# io.github.g-digital-by-Garrigues/ead-enterprise-suite (npm · @g-digital/mcp-ead-enterprise-suite)

MCP server for EAD Enterprise Suite - signatures, evidence, notifications, dossiers via AI agents.

- Trust score: 63/100 (medium)
- Change this week: +39
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- npm · `@g-digital/mcp-ead-enterprise-suite`: 63/100 (this document), [markdown](https://verifymcp.io/servers/g-digital-by-garrigues-ead-enterprise-suite/g-digital-mcp-ead-enterprise-suite.md), [page](https://verifymcp.io/servers/g-digital-by-garrigues-ead-enterprise-suite/g-digital-mcp-ead-enterprise-suite)

## Channel facts

- Registry: `npm`
- Package: `@g-digital/mcp-ead-enterprise-suite`
- Version: `1.6.1`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-08-03.

- **Supply Chain Security**: 87/100
  - No malware found by supply-chain analysis.
  - Only part of the dependency tree could be resolved (110 of 114), so this covers what we could see, not the whole tree.
  - No install/post-install scripts declared.
  - Only part of the dependency tree could be resolved (110 of 114), so this covers what we could see, not the whole tree.
- **Provenance & Transparency**: 45/100
  - Source repository is publicly reachable at the declared URL.
  - Build provenance is cryptographically sound, but it attests a different repository to the one declared in the registry. Most often the declared URL is simply stale.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 11 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 59/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 6344 tokens (~122/item across 52 items; 52 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 27/100
  - Stability observed for 8 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 70/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 10% of tool parameters carry a description.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### Claude

```bash
claude mcp add g-digital-by-garrigues-ead-enterprise-suite -- npx -y @g-digital/mcp-ead-enterprise-suite
```

### Codex

```bash
codex mcp add g-digital-by-garrigues-ead-enterprise-suite -- npx -y @g-digital/mcp-ead-enterprise-suite
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "g-digital-by-garrigues-ead-enterprise-suite": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "@g-digital/mcp-ead-enterprise-suite"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add g-digital-by-garrigues-ead-enterprise-suite --command npx --arg -y --arg @g-digital/mcp-ead-enterprise-suite
```

### Hermes

```yaml
mcp_servers:
  g-digital-by-garrigues-ead-enterprise-suite:
    command: "npx"
    args: ["-y", "@g-digital/mcp-ead-enterprise-suite"]
```

### Other

```json
{
  "mcpServers": {
    "g-digital-by-garrigues-ead-enterprise-suite": {
      "command": "npx",
      "args": [
        "-y",
        "@g-digital/mcp-ead-enterprise-suite"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-08-03 (score 63, +1)

No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-08-02 (score 62, +57)

- [security improvement] Install scripts: unverified → pass
- [security improvement] Known CVEs: unverified → partial
- [security improvement] Malware scan: unverified → pass
- [security] Provenance: Build provenance is cryptographically sound, but it attests a different repository to the one declared in the registry. Most often the declared URL is simply stale.
- [functional regression] Security disclosure: fail → unverified
- [functional improvement] Schema quality: unverified → good
- [functional improvement] Stability: unverified → 0.23
- [functional improvement] MCP protocol: unverified → pass
- [functional improvement] Maintenance: unverified → pass
- [functional improvement] License: unverified → pass
- [functional improvement] Tool coverage: unverified → 100
- [functional improvement] Dependency health: unverified → partial
- [functional] Licence: MIT

### 2026-08-01 (score 5, −12)

- [functional regression] Tool coverage: 100 → unverified

### 2026-07-31 (score 17, −6)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-30 (score 23, −18)

- [security regression] Malware scan: pass → unverified

### 2026-07-28 (score 41, +17)

- [functional regression] Security disclosure: unverified → fail
- [functional improvement] Tool coverage: unverified → 100
- [functional] First check of Schema quality: fail
- [functional] First check of Schema quality: unverified
- [functional] First check of Schema quality: fail
- [functional] First check of Tool coverage: 10

### 2026-07-27 (score 24)

First indexed and scored.

