Skip to main content
Glama
transkribus-mcp-server

transkribus-mcp-server

by lazyants

Export Collection

transkribus_coll_export
Read-onlyIdempotent

Start an export job for a Transkribus collection's documents, selecting PDF, TEI, DOCX, ALTO, PAGE XML, METS, images, or text outputs and configuring format-specific options.

Instructions

Start an export job for documents of a collection. Choose formats in commonPars and set format options in altoPars, pdfPars, teiPars or docxPars.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "collId": "<collId>"
    },
    "name": "transkribus_coll_export"
  }
}

Input Schema

NameRequiredDescriptionDefault
docsNoDocuments to export, each with an optional page selection
pagesNoPage range to export, e.g. "1-5,8"; all pages when omitted
collIdYesCollection ID
pdfParsNoPDF options
teiParsNoTEI options
altoParsNoALTO options
docxParsNoDOCX options
commonParsNoFormats and common options. Defaults: METS, images, PAGE XML and ALTO of the latest version

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed8 schema fields changedv4.2.0
    • addedInput schema / properties / altoPars
      Added value: +{
      +  "description": "ALTO options",
      +  "properties": {
      +    "altoVersion": {
      +      "enum": [
      +        "2.0",
      +        "4.0",
      +        "4.4"
      +      ],
      +      "type": "string"
      +    },
      +    "createAltov2": {
      +      "type": "boolean"
      +    },
      +    "exportStructureTags": {
      +      "type": "boolean"
      +    },
      +    "exportTextStyleTags": {
      +      "type": "boolean"
      +    },
      +    "splitIntoWordsInAltoXml": {
      +      "type": "boolean"
      +    },
      +    "useFilenameAsPageId": {
      +      "type": "boolean"
      +    }
      +  },
      +  "type": "object"
      +}
    • addedInput schema / properties / commonPars
      Added value: +{
      +  "description": "Formats and common options. Defaults: METS, images, PAGE XML and ALTO of the latest version",
      +  "properties": {
      +    "doBlackening": {
      +      "type": "boolean"
      +    },
      +    "doCreateTitle": {
      +      "type": "boolean"
      +    },
      +    "doExportAltoXml": {
      +      "description": "Export ALTO XML (options in altoPars)",
      +      "type": "boolean"
      +    },
      +    "doExportDocMetadata": {
      +      "description": "Export document metadata to metadata.xml",
      +      "type": "boolean"
      +    },
      +    "doExportPageXml": {
      +      "description": "Export PAGE XML",
      +      "type": "boolean"
      +    },
      +    "doExportSingleTxtFiles": {
      +      "description": "Export one TXT file per image",
      +      "type": "boolean"
      +    },
      +    "doIncludeImagesInXlsx": {
      +      "type": "boolean"
      +    },
      +    "doResume": {
      +      "type": "boolean"
      +    },
      +    "doWriteDocx": {
      +      "description": "Export DOCX (options in docxPars)",
      +      "type": "boolean"
      +    },
      +    "doWriteImages": {
      +      "description": "Export the image files",
      +      "type": "boolean"
      +    },
      +    "doWriteMets": {
      +      "description": "Write mets.xml (metadata, pagination)",
      +      "type": "boolean"
      +    },
      +    "doWriteOneTableForDoc": {
      +      "type": "boolean"
      +    },
      +    "doWriteOneTxt": {
      +      "description": "Export one TXT file per document",
      +      "type": "boolean"
      +    },
      +    "doWritePageMdXlsx": {
      +      "description": "Export page metadata to XLSX",
      +      "type": "boolean"
      +    },
      +    "doWritePdf": {
      +      "description": "Export PDF (options in pdfPars)",
      +      "type": "boolean"
      +    },
      +    "doWriteStructureInMets": {
      +      "description": "Add the logical structure to mets.xml",
      +      "type": "boolean"
      +    },
      +    "doWriteStructuresInXlsx": {
      +      "type": "boolean"
      +    },
      +    "doWriteStructuresRowBased": {
      +      "type": "boolean"
      +    },
      +    "doWriteTableSingleColumn": {
      +      "type": "boolean"
      +    },
      +    "doWriteTablesXlsx": {
      +      "description": "Export tables to XLSX",
      +      "type": "boolean"
      +    },
      +    "doWriteTagsIob": {
      +      "type": "boolean"
      +    },
      +    "doWriteTagsXlsx": {
      +      "type": "boolean"
      +    },
      +    "doWriteTei": {
      +      "description": "Export TEI (options in teiPars)",
      +      "type": "boolean"
      +    },
      +    "doWriteWordsIntoTable": {
      +      "type": "boolean"
      +    },
      +    "exportTranscriptMetadata": {
      +      "type": "boolean"
      +    },
      +    "fileNamePattern": {
      +      "type": "string"
      +    },
      +    "filterHiddenPages": {
      +      "type": "boolean"
      +    },
      +    "font": {
      +      "description": "Font of the text in PDF exports",
      +      "type": "string"
      +    },
      +    "hideUser": {
      +      "description": "How the uploader is anonymized in exported metadata",
      +      "enum": [
      +        "NULL",
      +        "NA",
      +        "HIDDEN"
      +      ],
      +      "type": "string"
      +    },
      +    "remoteImgQuality": {
      +      "description": "Which image derivative to export",
      +      "enum": [
      +        "orig",
      +        "browser",
      +        "view",
      +        "thumb",
      +        "scale50",
      +        "scale25",
      +        "bin"
      +      ],
      +      "type": "string"
      +    },
      +    "selectedTags": {
      +      "items": {
      +        "type": "string"
      +      },
      +      "type": "array"
      +    },
      +    "splitIntoWordsInAltoXml": {
      +      "type": "boolean"
      +    },
      +    "store2019PageXml": {
      +      "type": "boolean"
      +    },
      +    "storeValidPageXml": {
      +      "type": "boolean"
      +    },
      +    "structureTagNames": {
      +      "items": {
      +        "type": "string"
      +      },
      +      "type": "array"
      +    },
      +    "tableColumn": {
      +      "maximum": 9007199254740991,
      +      "minimum": -9007199254740991,
      +      "type": "integer"
      +    },
      +    "updatePageXmlImageDimensions": {
      +      "type": "boolean"
      +    },
      +    "useVersionStatus": {
      +      "description": "Transcript version to export, e.g. \"Latest\"",
      +      "type": "string"
