Docugami Model Context Protocol (MCP) Server Tools (Preview)
Download OpenAPI specification:
List documents
Authorizations:
Request Body schema: application/json
| name | string Filters documents by name, excluding any prefix. |
| prefix | string Filters documents by |
| limit | integer <int32> [ 1 .. 100 ] Default: 30 Maximum number of items to return. |
| cursor | string Opaque continuation token used to get additional items when a previous query returned more than |
| docsetId | string Filters documents by docset. |
| status | string (document-status) Enum: "New" "Ingesting" "Ingested" "Processing" "Ready" "Error" "OverQuota" Filters documents by status. |
| minPages | integer <int32> >= 0 Filters documents by minimum number of pages in the document. |
| maxPages | integer <int32> >= 0 Filters documents by maximum number of pages in the document. |
| minSize | integer <int32> >= 0 Filters documents by minimum file size in bytes. |
| maxSize | integer <int32> >= 0 Filters documents by maximum file size in bytes. |
| samples | boolean Whether or not to return sample documents. |
| metadata | object[] Filters documents by metadata value. |
Responses
Request samples
- Payload
- list_documents
{- "name": "string",
- "prefix": "string",
- "limit": 30,
- "cursor": "string",
- "docsetId": "string",
- "status": "Ready",
- "minPages": 0,
- "maxPages": 0,
- "minSize": 0,
- "maxSize": 0,
- "samples": true,
- "metadata": null
}Response samples
- 200
{- "documents": [
- {
- "id": "bn0px5iaym7z",
- "name": "Master Services Agreement.pdf",
- "status": "Ready",
- "createdAt": "2023-03-06T17:23:26.8324745+00:00",
- "size": 119907,
- "processedAt": "2023-03-06T17:30:30.9086048+00:00",
- "pageCount": 9,
- "error": {
- "title": "Encrypted File",
- "detail": "string"
}, - "docset": {
- "id": "gmk07l49tk2c",
}, - "isSample": false,
- "metadata": [
- {
- "key": "my key",
- "value": "my value"
}
]
}
], - "next": [
- {
- "\"token\":\"<token>\"": null,
- "\"range\"": {
- "\"min\":\"05C1E30EA355AB\"": null,
- "\"max\":\"FE\"": null
}
}
]
}Get a document
Authorizations:
Request Body schema: application/json
| id required | string The ID of the document to retrieve. |
Responses
Request samples
- Payload
- get_document
{- "id": "string"
}Response samples
- 200
{- "id": "bn0px5iaym7z",
- "name": "Master Services Agreement.pdf",
- "status": "Ready",
- "createdAt": "2023-03-06T17:23:26.8324745+00:00",
- "size": 119907,
- "processedAt": "2023-03-06T17:30:30.9086048+00:00",
- "pageCount": 9,
- "error": {
- "title": "Encrypted File",
- "detail": "string"
}, - "docset": {
- "id": "gmk07l49tk2c",
}, - "isSample": false,
- "metadata": [
- {
- "key": "my key",
- "value": "my value"
}
]
}Upload a document
The maximum request size is 300 MB. The allowed file extensions are: .pdf, .docx, .doc, .txt, .html, and .zip. For zip archive uploads, only files with .pdf, .docx, .txt, .html, or .doc extensions within the archive will be processed.