## MCP tools (52)

### `evidence_create` (~420 tokens)

Registers a NEW evidence record inside an evidence group. Requires: evidence_group_create → evidenceGroupId, case_file_create → caseFileId. Generate a UUID v4 for `id`. Compute the SHA-256 hex hash of the file BEFORE calling. Normal INTERNAL flow: call evidence_create with custodyType INTERNAL and NO fileUrl; the API returns uploadFileUrl, a presigned S3 URL. You MUST PUT the exact file bytes to uploadFileUrl, then verify with evidence_get/evidence_list, and ONLY THEN call evidence_seal. Do not seal an evidence group until every INTERNAL evidence file has been uploaded. Convenience flow: if you pass `fileUrl` (public HTTPS, no redirects, under 1 GiB), this tool downloads that URL and PUTs the bytes to uploadFileUrl for you. EXTERNAL flow: use custodyType EXTERNAL only when you intentionally register hash-only evidence; still generate a fresh UUID for each evidence. If an INTERNAL evidence creation/upload failed and you want to retry as EXTERNAL, create a NEW evidence id; do not reuse an id whose outcome is unknown. WARNING: the API sometimes returns {code:'EvidenceCreateError'} even when the evidence was successfully persisted — always verify with evidence_list before retrying.

Input parameters:

- `caseFileId` (string, required): UUID of the case file
- `custodyType` (string): INTERNAL = EAD stores the file; EXTERNAL = only hash registered
- `evidenceGroupId` (string, required): UUID of the evidence group
- `fileName` (string, required): Original file name including extension
- `fileUrl` (string): Optional public HTTPS URL to download and auto-upload to the returned uploadFileUrl (custodyType INTERNAL only). Omit this when you want the manual presigned-URL flow.
- `hash` (string, required): SHA-256 hex digest of the file content (64 hex chars)
- `id` (string, required): UUID v4 for the new evidence record (idempotency key)
- `title` (string, required): Human-readable title for the evidence

### `evidence_list` (~81 tokens)

Lists all evidence records in a specific evidence group. Requires: caseFileId and evidenceGroupId. Returns paginated list with IDs, titles, status, and timestamps.

Input parameters:

- `caseFileId` (string, required)
- `evidenceGroupId` (string, required)
- `filter` (object)
- `order` (object)
- `page` (object)

### `evidence_seal` (~162 tokens)

Seal and certify an evidence group. Closes the group to new additions and triggers async timestamping. Returns immediately — the group transitions OPEN → CLOSING → CLOSED. Poll evidence_group_list until status is CLOSED before linking to a dossier.

Input parameters:

- `altitudeLocation` (string)
- `attestation` (object)
- `caseFileId` (string, required)
- `deviceManufacturer` (string)
- `deviceModel` (string)
- `deviceOS` (string)
- `evidencesCount` (number, required)
- `id` (string, required)
- `latitudeLocation` (string)
- `locationAccuracy` (string)
- `longitudeLocation` (string)
- `userAgent` (string)
- `webUrl` (string)

### `evidence_get` (~83 tokens)

Retrieves a specific evidence record. Requires: evidence_create → evidenceId, evidence_group_create → evidenceGroupId, case_file_create → caseFileId. Returns status (COMPLETED|IN_PROCESS|ERROR), hash, and tspTimestamp when certified.

Input parameters:

- `caseFileId` (string, required)
- `evidenceGroupId` (string, required)
- `id` (string, required)

### `evidence_group_create` (~110 tokens)

Creates an evidence group inside a case file. Requires: case_file_create → caseFileId. Generate a UUID v4 for `id`. Set evidenceType to FILE, PHOTO, VIDEO, or WEB_PLUGIN. Returns evidenceGroupId. One group can contain multiple evidence records.

Input parameters:

- `attestation` (object)
- `caseFileId` (string, required)
- `description` (string)
- `evidenceType` (string, required)
- `id` (string, required)
- `name` (string, required)

### `evidence_group_list` (~81 tokens)

Lists all evidence groups in a case file with their current status (OPEN, CLOSING, CLOSED). Use to find an existing group or check which groups are ready for sealing. Requires: caseFileId.