      +    },
      +    "writeTextOnWordLevel": {
      +      "type": "boolean"
      +    }
      +  },
      +  "type": "object"
      +}
    • addedInput schema / properties / docs
      Added value: +{
      +  "description": "Documents to export, each with an optional page selection",
      +  "items": {
      +    "properties": {
      +      "docId": {
      +        "description": "Document ID",
      +        "exclusiveMinimum": 0,
      +        "maximum": 9007199254740991,
      +        "type": "integer"
      +      },
      +      "pageIds": {
      +        "description": "Page IDs; all pages when omitted",
      +        "items": {
      +          "exclusiveMinimum": 0,
      +          "maximum": 9007199254740991,
      +          "type": "integer"
      +        },
      +        "type": "array"
      +      }
      +    },
      +    "required": [
      +      "docId"
      +    ],
      +    "type": "object"
      +  },
      +  "type": "array"
      +}
    • addedInput schema / properties / docxPars
      Added value: +{
      +  "description": "DOCX options",
      +  "properties": {
      +    "doDocxExpandAbbrevs": {
      +      "type": "boolean"
      +    },
      +    "doDocxForcePageBreaks": {
      +      "type": "boolean"
      +    },
      +    "doDocxIgnoreSuppliedTag": {
      +      "type": "boolean"
      +    },
      +    "doDocxKeepAbbrevs": {
      +      "type": "boolean"
      +    },
      +    "doDocxMarkUnclear": {
      +      "type": "boolean"
      +    },
      +    "doDocxPreserveLineBreaks": {
      +      "type": "boolean"
      +    },
      +    "doDocxShowSuppliedTagWithBrackets": {
      +      "type": "boolean"
      +    },
      +    "doDocxSubstituteAbbrevs": {
      +      "type": "boolean"
      +    },
      +    "doDocxWithTags": {
      +      "type": "boolean"
      +    },
      +    "doDocxWriteFilenames": {
      +      "type": "boolean"
      +    }
      +  },
      +  "type": "object"
      +}
    • removedInput schema / properties / format
      Removed value: -{
      -  "description": "Export format (e.g. \"pdf\", \"docx\", \"tei\")",
      -  "type": "string"
      -}
    • changedInput schema / properties / pages / description
      Previous value: -"Page range to export (e.g. \"1-10\")"New value: +"Page range to export, e.g. \"1-5,8\"; all pages when omitted"
    • addedInput schema / properties / pdfPars
      Added value: +{
      +  "description": "PDF options",
      +  "properties": {
      +    "compressionLevel": {
      +      "description": "Stream compression and JPEG quality: 0 = fastest, 9 = smallest, -1 = default",
      +      "maximum": 9007199254740991,
      +      "minimum": -9007199254740991,
      +      "type": "integer"
      +    },
      +    "defaultLineHeight": {
      +      "maximum": 9007199254740991,
      +      "minimum": -9007199254740991,
      +      "type": "integer"
      +    },
      +    "doPdfA": {
      +      "type": "boolean"
      +    },
      +    "doPdfImagesOnly": {
      +      "type": "boolean"
      +    },
      +    "doPdfImagesPlusText": {
      +      "type": "boolean"
      +    },
      +    "doPdfTableStructure": {
      +      "type": "boolean"
      +    },
      +    "doPdfWithArticles": {
      +      "type": "boolean"
      +    },
      +    "doPdfWithTags": {
      +      "type": "boolean"
      +    },
      +    "doPdfWithTextPages": {
      +      "type": "boolean"
      +    },
      +    "doSinglePagePdfs": {
      +      "type": "boolean"
      +    },
      +    "doTableCellBorders": {
      +      "type": "boolean"
      +    },
      +    "doTagHighlightsInText": {
      +      "type": "boolean"
      +    },
      +    "doTagHighlightsOnImage": {
      +      "type": "boolean"
      +    },
      +    "doTagLegendPage": {
      +      "type": "boolean"
      +    },
      +    "doUseLinePolygons": {
      +      "type": "boolean"
      +    },
      +    "fullCompression": {
      +      "type": "boolean"
      +    },
      +    "imgMaxDpi": {
      +      "description": "Downscale embedded images to this DPI; 0 = off",
      +      "maximum": 9007199254740991,
      +      "minimum": -9007199254740991,
      +      "type": "integer"
      +    },
      +    "isAddImagePages": {
      +      "type": "boolean"
      +    },
      +    "pageNumberPosition": {
      +      "description": "Page number position, e.g. \"BC\" (bottom center); empty = none",
      +      "type": "string"
      +    },
      +    "pdfImgQuality": {
      +      "enum": [
      +        "orig",
      +        "browser",
      +        "view",
      +        "thumb",
      +        "scale50",
      +        "scale25",
      +        "bin"
      +      ],
      +      "type": "string"
      +    },
      +    "textPageLayout": {
      +      "enum": [
      +        "legacy",
      +        "compact"
      +      ],
      +      "type": "string"
      +    }
      +  },
      +  "type": "object"
      +}
    • addedInput schema / properties / teiPars
      Added value: +{
      +  "description": "TEI options",
      +  "properties": {
      +    "boundingBoxCoords": {
      +      "type": "boolean"
      +    },
      +    "combineContinuedTags": {
      +      "type": "boolean"
      +    },
      +    "exportPredefinedTagsAndAttsInTei": {
      +      "type": "boolean"
      +    },
      +    "lineBreakAtBeginningOfLine": {
      +      "type": "boolean"
      +    },
      +    "lineXmlIds": {
      +      "type": "boolean"
      +    },
      +    "lineZones": {
      +      "type": "boolean"
      +    },
      +    "linebreakType": {
      +      "type": "string"
      +    },
      +    "pbImageNameAsXmlId": {
      +      "type": "boolean"
      +    },
      +    "regionZones": {
      +      "type": "boolean"
      +    },
      +    "tokenizeWhitespace": {
      +      "type": "boolean"
      +    },
      +    "useAbElements": {
      +      "type": "boolean"
      +    },
      +    "useBoundingRects": {
      +      "type": "boolean"
      +    },
      +    "useRsTags": {
      +      "type": "boolean"
      +    },
      +    "useWordCoordinates": {
      +      "type": "boolean"
      +    },
      +    "useXslTransformation": {
      +      "description": "Build the TEI with the page2tei XSL transformation",
      +      "type": "boolean"
      +    },
      +    "withoutTextline": {
      +      "type": "boolean"
      +    },
      +    "wordZones": {
      +      "type": "boolean"
      +    }
      +  },
      +  "type": "object"
      +}
  2. First observedv2.1.1