Authorizations:
Request Body schema: application/json
| fileName required | string File name. |
| base64Content required | string <base64-encoded> Binary file. Must be a .pdf, .docx, .doc, .html, .txt, or .zip. |
| docsetIds required | string Optional. If a single docset ID is provided the document will be assigned to that docset. If multiple docset IDs are provided in a '|' delimited list (e.g. 'id1|id2|id3') then the document will be classified into one of the provided docsets based on its similarities to existing files in that docset. |
Responses
Request samples
- Payload
- upload_document
{- "fileName": "string",
- "base64Content": "string",
- "docsetIds": "string"
}Response samples
- 200
- 201
- 403
{- "documents": [
- {
- "id": "bn0px5iaym7z",
- "name": "Master Services Agreement.pdf",
- "status": "Ready",
- "createdAt": "2023-03-06T17:23:26.8324745+00:00",
- "size": 119907,
- "processedAt": "2023-03-06T17:30:30.9086048+00:00",
- "pageCount": 9,
- "error": {
- "title": "Encrypted File",
- "detail": "string"
}, - "docset": {
- "id": "gmk07l49tk2c",
}, - "isSample": false,
- "metadata": [
- {
- "key": "my key",
- "value": "my value"
}
]
}
], - "next": [
- {
- "\"token\":\"<token>\"": null,
- "\"range\"": {
- "\"min\":\"05C1E30EA355AB\"": null,
- "\"max\":\"FE\"": null
}
}
]
}List docsets
Authorizations:
Request Body schema: application/json
| name | string Filters documents by name, excluding any prefix. |
| limit | integer <int32> [ 1 .. 100 ] Default: 30 Maximum number of items to return. |
| cursor | string Opaque continuation token used to get additional items when a previous query returned more than |
| minDocuments | integer <int32> >= 0 Minimum number of documents in the docset. |
| maxDocuments | integer <int32> >= 0 Maximum number of documents in the docset. |
| samples | boolean Whether or not to return sample documents. |
Responses
Request samples
- Payload
- list_document_sets
{- "name": "string",
- "limit": 30,
- "cursor": "string",
- "minDocuments": 0,
- "maxDocuments": 0,
- "samples": true
}Response samples
- 200
{- "docsets": [
- {
- "id": "gmk07l49tk2c",
- "name": "Service Agreements",
- "updatedAt": "2023-03-06T17:41:50+00:00",
- "documentCount": 6,
- "createdAt": "2023-03-06T17:23:25.9993034+00:00",
- "isSample": false
}
], - "next": [
- {
- "\"token\":\"<token>\"": null,
- "\"range\"": {
- "\"min\":\"05C1E30EA355AB\"": null,
- "\"max\":\"FE\"": null
}
}
]
}Get a docset
Authorizations:
Request Body schema: application/json
| id required | string The ID of the docset to retrieve. |
Responses
Request samples
- Payload
- get_document_set
{- "id": "string"
}Response samples
- 200
{- "id": "gmk07l49tk2c",
- "name": "Service Agreements",
- "updatedAt": "2023-03-06T17:41:50+00:00",
- "documentCount": 6,
- "createdAt": "2023-03-06T17:23:25.9993034+00:00",
- "isSample": false
}Delete a docset
Deleting a docset does not delete any documents it contains.
Authorizations:
Request Body schema: application/json
| id required | string The ID of the docset to delete. |
Responses
Request samples
- Payload
- delete_document_set
{- "id": "string"
}Response samples
- 200
trueList documents in a docset
Authorizations:
Request Body schema: application/json
| id required | string The ID of the docset to retrieve documents for. |
| prefix | string Filters documents by |
| limit | integer <int32> [ 1 .. 100 ] Default: 30 Maximum number of items to return. |
| cursor | string Opaque continuation token used to get additional items when a previous query returned more than |
| status | string (document-status) Enum: "New" "Ingesting" "Ingested" "Processing" "Ready" "Error" "OverQuota" Filters documents by status. |
| minPages | integer <int32> >= 0 Filters documents by minimum number of pages in the document. |
| maxPages | integer <int32> >= 0 Filters documents by maximum number of pages in the document. |
| minSize | integer <int32> >= 0 Filters documents by minimum file size in bytes. |
| maxSize | integer <int32> >= 0 Filters documents by maximum file size in bytes. |
Responses
Request samples
- Payload
- get_document_set_documents
{- "id": "string",
- "prefix": "string",
- "limit": 30,
- "cursor": "string",
- "status": "Ready",
- "minPages": 0,
- "maxPages": 0,
- "minSize": 0,
- "maxSize": 0
}Response samples
- 200
{- "documents": [
- {
- "id": "bn0px5iaym7z",
- "name": "Master Services Agreement.pdf",
- "status": "Ready",
- "createdAt": "2023-03-06T17:23:26.8324745+00:00",
- "size": 119907,
- "processedAt": "2023-03-06T17:30:30.9086048+00:00",
- "pageCount": 9,
- "error": {
- "title": "Encrypted File",
- "detail": "string"
}, - "docset": {
- "id": "gmk07l49tk2c",
}, - "isSample": false,
- "metadata": [
- {
- "key": "my key",
- "value": "my value"
}
]
}
], - "next": [
- {
- "\"token\":\"<token>\"": null,
- "\"range\"": {
- "\"min\":\"05C1E30EA355AB\"": null,
- "\"max\":\"FE\"": null
}
}
]
}Add a document to a docset
The document is moved if it is already part of a docset.
Authorizations:
Request Body schema: application/json
| docsetId required | string The ID of the docset to add the document to. |
| documentId required | string The ID of the document to add to the docset. |
Responses
Request samples
- Payload
- add_document
{- "docsetId": "string",
- "documentId": "string"
}Response samples
- 200
{- "id": "gmk07l49tk2c",
- "name": "Service Agreements",
- "updatedAt": "2023-03-06T17:41:50+00:00",
- "documentCount": 6,
- "createdAt": "2023-03-06T17:23:25.9993034+00:00",
- "isSample": false
}Remove a document from a docset
Removing a document from a docset does not delete the document.