Input parameters:

- `caseFileId` (string, required)
- `filter` (object)
- `order` (object)
- `page` (object)

### `dossier_create` (~164 tokens)

Creates a dossier to aggregate certified evidence groups into a single tamper-evident PDF. Requires: case_file_create → caseFileId. Evidence groups must be in CLOSED status before linking. Generate a UUID v4 string for `id`. Returns dossierId. After creation, link evidence with dossier_evidence_link, then certify with dossier_certify.

Input parameters:

- `accessToken` (string)
- `caseFileId` (string, required)
- `dossierTemplateId` (string)
- `filledFields` (object)
- `id` (string, required)
- `language` (string, required)
- `modelId` (string)
- `name` (string, required)
- `purpose` (string)
- `validityFrom` (string, required)
- `validityTo` (string, required)

### `dossier_update` (~125 tokens)

Updates the metadata of an existing dossier. Requires: dossier_create → dossierId, caseFileId. Only available while dossier is in DRAFT status.

Input parameters:

- `accessToken` (string)
- `caseFileId` (string, required)
- `dossierId` (string, required)
- `dossierTemplateId` (string)
- `filledFields` (object)
- `language` (string)
- `modelId` (string)
- `name` (string)
- `purpose` (string)
- `validityFrom` (string)
- `validityTo` (string)

### `dossier_certify` (~95 tokens)

Certifies a dossier, generating a tamper-evident PDF and locking all linked evidence. Requires: dossier_create → dossierId, dossier_evidence_link (evidence linked), case_file_create → caseFileId. ASYNC: transitions DRAFT → CERTIFYING → CERTIFIED. Poll dossier_list until dossierId status === CERTIFIED.

Input parameters:

- `caseFileId` (string, required)
- `dossierId` (string, required)

### `dossier_list` (~80 tokens)

Lists all dossiers in a case file. Requires: caseFileId. Returns paginated list with IDs, names, status, and creation dates. Use to monitor certification progress — poll until status: CERTIFIED.

Input parameters:

- `caseFileId` (string, required)
- `filter` (object)
- `order` (object)
- `page` (object)

### `dossier_get` (~51 tokens)

Retrieves full details of a specific dossier including status, linked evidence, and download URLs. Requires: caseFileId and dossierId.

Input parameters:

- `caseFileId` (string, required)
- `dossierId` (string, required)

### `dossier_template_list` (~45 tokens)

Lists available dossier templates. No prerequisites. Returns template IDs and their translations per language. Use the returned id as dossierTemplateId in dossier_create.

Input parameters:

- `page` (object)

### `dossier_preview` (~45 tokens)

Returns an HTML preview URL of a dossier before certification. Requires: caseFileId and dossierId.

Input parameters:

- `caseFileId` (string, required)
- `dossierId` (string, required)

### `dossier_document_url` (~53 tokens)

Returns the download URL for the certified dossier PDF. Requires: dossier_certify (CERTIFIED status), caseFileId, dossierId.

Input parameters:

- `caseFileId` (string, required)
- `dossierId` (string, required)

### `dossier_package_url` (~58 tokens)

Returns the download URL for the full dossier package (PDF + evidence files). Requires: dossier_certify (CERTIFIED status), caseFileId, dossierId.

Input parameters:

- `caseFileId` (string, required)
- `dossierId` (string, required)

### `dossier_visibility` (~61 tokens)

Updates the visibility (public/private) of a certified dossier. Requires: dossier_certify (CERTIFIED status), caseFileId, dossierId.

Input parameters:

- `caseFileId` (string, required)
- `dossierId` (string, required)
- `visibility` (string, required)

### `dossier_delete` (~66 tokens)

Deletes a dossier. Available in DRAFT status (to discard before certification) or in CERTIFIED status (to permanently remove the certified dossier). Irreversible. Requires: caseFileId and dossierId.

Input parameters:

- `caseFileId` (string, required)
- `dossierId` (string, required)

### `dossier_group_certify` (~133 tokens)

Creates AND certifies a dossier from a single sealed evidence group in one call (express path). Requires: evidence_seal (CLOSED), case_file_create → caseFileId, evidence_group_create → evidenceGroupId. Generate a UUID v4 string for `id`. Returns dossierId with CERTIFYING status → poll until CERTIFIED.