TDQS

B3.3/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already cover the safety profile (readOnlyHint, idempotentHint, destructiveHint=false, openWorldHint), so the description's main added duty is job behavior. It says a job is 'started', but never says whether the call returns immediately with a job handle, whether the caller must poll or wait, whether credits are consumed, or what the default output bundle contains (that detail only appears buried in the commonPars schema description).

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, zero filler, and the core action is front-loaded before the configuration hint. Nothing is repeated or padded.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For an 8-parameter tool with four nested option objects and no output schema, the description is thin on lifecycle: no return shape, no job-status follow-up, no defaults. The configuration hint helps, but an agent still cannot tell from the description alone what happens after the call returns.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the schema already documents every parameter, including the 'PDF options'/'TEI options' groupings. The description's mapping of formats to commonPars and per-format options to altoPars/pdfPars/teiPars/docxPars reinforces that structure but adds little the schema does not already state (e.g. 'doWritePdf (options in pdfPars)').

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

Names a specific verb and resource ('Start an export job for documents of a collection'), which is clearly distinguishable from the collection-management siblings. It does not distinguish itself from the near-neighbor transkribus_doc_export, so the scope boundary is left implicit.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to use a collection export versus a single-document export, no stated prerequisites, and no mention of what to do after starting the job. The only steering given is which parameter groups hold format options, which is configuration rather than usage guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server

Other Tools