Docparser MCP integration for AI agents.
Connect AI agents to Docparser through 10 structured actions, including get document result, upload document by content, and fetch document from url. Review…
- ACTION CONTRACTS
- 10
- AUTHENTICATION
- API key
- SOURCE STATUS
- Provider-backed
CATALOG SOURCE REVIEWED AUGUST 23, 2026 / ACTION NAMES AND SCHEMAS DERIVED FROM WORKING MACHINES PROVIDER SOURCE
CAPABILITY PROFILE
What the Docparser integration exposes
The Docparser Agent App exposes 10 provider-backed actions for productivity and data work. Its current contract lets an authorized agent retrieve the parsed data of one docparser document. when child documents exist and are included, multiple result rows may be returned, upload a document to a docparser parser by sending base64-encoded file content and an optional file name, and queue a publicly accessible document url for import into a docparser parser and return the scheduled document metadata. These operations are called through Working Machines as typed capabilities rather than through browser navigation or copied UI steps.
A connection uses API key. Before execution, the agent can inspect the selected action, its required fields, declared scopes, and expected output contract. Provider credentials remain inside the Working Machines runtime; the calling agent receives the capability and its structured result, not the underlying secret.
For reliable operation, start with the narrowest action that satisfies the task, resolve stable provider identifiers before changing state, and validate the returned object or status after execution. Availability still depends on the connected Docparser account, granted provider permissions, workspace policy, region, plan, and upstream API behavior.
VERIFIED ACTION SAMPLE
Real Docparser capabilities.
Showing 10 of 10 actions. Risk labels are conservative signals based on operation names, not substitutes for provider documentation or runtime policy.
get_document_resultREADRetrieve the parsed data of one Docparser document. When child documents exist and are included, multiple result rows may be returned.
INPUTS: parserId / documentId / format / includeChildren
upload_document_by_contentWRITEUpload a document to a Docparser parser by sending base64-encoded file content and an optional file name.
INPUTS: parserId / contentBase64 / fileName / remoteId
fetch_document_from_urlREVIEWQueue a publicly accessible document URL for import into a Docparser parser and return the scheduled document metadata.
INPUTS: parserId / url / remoteId
get_document_statusREADRetrieve the import, preprocessing, parsing, and webhook-dispatch status of one Docparser document.
INPUTS: parserId / documentId
get_multiple_document_resultsREADRetrieve parsed data for multiple documents of a specific parser with optional filtering, pagination, queue inclusion, and sorting.
INPUTS: parserId / format / list / limit / date
get_parser_modelsREADList all model layouts for a specific Docparser parser.
INPUTS: parserId
list_parsersREADList all Document Parsers linked to the current Docparser account.
pingREVIEWPing the Docparser API to verify that the provided API key is valid.
reintegrate_documentsREVIEWSchedule one or more Docparser documents for the integration queue using their document IDs.
INPUTS: parserId / documentIds
reparse_documentsREVIEWSchedule one or more Docparser documents for re-parsing using their document IDs.
INPUTS: parserId / documentIds
INPUT CONTRACTS
Know what the action needs before it runs.
get_document_result
parserIdREQUIRED- The parser identifier that owns the document.
documentIdREQUIRED- The unique document identifier returned during import.
formatOPTIONAL- The output format for parsed data. `object` returns nested JSON and `flat` returns flattened key/value pairs.
includeChildrenOPTIONAL- Whether parsed data of child documents should also be returned.
upload_document_by_content
parserIdREQUIRED- The parser identifier to upload the document to.
contentBase64REQUIRED- The base64-encoded document content to upload.
fileNameOPTIONAL- The file name to attribute to the uploaded document.
remoteIdOPTIONAL- An optional passthrough ID that is stored with the document.
fetch_document_from_url
parserIdREQUIRED- The parser identifier to import the document into.
urlREQUIRED- The publicly accessible document URL to fetch.
remoteIdOPTIONAL- An optional passthrough ID that is stored with the fetched document.
get_document_status
parserIdOPTIONAL- The parser identifier that owns the document.
documentIdOPTIONAL- The unique document identifier returned during import.
PROVIDER-SPECIFIC WORKFLOWS
Jobs this Agent App can support
Inspect Get Document Result
Retrieve the parsed data of one Docparser document. When child documents exist and are included, multiple result rows may be returned. Use this as a bounded discovery step, retain the returned identifier, and avoid expanding the read beyond the task's stated scope.
get_document_resultControl Upload Document By Content
Upload a document to a Docparser parser by sending base64-encoded file content and an optional file name. Resolve the target first, present material changes for confirmation, and make retries idempotent where the provider supports it.
upload_document_by_contentVerify with Get Document Status
Retrieve the import, preprocessing, parsing, and webhook-dispatch status of one Docparser document. Compare the returned provider state with the intended outcome and preserve stable IDs or canonical links in the run record.
get_document_statusSAFETY BOUNDARY
Operate Docparser with explicit limits
- Authorize Docparser with API key and grant only the provider access required by the selected actions.
- 1 action is change-capable by name. Confirm the target identity and material parameters before allowing a write.
- Do not infer permission from catalog visibility. Workspace policy, connection identity, and upstream authorization still govern execution.
- No provider scope string is declared on the sampled actions. Verify the connected account's actual permissions in Docparser rather than assuming unrestricted access.
- After a call, inspect the structured result and execution record before reporting that the Docparser task completed successfully.
CONNECTION MODEL
API key
Docparser API key sent with the api_key header. Open your parser, go to More > Integrations, and copy the parser API key from the official integration settings.
Working Machines stores provider credentials behind the execution boundary. An agent can use an authorized connection identity, but catalog discovery alone does not reveal OAuth tokens, API keys, or provider secrets.
- READ SIGNALS
- 5
- WRITE SIGNALS
- 1
- HIGH IMPACT
- 0
- REVIEW SIGNALS
- 4
EVIDENCE AND AVAILABILITY
Provider reference
Action names, input fields, authentication types, and counts on this page are generated from the Working Machines provider catalog. Provider behavior, quotas, object semantics, account eligibility, and regional availability remain governed by Docparser.