Input parameters:

- `caseFileId` (string, required)
- `evidenceGroupId` (string, required)
- `evidenceIds` (array)
- `id` (string, required)
- `language` (string, required)
- `modelId` (string)
- `name` (string, required)

### `dossier_evidence_link` (~100 tokens)

Links evidence items from a sealed group to a dossier. Requires: dossier_create → dossierId, evidence_seal (CLOSED), case_file_create → caseFileId. Pass the ids array of evidence UUIDs. Can be called multiple times for evidence from different case files.

Input parameters:

- `caseFileId` (string, required)
- `caseFileToLinkId` (string, required)
- `dossierId` (string, required)
- `ids` (array, required)

### `dossier_evidence_list_to_link` (~88 tokens)

Lists evidence items available to be linked to a dossier (CLOSED groups not yet linked). Requires: caseFileId and dossierId.

Input parameters:

- `caseFileId` (string, required)
- `caseFileToLinkId` (string, required)
- `dossierId` (string, required)
- `filter` (object)
- `order` (object)
- `page` (object)

### `dossier_evidence_list` (~76 tokens)

Lists all evidence items linked to a dossier. Requires: caseFileId and dossierId.

Input parameters:

- `caseFileId` (string, required)
- `dossierEvidenceGroupId` (string, required)
- `dossierId` (string, required)
- `filter` (object)
- `order` (object)
- `page` (object)

### `dossier_evidence_get` (~70 tokens)

Retrieves details of a specific evidence item linked to a dossier. Requires: caseFileId, dossierId, evidenceId.

Input parameters:

- `caseFileId` (string, required)
- `dossierEvidenceGroupId` (string, required)
- `dossierEvidenceId` (string, required)
- `dossierId` (string, required)

### `dossier_evidence_delete` (~76 tokens)

Removes an evidence item from a dossier. Only available while dossier is in DRAFT status. Requires: caseFileId, dossierId, evidenceId.

Input parameters:

- `caseFileId` (string, required)
- `dossierEvidenceGroupId` (string, required)
- `dossierEvidenceId` (string, required)
- `dossierId` (string, required)

### `notification_document_add` (~73 tokens)

Performs the notification_document_add operation. Review the API documentation for full field details.

Input parameters:

- `caseFileId` (string, required)
- `fileName` (string, required)
- `fileSize` (number)
- `hash` (string, required)
- `id` (string, required)
- `notificationRequestId` (string, required)

### `notification_request_create` (~228 tokens)

Creates a certified notification request. Requires: case_file_create → caseFileId. Generate a UUID v4 for `id`. Set language to en_GB or es_ES. Returns notificationRequestId. Add at least one receiver with notification_receiver_add before sending. IMPORTANT: The `content` field must be valid HTML — plain text without HTML tags will not render on the recipient landing page. Only the following HTML formats are supported: paragraphs (<p>), bold (<strong>), italic (<em>), unordered lists (<ul><li>), ordered lists (<ol><li>). Do not use other HTML tags or CSS. Avoid special typographic characters (em dashes, smart quotes) in `subject`; use standard ASCII equivalents (hyphen, straight quotes) instead.

Input parameters:

- `caseFileId` (string, required)
- `content` (string, required)
- `id` (string, required)
- `language` (string, required)
- `otpByDefault` (boolean)
- `sendWaUrlByDefault` (boolean)
- `subject` (string, required)
- `type` (string)

### `notification_request_send` (~59 tokens)

Trigger delivery of a certified notification to all added recipients. Returns immediately — delivery is async. Poll notification_request_status until status is DELIVERED before retrieving certificates.

Input parameters:

- `caseFileId` (string, required)
- `notificationRequestId` (string, required)

### `notification_request_status` (~111 tokens)

Checks the delivery status of a certified notification. Requires: notificationRequestId, caseFileId. Returns status (CREATING|DRAFT|IN_PROCESS|SENT|PARTIALLY_READ|FULLY_READ|PARTIALLY_ANSWERED|FULLY_ANSWERED). Poll until status is SENT or beyond. Do not call notification_certificate_get while status is CREATING, DRAFT, or IN_PROCESS.

