Documents
Extract text from uploaded documents (CVs, certificates): PDF with per-page OCR fallback, DOCX, plain text and images. Runs on our own servers; no document is sent to a third party. Members ingest their own gated-files upload and read back only their own result.
Endpoints (7)
Queue text extraction for your own member upload. Requires a verified tenant_auth session (wst_ Bearer). The file must be a gated-files member upload by you, in your tenant. Idempotent: offering the same file again returns the same extraction. Returns { extraction_id, status, record_id, existing }.
| Field | Type | Required | Description |
|---|---|---|---|
file_id |
integer | ✓ Yes | file_id from gated-files/put-upload. |
Status and result of one of your own extractions. Requires a verified tenant_auth session. Returns status (queued | extracting | ok | partial | failed), method, quality, errors, notes and per-page metadata; the text only with include_text=true.
| Field | Type | Required | Description |
|---|---|---|---|
extraction_id |
integer | ✓ Yes | extraction_id from ingest. |
include_text |
boolean | No | Include the extracted text (default false). |
Project settings. ingest_enabled switches member ingest on (default off). record_entity names the MAPI entity for the per-upload anchor record; it must have the fields gated_file_id, extraction_id and original_filename, an owner_field and create: { verified: self }. Checked on save. Send an empty record_entity to switch the anchor record off.
| Field | Type | Required | Description |
|---|---|---|---|
ingest_enabled |
boolean | No | Allow members to ingest uploads (default false). |
record_entity |
string | No | MAPI entity for the anchor record, or empty for none. |
Full extraction for the owner: status, text, per-page text and methods, quality, engines, errors and notes. For review and for the skill-extraction step.
| Field | Type | Required | Description |
|---|---|---|---|
extraction_id |
integer | ✓ Yes | Extraction ID. |
Which extraction programs are installed on the serving node, with versions and OCR languages. Diagnostics after an install or deploy.
No input parameters required.
Skill candidates found in one extraction: occupations (from job titles), software and skills, each grounded in the occupations reference, with the CV lines as evidence, the method version and the O*NET release. Candidates are not profile data until the member confirms them.
| Field | Type | Required | Description |
|---|---|---|---|
extraction_id |
integer | ✓ Yes | Extraction ID. |
status |
string | No | Filter: pending | confirmed | rejected. Default all. |
Queue a new candidate run for an extraction, for example after the method improved. Candidates the member already confirmed or rejected stay as they are.
| Field | Type | Required | Description |
|---|---|---|---|
extraction_id |
integer | ✓ Yes | Extraction ID. |
MCP Tool Names
When using this integration through an AI assistant (Claude, ChatGPT, Cursor, etc.), the endpoints are available as MCP tools:
| Endpoint | MCP Tool Name |
|---|---|
| ingest | documents_ingest |
| status | documents_status |
| configure | documents_configure |
| extraction | documents_extraction |
| tools-status | documents_tools_status |
| candidates | documents_candidates |
| regenerate | documents_regenerate |
Website