Authorizations:
Request Body schema: application/json
| docsetId required | string The ID of the docset to remove the document from. |
| documentId required | string The ID of the document to remove from the docset. |
Responses
Request samples
- Payload
- remove_document
{- "docsetId": "string",
- "documentId": "string"
}List projects
List projects in the workspace. Projects are used to organize and manage artifacts created from documents in docsets.
Authorizations:
Request Body schema: application/json
| name | string Filters projects by name. |
| limit | integer <int32> [ 1 .. 100 ] Default: 30 Maximum number of items to return. |
| cursor | string Opaque continuation token used to get additional items when a previous query returned more than |
| docsetId | string Filters projects by docset. |
| type | string (project-type) Enum: "TabularReport" "Abstract" "ExcelExport" "AssistedAuthoring" "AutomationAnywhereDocumentAssembly" "AutomationAnywhereWorkFlow" "ZapierWorkFlow" "UiPathWorkFlow" "UiPathDocumentAssembly" "PowerAutomateWorkFlow" "DiligenceReport" Filters projects by type. |
Responses
Request samples
- Payload
- list_projects
{- "name": "string",
- "limit": 30,
- "cursor": "string",
- "docsetId": "string",
- "type": "TabularReport"
}Response samples
- 200
{- "projects": [
- {
- "id": "0gjiwhvpeqcg",
- "name": "My Report",
- "type": "TabularReport",
- "updatedAt": "2023-03-13T20:22:31.0982176+00:00",
- "createdAt": "2023-03-13T20:22:30.6981643+00:00",
- "artifacts": {
- "version": "1",
}
}
], - "next": [
- {
- "\"token\":\"<token>\"": null,
- "\"range\"": {
- "\"min\":\"05C1E30EA355AB\"": null,
- "\"max\":\"FE\"": null
}
}
]
}Get a project
Authorizations:
Request Body schema: application/json
| id required | string The ID of the project to retrieve. |
Responses
Request samples
- Payload
- get_project
{- "id": "string"
}Response samples
- 200
{- "id": "0gjiwhvpeqcg",
- "name": "My Report",
- "type": "TabularReport",
- "updatedAt": "2023-03-13T20:22:31.0982176+00:00",
- "createdAt": "2023-03-13T20:22:30.6981643+00:00",
- "artifacts": {
- "version": "1",
}
}List artifacts
List the artifacts of the specified project from Docugami. Artifacts are created from documents in docsets associated with the project.
Authorizations:
Request Body schema: application/json
| projectId required | string The ID of the project to retrieve artifacts for. |
| version | string The version of the artifacts to retrieve. Use "latest" to get the latest version. |
| name | string Filters artifacts by name. |
| documentId | string Filters artifacts by document id. |
| limit | integer <int32> [ 1 .. 100 ] Default: 30 Maximum number of items to return. |
| cursor | string Opaque continuation token used to get additional items when a previous query returned more than |
| minSize | integer <int32> Filters artifacts by minimum file size in bytes. |
| maxSize | integer <int32> Filters artifacts by maximum file size in bytes |
| isReadOnly | boolean Filters artifacts by read-only status. |
Responses
Request samples
- Payload
- list_artifacts
{- "projectId": "string",
- "version": "1",
- "name": "string",
- "documentId": "string",
- "limit": 30,
- "cursor": "string",
- "minSize": 0,
- "maxSize": 0,
- "isReadOnly": true
}Response samples
- 200
{- "artifacts": [
- {
- "id": "sydeqizookql",
- "name": "document.xml",
- "size": 263206,
- "version": "1",
- "createdAt": "2023-03-21T23:15:32+00:00",
- "updatedAt": "2023-03-21T23:15:32+00:00",
- "isReadOnly": true,
- "document": {
- "id": "h6qpx6eofeez",
},
}
], - "next": [
- {
- "\"token\":\"<token>\"": null,
- "\"range\"": {
- "\"min\":\"05C1E30EA355AB\"": null,
- "\"max\":\"FE\"": null
}
}
]
}Downloads an artifact
Download an artifact from Docugami. The file content is returned as a base64-encoded string.
Authorizations:
Request Body schema: application/json
| projectId required | string The ID of the project the artifact belongs to. |
| version required | string The version of the artifact to retrieve. Use "latest" to get the latest version. |
| artifactId required | string The ID of the artifact to download. |
Responses
Request samples
- Payload
- download_artifact
{- "projectId": "string",
- "version": "1",
- "artifactId": "string"
}Response samples
- 200
"string"