Input parameters:

- `caseFileId` (string, required)
- `notificationRequestId` (string, required)

### `notification_receiver_add` (~141 tokens)

Adds a recipient to a notification request. Requires: notification_request_create → notificationRequestId, case_file_create → caseFileId. The `id` can be a UUID v4 or custom string. Returns receiverId — save it for notification_certificate_get.

Input parameters:

- `caseFileId` (string, required)
- `email` (string, required)
- `firstName` (string, required)
- `id` (string, required)
- `lastName` (string, required)
- `notificationRequestId` (string, required)
- `otpRequired` (boolean)
- `phoneNumber` (string)
- `phonePrefix` (string)
- `sendWaUrl` (boolean)

### `notification_certificate_get` (~153 tokens)

Creates or retrieves a PDF certificate for a specific notification receiver. Requires notification_request_send and notification_receiver_add. Generate a UUID v4 for `id` the first time and reuse that id when polling. This tool is idempotent: it first lists existing certificates for the receiver and, if `id` already exists, returns it instead of creating it again. If the certificate status is CERTIFIED, the response includes documentUrl when available. If it is CERTIFYING, poll this same tool with the same id.

Input parameters:

- `caseFileId` (string, required)
- `id` (string, required)
- `language` (string)
- `notificationRequestId` (string, required)
- `receiverId` (string, required)

### `case_file_create` (~97 tokens)

Creates a new case file — the top-level container for all related operations (evidence, notifications, signatures, dossiers). Call this first before any other operation. Generate a UUID v4 for `id`. Returns caseFileId needed for all subsequent calls.

Input parameters:

- `description` (string)
- `id` (string, required)
- `name` (string, required)
- `reference` (string)
- `useCaseId` (string, required)

### `case_file_list` (~80 tokens)

Lists all case files in your EAD Enterprise Suite account. Pass userId (from session_login or session_info) to scope results to your account. Returns paginated list with IDs, names, and status.

Input parameters:

- `filter` (object)
- `order` (object)
- `page` (object)
- `userId` (string, required)

### `case_file_get` (~50 tokens)

Retrieves details of a specific case file. Requires: caseFileId. Use to verify a case file exists before creating evidence groups, dossiers, or signature requests.

Input parameters:

- `caseFileId` (string, required)

### `session_login` (~69 tokens)

Authenticate with EAD Enterprise Suite. Credentials are read from the server environment: if MCP_AUTH_USER_KEY is set it is exchanged for a session token; otherwise MCP_AUTH_EMAIL + MCP_AUTH_PASSWORD are used. The server manages authentication automatically — call this only to force a re-login or after a 401.

### `session_info` (~154 tokens)

Returns the authenticated user's session info including userId and session type (Password or UserKey). Use this to retrieve the userId (UUID) required by case_file_list and other user-scoped operations. Works on both auth flows: with a user key (MCP_AUTH_USER_KEY) it resolves identity via profile_get (GET /profile → `id`), since no email is configured; with MCP_AUTH_EMAIL it queries /session-info. profile_get is the canonical way to obtain the userId and returns more (companyId, defaultCaseFileId). Prerequisites: a valid session (call session_login first if needed). Example: session_info() → { userId: '...uuid...', type: 'Password' }

### `profile_get` (~134 tokens)

Returns the authenticated user's own profile. Works on EVERY auth flow (user key or email/password) because it identifies the caller from the session token alone — no email needed. Its `id` field IS your userId (UUID): the value required by case_file_list and every /users/{userId}/... operation. Prefer this over session_info when you need the userId, and it is the ONLY way to obtain it on a user-key deployment (MCP_AUTH_USER_KEY), where no email is configured. Also returns companyId (needed to subscribe to the notifications SSE stream) and defaultCaseFileId. No parameters.

### `use_case_list` (~54 tokens)

Lists available use cases for the account. Use cases define the allowed signature workflows and document types. Returns useCaseId values needed for signature_request_create.

