is the single most common cause. This result also carries allow_free_usage (false = the free tier is off for this organization) and usage_summary.white_label_sessions. Only a NEGATIVE balance stops free-tier work; zero does not.

didit_org_list

ChatGPT
List the organizations you belong to (each has an id to pass as organization_id to other tools). In hosted OAuth mode no arguments are needed.

didit_org_list_api_keys

ChatGPT
List API key metadata with raw key values redacted (pass application_id for an app's keys).

didit_org_list_applications

ChatGPT
List the applications in an organization (each has an id to pass as application_id). In hosted OAuth mode pass only organization_id.

didit_questionnaire_create

ChatGPT
Create a custom questionnaire from an ordered list of questions. Send title + form_elements (an array of form-element objects, each with an UPPERCASE element_type) — NOT questions. The MCP assembles them into the questionnaire graph the backend stores (node ids and their ordering are derived here), so send the questions in the order the user should answer them and never build a graph yourself. Pass status:'draft' to keep it unpublished. A choice list longer than ~100 options does NOT fit in one call (the call is emitted token by token and gets cut off mid-JSON): create with status:'draft' carrying only the first ~100 choices, then add the rest with didit_questionnaire_append_choices in batches (its publish flag publishes with the final batch — a published questionnaire cannot be edited further).

didit_questionnaire_get

ChatGPT
Get questionnaire questions and options. Translations are summarized to one locale by default to keep the response consumable; pass include_translations:true for every locale.

didit_questionnaire_list

ChatGPT
List all custom questionnaires for your application.

didit_questionnaire_update

ChatGPT
Overwrite a questionnaire's supplied settings. Sending form_elements REPLACES the entire question list, removing omitted questions; pass every question to keep, in order, with UPPERCASE element_type. Omitted status preserves the current draft/published state; publication changes only when status is explicitly passed. Before calling, show the questionnaire and proposed changes and obtain explicit user confirmation, including the full replacement when form_elements is supplied.

didit_report_list

ChatGPT
List export report references, processing statuses and dates; report contents and download links are not returned. Personal-record results contain only record references, statuses, counts and dates needed to locate and review the requested records. Open the Didit console for detailed identity evidence, images, notes or report contents. Do not supply government identifiers or authentication secrets.

didit_session_create

ChatGPT
Create a hosted verification link. The customer completes identity checks on Didit's hosted page. Returns only the link, session reference and status. Do not supply identity documents, biometric images, government identifiers or authentication secrets.

didit_session_get_decision

ChatGPT
Get a session's verification status, its individual check statuses with their warning codes, its status history and its hosted verification link. Personal-record results contain only record references, statuses, counts and dates needed to locate and review the requested records. Open the Didit console for detailed identity evidence, images, notes or report contents. Do not supply government identifiers or authentication secrets.

didit_session_list

ChatGPT
List verification session references, statuses, workflow names, per-check statuses and warning codes for the selected application. Personal-record results contain only record references, statuses, counts and dates needed to locate and review the requested records. Open the Didit console for detailed identity evidence, images, notes or report contents. Do not supply government identifiers or authentication secrets.

didit_session_list_reviews

ChatGPT
List a session's review status changes and dates; reviewer notes are not returned. Personal-record results contain only record references, statuses, counts and dates needed to locate and review the requested records. Open the Didit console for detailed identity evidence, images, notes or report contents. Do not supply government identifiers or authentication secrets.

didit_session_update_status

ChatGPT
Overwrite a session's decision by approving, declining or requesting resubmission; optionally send a notification email that cannot be recalled. Before calling, obtain explicit user confirmation of the session, new decision and any notification recipient. Returns the updated status. Personal-record results contain only record references, statuses, counts and dates needed to locate and review the requested records. Open the Didit console for detailed identity evidence, images, notes or report contents. Do not supply government identifiers or authentication secrets.

didit_webhook_create

ChatGPT
Create a webhook destination. The signing secret is redacted in the response.

didit_webhook_delete

ChatGPT
Delete a webhook destination so it stops receiving events.

didit_webhook_get

ChatGPT
Get a single webhook destination with redacted signing-secret metadata.

didit_webhook_list

ChatGPT
List configured webhook destinations. Each destination has its own URL, version, enabled flag, subscribed events, and redacted signing-secret metadata.

didit_webhook_update

ChatGPT
Overwrite the supplied settings of an existing webhook destination. Changing its URL redirects future deliveries; disabling it stops deliveries, and subscribed_events replaces its event subscriptions. Before calling, show the destination UUID and each proposed field change and obtain explicit user confirmation.

didit_workflow_create

ChatGPT
Create a SIMPLE (linear) verification workflow from an ordered list of features. Send features in execution order (uppercase values; put dependency features first, e.g. OCR before FACE_MATCH/NFC/DATABASE_VALIDATION). The MCP assembles them into a real workflow graph and publishes it; pass status:'draft' to keep it unpublished. A bad feature order fails validation and leaves a fixable draft. A workflow verifies EITHER a person (KYC) or a business (KYB), never both, and the type follows WHO is verified: KYB workflows use the KYB_* features (company paperwork belongs in KYB_DOCUMENTS or DOCUMENT_AI) and must not mix in person-only features (OCR/LIVENESS/FACE_MATCH/NFC/PROOF_OF_ADDRESS/DATABASE_VALIDATION/AGE_ESTIMATION); to verify the people behind a company, create a separate KYC workflow and link it from the KYB_KEY_PEOPLE node. For BRANCHING or conditional logic, use the graph tools instead: didit_workflow_get_field_definitions, then didit_workflow_validate_graph, then didit_workflow_set_graph.