Input parameters:

- `companyId` (string, required)
- `page` (object)

### `signature_group_create` (~260 tokens)

Creates a signing order group for a CONFIGURABLE signature request. Types: 'Document' (groups documents into signing rounds — use its id as groupId in signature_request_add_document), 'Signatory' (groups signatories into signing rounds — use its id as groupId in signature_participant_create), 'DocumentSignatory' (links a specific document to a signing round, requires documentId). IMPORTANT — avoid empty groups: when a CONFIGURABLE request is created, the API automatically pre-creates one Document group and one Signatory group both at index:1. Always use these pre-existing index:1 groups for your first document and first signatory (retrieve their IDs with signature_group_list immediately after creating the request). Only call signature_group_create for the ADDITIONAL groups (index:2, 3…). Add participants with linkToAllDocuments:true so DocumentSignatory groups are auto-generated at the correct index. Adding participants without linkToAllDocuments leaves them unlinked to documents and signature_coordinate_set will fail with 'Signatory not found'.

Input parameters:

- `caseFileId` (string, required)
- `documentId` (string)
- `id` (string, required)
- `requestId` (string, required)
- `type` (string, required)

### `signature_group_list` (~105 tokens)

Lists all signing order groups of a CONFIGURABLE signature request. Returns id, type (Document/Signatory/DocumentSignatory), index, and documentId for each group. Call immediately after signature_request_create to retrieve the pre-created index:1 group IDs before adding documents or participants.

Input parameters:

- `caseFileId` (string, required)
- `filter` (object)
- `order` (object)
- `page` (object)
- `requestId` (string, required)

### `signature_request_create` (~150 tokens)

Creates a new signature request in DRAFT status. Requires: case_file_create → caseFileId. Generate a UUID v4 for `id`. Set deadline as ISO 8601 datetime (max ~30 days ahead). Returns requestId. Add documents with signature_request_add_document and participants with signature_participant_create before activating.

Input parameters:

- `caseFileId` (string, required)
- `closeCondition` (string)
- `dashboardUrl` (string)
- `deadline` (string, required)
- `id` (string, required)
- `language` (string, required)
- `name` (string, required)
- `objectiveId` (string)
- `sequence` (string)
- `signatureType` (string)

### `signature_request_get` (~70 tokens)

Retrieves full details of a signature request. Requires: signature_request_create → requestId, case_file_create → caseFileId. Returns status, documents, participants, deadline, and history. Use to check overall process state.

Input parameters:

- `caseFileId` (string, required)
- `requestId` (string, required)

### `signature_request_cancel` (~59 tokens)

Cancels an active signature request. Requires: activate_signature_request (ACTIVE status), requestId, caseFileId. Transitions to CANCELLED. Cannot be undone.

Input parameters:

- `caseFileId` (string, required)
- `requestId` (string, required)

### `signature_request_add_document` (~340 tokens)

Adds a document to a DRAFT signature request. Requires: signature_request_create → requestId, case_file_create → caseFileId. Provide a string `id` for the document. Compute SHA-256 hex hash of the PDF before calling. Optional: pass `fileUrl` (a publicly accessible URL) to have the tool download and upload the file to S3 automatically — no separate PUT needed. If fileUrl is omitted, returns url (presigned S3 upload URL) for manual PUT. Cannot add documents after activate_signature_request is called. For CONFIGURABLE sequence: `groupId` must reference a Document type group (not Signatory or DocumentSignatory) — passing a wrong group type returns 'Signature group not found'.

Input parameters:

- `caseFileId` (string, required): UUID of the case file
- `convertToPdf` (boolean): Convert non-PDF to PDF before processing
- `fileName` (string, required): File name including extension (e.g. contract.pdf)
- `fileSize` (number): File size in bytes (optional)
- `fileUrl` (string): Optional public URL to download and auto-upload the PDF to S3. Eliminates the manual PUT step.
- `groupId` (string): For CONFIGURABLE sequence: ID of a Document type group
- `hash` (string, required): SHA-256 hex digest of the PDF content (64 hex chars)
- `id` (string, required): UUID for the document — becomes documentId for coordinate_set and certificate_get
- `requestId` (string, required): UUID of the signature request (DRAFT)
- `title` (string, required): Document title shown to signatories

### `signature_document_list` (~134 tokens)

Lists documents in a signature request with their signing status per document. Requires: signature_request_create → requestId, case_file_create → caseFileId. IMPORTANT: when called with documentId it returns participant signing status (PENDING = not yet signed), NOT document processing status. To check if documents reached READY_TO_SIGN (required before activate_signature_request), use signature_request_get instead. Post-activation: poll until document status === SIGNED before calling signature_certificate_get.

Input parameters:

- `caseFileId` (string, required)
- `documentId` (string, required)
- `page` (object)
- `requestId` (string, required)

### `signature_participant_create` (~284 tokens)

Adds a participant (signatory, observer, or validator) to a DRAFT signature request. Requires: signature_request_add_document → documentId + file uploaded to S3, signature_request_create → requestId, case_file_create → caseFileId. Use role SIGNATORY for required signers, OBSERVER for read-only, VALIDATOR for approvers. For ADVANCED signatures, phonePrefix and phoneNumber are mandatory because the signer receives the OTP there; WhatsApp delivery is NOT currently supported for ADVANCED. For INTERPOSITION signatures, phone is optional, and WhatsApp sending is currently available only for this simple/interposition flow when the platform is configured to send a WhatsApp signing link. Returns signatoryId. Add at least one SIGNATORY before activating. For VALIDATOR role: do NOT include groupId or linkToAllDocuments — use assign_validator_to_signatory to link the validator to a specific signatory after creation.

Input parameters:

- `caseFileId` (string, required)
- `email` (string, required)
- `firstName` (string, required)
- `groupId` (string)
- `id` (string, required)
- `lastName` (string, required)
- `linkToAllDocuments` (boolean)
- `phoneNumber` (string)
- `phonePrefix` (string)
- `requestId` (string, required)
- `role` (string, required)

### `signature_participant_list` (~77 tokens)

Lists all participants of a signature request. Requires: signature_request_create → requestId, case_file_create → caseFileId. Returns roles, contact details, and signing status.

Input parameters:

- `caseFileId` (string, required)
- `documentId` (string, required)
- `page` (object)
- `requestId` (string, required)

### `assign_validator_to_signatory` (~117 tokens)

Assigns one or more validators to a specific signatory in a signature request. The validator must approve before the signatory can sign. Requires: signature_participant_create (validator) → validatorId in validatorIds array, signature_participant_create (signatory) → signatoryId, signature_request_create → requestId, case_file_create → caseFileId.

Input parameters:

- `caseFileId` (string, required)
- `requestId` (string, required)
- `signatoryId` (string, required)
- `validatorIds` (array, required)

### `activate_signature_request` (~216 tokens)

Activates a signature request, transitioning from DRAFT to ACTIVE and sending signing invitations to all signatories. Do NOT call this immediately after uploading files. Activation preconditions: request is DRAFT; at least one SIGNATORY exists; every document has been uploaded to its presigned URL; backend processing has had time to complete for every uploaded document (use processed/READY_TO_SIGN from signature_request_get when exposed; otherwise wait after the successful PUT); and PDF documents have signature coordinates set for every required signatory. INTERPOSITION may send a simple signing link, including WhatsApp when available/configured; ADVANCED uses phonePrefix/phoneNumber for OTP and currently does not support WhatsApp delivery. IRREVERSIBLE: cannot add documents or participants after activation. ASYNC: after activation, poll signature_request_get until status is ACTIVE, then use signature_document_list with documentId to monitor signing; call signature_certificate_get only after the document is SIGNED.

Input parameters:

- `caseFileId` (string, required)
- `requestId` (string, required)

### `signature_coordinate_set` (~152 tokens)

Sets the visual position of the signature field on a PDF document page. Required for PDF documents before activation, for both INTERPOSITION and ADVANCED signatures. Requires: signature_participant_create → signatoryId, signature_request_add_document → documentId, signature_request_create → requestId, case_file_create → caseFileId. Provide coordinates as array of {page (1-based), x (points from left), y (points from bottom)}. Set coordinates after the document has been uploaded and before activate_signature_request.