didit_workflow_create_draft

ChatGPT
Create an editable DRAFT version from a published workflow (graph/config edits require a DRAFT). Returns the new draft's uuid.

didit_workflow_edit_graph

ChatGPT
MODIFY an existing workflow's graph with small OPERATIONS - the right tool for editing a live workflow. You send only the deltas; the MCP fetches the full current graph SERVER-SIDE, applies your ops in order, validates, auto-creates a DRAFT (the live version is never touched), and saves. This means huge feature configs (documents_allowed, poa_documents_allowed, phone countries) are preserved exactly and you NEVER resend them. Validation failures return applied:false with the errors (nothing saved). The six op shapes are documented on the operations parameter; a typical edit upserts new nodes with set_node and rewires their neighbors with set_next. To branch after a feature node, point its next at a new branch node whose branches carry the rules (from didit_workflow_get_field_definitions) and whose goto targets are new status or feature nodes.

didit_workflow_get

ChatGPT
Get the full configuration of a specific workflow, including response_attributes (returned data / data minimization): which data points the client receives per feature.

didit_workflow_get_feature_config_schema

ChatGPT
The exact config object each workflow feature accepts - every key, its type, bounds, default, accepted values and meaning. Generated from the backend serializers that validate a save (contract sha256:a2c413a50107faf3ea47fa187089a930ac17d3d04893e24176f494a58470e982), so it is never out of date with the API. Call it before configuring a feature you have not configured before, and whenever a config key you set came back missing: a key outside this contract is dropped silently. Pass feature for one feature (AGE_ESTIMATION, AML, BANK_VERIFICATION, DATABASE_VALIDATION, DOCUMENT_AI, EMAIL_VERIFICATION, FACE_MATCH, GEOLOCATION, IP_ANALYSIS, KYB_DOCUMENTS, KYB_KEY_PEOPLE, KYB_REGISTRY, LIVENESS, NFC, OCR, PHONE_VERIFICATION, PROOF_OF_ADDRESS, QUESTIONNAIRE), or omit it for all of them.

didit_workflow_get_field_definitions

ChatGPT
List every field you can branch on plus the operators valid for each (e.g. kyc.status, kyc.extra_fields.profession with fuzzy_match, document_ai.<key>, aml.risk_score). Call this before building branch rules so the field/operator pairs are valid.

didit_workflow_get_graph

ChatGPT
Get the node/graph for a workflow (the structure: nodes, branches, conditions, Document-AI steps) + status/version/is_editable. Large feature configs (documents_allowed, poa_documents_allowed, phone countries) are SUMMARIZED by default so the response never overflows — set include_config:true for the raw config. Includes returned_data (response_attributes): the ONLY source of truth for what data the client/relying party receives in the API response and webhooks — never infer that from which features run. Also includes age_assurance: whether the workflow checks age, and by which method (document age restrictions and/or AGE_ESTIMATION) — decide that from this block, never from the workflow's name. Pass just workflow_id; the owning org/app is resolved automatically. To MODIFY the graph, prefer didit_workflow_edit_graph (small ops, no need to resend big configs).

didit_workflow_list

ChatGPT
List verification workflows. With multiple apps (or no scope) it auto-spans every app, each row tagged with its org/app. To find one workflow by id/label across all apps, prefer didit_workflow_search. The features on a row do NOT tell you whether a workflow checks age: age assurance done from the DOCUMENT (age restrictions on the OCR step) shows no feature of its own. For any question about which workflows do age assurance, pass include_age_assurance:true — it annotates each row with does_age_assurance/methods server-side, which is the only reliable way to find them.

didit_workflow_publish

ChatGPT
Publish the workflow version that holds the pending changes — makes it live for NEW sessions. Existing sessions are unaffected. Pass the version_uuid that set_graph/edit_graph returned: a published version can never hold an edit, so a stable workflow_id resolves to the version that is ALREADY live. Publishing a live version with no draft is refused instead of reported as done.

didit_workflow_update

ChatGPT
Update a workflow's top-level SETTINGS only (workflow_label, is_default, retry/expiration, white-label, etc.). Omitted status preserves the current draft/published state; publication changes only when status is explicitly passed. It does NOT change which features run: to add/remove/reorder features, add a conditional branch, or add a Document-AI step, edit the graph with didit_workflow_edit_graph (small ops, preserves the big allow-lists) or didit_workflow_set_graph (full replace) — those are the only ways feature changes actually persist.

didit_workflow_validate_graph

ChatGPT
Dry-run validate a graph WITHOUT saving. Returns per-node errors (bad field/operator, missing dependency, branching on a field before its feature runs, etc.). Always validate before didit_workflow_set_graph.

Capabilities

InteractiveWrites

Example Prompts

Click any prompt to copy it.

Similar Apps

Listed on MCP App Store

Listed on MCP App Store

Add this badge to your site or README. It links to this page.

HTML

<a href="https://mcp-app-store.keenethics-labs.com/app/didit"><img src="https://mcp-app-store.keenethics-labs.com/badges/listed-on-mcp-app-store.svg" alt="Listed on MCP App Store" width="220" height="44"></a>

Markdown

[![Listed on MCP App Store](https://mcp-app-store.keenethics-labs.com/badges/listed-on-mcp-app-store.svg)](https://mcp-app-store.keenethics-labs.com/app/didit)