Input parameters:

- `caseFileId` (string, required)
- `coordinates` (array, required)
- `documentId` (string, required)
- `requestId` (string, required)
- `signatoryId` (string, required)

### `signature_certificate_get` (~93 tokens)

Retrieves the signed document certificate PDF. Requires: activate_signature_request (document fully SIGNED), signature_request_add_document → documentId, signature_request_create → requestId, case_file_create → caseFileId. Returns documentUrl (signed PDF certificate). ASYNC: poll until documentUrl is available.

Input parameters:

- `caseFileId` (string, required)
- `documentId` (string, required)
- `requestId` (string, required)

### `large_evidence_upload_initiate` (~104 tokens)

Performs the large_evidence_upload_initiate operation against the GoCertius API. Review the API documentation for full field details.

Input parameters:

- `capturedAt` (string, required)
- `caseFileId` (string, required)
- `evidenceGroupId` (string, required)
- `evidenceId` (string, required)
- `fileName` (string, required)
- `id` (string, required)
- `title` (string, required)
- `totalSizeMB` (number, required)

### `large_evidence_upload_complete` (~82 tokens)

Finalize a multipart evidence upload and register the evidence in the group. Returns immediately — the evidence transitions asynchronously to COMPLETED. Poll evidence_list until status is COMPLETED before sealing the group.

Input parameters:

- `caseFileId` (string, required)
- `evidenceGroupId` (string, required)
- `id` (string, required)
- `userAgent` (string)

### `evidence_upload` (~375 tokens)

Uploads a local file as evidence in one step: computes its SHA-256, registers the evidence record (custodyType INTERNAL = EAD stores the file), and uploads the bytes to S3 — no manual hashing or PUT needed. Internally this follows the required EAD sequence: create INTERNAL evidence → receive uploadFileUrl (presigned S3 URL) → PUT file bytes → return uploaded:true. Requires: case_file_create → caseFileId, evidence_group_create → evidenceGroupId. Provide EXACTLY ONE of `filePath` (absolute local path, stdio/local mode only) or `contentBase64` (base64-encoded file content, ~10 MB max). Use evidence_upload when the file is on the local machine; use evidence_create when you already have the SHA-256 hash, need to inspect/use uploadFileUrl manually, or have a public fileUrl. After this tool succeeds, verify with evidence_get/evidence_list and only then call evidence_seal. If this tool fails before returning an evidence id, check evidence_list before retrying; if retrying manually, use evidence_create with a fresh UUID. Local files must be under 1 GiB.

Input parameters:

- `caseFileId` (string, required): UUID of the case file
- `contentBase64` (string): Base64-encoded file content (~10 MB max). The tool will create evidence, receive uploadFileUrl, and PUT these bytes to it.
- `evidenceGroupId` (string, required): UUID of the evidence group
- `fileName` (string, required): File name including extension
- `filePath` (string): Absolute local path to the file (stdio/local mode only). The tool will create evidence, receive uploadFileUrl, and PUT this file to it.
- `title` (string, required): Human-readable title for the evidence

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/g-digital-by-garrigues-ead-enterprise-suite/g-digital-mcp-ead-enterprise-suite#diagnostics

## Score history

- 2026-08-03: 63
- 2026-08-02: 62
- 2026-08-01: 5
- 2026-07-31: 17
- 2026-07-30: 23
- 2026-07-28: 41
- 2026-07-27: 24

## Links

- npm package: https://www.npmjs.com/package/@g-digital/mcp-ead-enterprise-suite
- Socket report: https://socket.dev/npm/package/@g-digital/mcp-ead-enterprise-suite
- Repository: https://github.com/g-digital-by-Garrigues/EAD_Enterprise_Suite_MCP
- Changelog RSS feed: https://verifymcp.io/servers/g-digital-by-garrigues-ead-enterprise-suite/g-digital-mcp-ead-enterprise-suite/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/g-digital-by-garrigues-ead-enterprise-suite/g-digital-mcp-ead-enterprise-suite/changelog.json
- HTML version of this page: https://verifymcp.io/servers/g-digital-by-garrigues-ead-enterprise-suite/g-digital-mcp-ead-enterprise-suite