Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

io.github.lazyants/transkribus

NPM · @LAZYANTS/TRANSKRIBUS-MCP-SERVER · SCANNED SEP 21

MCP server for the Transkribus REST API — collections, documents, HTR/OCR, and models.

−2 this week 90 Trust /100
Trust breakdown (7 categories)

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. How we score → Why this is hard to score →

Supply Chain Security99
  • No malware found by supply-chain analysis.Pass
  • No known CVEs affecting this package version or its production dependencies.Pass
  • No install/post-install scripts declared.Pass
  • 34 of 121 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency87
  • Source repository is publicly reachable at the declared URL. View diagnostics → Pass
  • Cryptographically verified build provenance (signed, bound to lazyants/transkribus-mcp-server). View diagnostics → Pass
  • License check failed: the license (FSL-1.1-MIT) isn't a recognized OSI-approved license. See how to fix → Fail
  • Actively maintained (last published 13 days ago).Pass
  • Publishes a security disclosure policy (SECURITY.md).Pass
Schema Quality & AI Usability79
  • 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
  • AI-judged instruction clarity (good).Pass
  • Tool/resource definitions use about 22100 tokens (~72/item across 305 items; 304 tools + 1 resources), lean.Pass
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management78
  • Stability check failed: the tool surface changed between 3.1.0 and 4.0.0: 3 tool removals, 5 breaking changes, 7 additions. See how to fix → Fail
Tool Coverage100
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 100% of tool parameters carry a description.Pass
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • All 29 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.Pass
  • An AI judge read all 305 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Install

How do I install the io.github.lazyants/transkribus MCP server?

io.github.lazyants/transkribus runs locally as an npm package, launched with npx -y @lazyants/transkribus-mcp-server. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

npm · @lazyants/transkribus-mcp-server

# add to Claude Code
claude mcp add lazyants-transkribus -- npx -y @lazyants/transkribus-mcp-server
// .cursor/mcp.json
{
  "mcpServers": {
    "lazyants-transkribus": {
      "command": "npx",
      "args": [
        "-y",
        "@lazyants/transkribus-mcp-server"
      ]
    }
  }
}
// .vscode/mcp.json
{
  "servers": {
    "lazyants-transkribus": {
      "command": "npx",
      "args": [
        "-y",
        "@lazyants/transkribus-mcp-server"
      ]
    }
  }
}
# add to Codex CLI
codex mcp add lazyants-transkribus -- npx -y @lazyants/transkribus-mcp-server
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "lazyants-transkribus": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "@lazyants/transkribus-mcp-server"
      ],
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add lazyants-transkribus --command npx --arg -y --arg @lazyants/transkribus-mcp-server
# ~/.hermes/config.yaml
mcp_servers:
  lazyants-transkribus:
    command: "npx"
    args: ["-y", "@lazyants/transkribus-mcp-server"]
// ~/.netclaw/config/netclaw.json
{
  "McpServers": {
    "lazyants-transkribus": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "@lazyants/transkribus-mcp-server"
      ]
    }
  }
}
# add to Vellum
assistant mcp add lazyants-transkribus -t stdio -c npx -a -y @lazyants/transkribus-mcp-server
// mcp.json
{
  "mcpServers": {
    "lazyants-transkribus": {
      "command": "npx",
      "args": [
        "-y",
        "@lazyants/transkribus-mcp-server"
      ]
    }
  }
}
Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 20 Sept 26 −3

    No change was recorded against any check on this day. Stability & Change Management went from 98 to 75.

  • 18 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 92 to 95.

  • 17 Sept 26 −1

    No change was recorded against any check on this day. Stability & Change Management went from 98 to 92.

  • 16 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 95 to 98. Other categories moved too: Supply Chain Security rose 1.

  • 14 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 88 to 92.

  • 13 Sept 26 +1
    • Security disclosure: unverified → pass functional
  • 12 Sept 26 −1
    • Security disclosure: pass → unverified functional
  • 11 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 78 to 82.

Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 21 Sept 2026 · Analysed npm/@lazyants/transkribus-mcp-server@4.0.0

Provenance Verified

A signed build attestation was found and verified, binding this exact artifact to the source repository it claims to come from.

Result Verified
Ecosystem npm
Reason Verified
Discovered via Registry attestation endpoint
Source repo lazyants/transkribus-mcp-server
Certificate issuer https://token.actions.githubusercontent.com
Certificate SAN https://github.com/lazyants/transkribus-mcp-server/.github/workflows/publish-registry.yml@refs/tags/v4.0.0
Rekor log index 2753144926
Predicate type https://slsa.dev/provenance/v1
Subject digest sha512:43f92d3b9bec78141b1426bda49500c4362390f20c165ee96cd614531b966bdef3c28e086fbefbdebb582ae8f9be9324e28faa65c18be0acb3272df5f

Background: How many MCP packages publish verified provenance →

Dependencies 121 packages
Packages resolved 121
Stale 34
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 304 exposed · ~22,073 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
transkribus_page_get ~49

Get details of a specific page in a document.

NameTypeReqDescription
collIdintegeryesCollection ID
idintegeryesDocument ID
pageintegeryesPage number

No output schema declared.

No examples provided.

transkribus_page_get_curr_transcript ~50

Get the current transcript for a page.

NameTypeReqDescription
collIdintegeryesCollection ID
idintegeryesDocument ID
pageintegeryesPage number

No output schema declared.

No examples provided.

transkribus_page_get_image ~127

Return the scanned image of a page as an image content block, so a multimodal client can read the manuscript itself. Defaults to the thumbnail and a 5000000-byte cap; ask for size "full" to get the full-resolution scan.

NameTypeReqDescription
collIdintegeryesCollection ID
idintegeryesDocument ID
maxBytesintegerReject an image larger than this many bytes (default 5000000)
pageintegeryesPage number
sizestringWhich image to fetch (default "thumb")

No output schema declared.

No examples provided.

transkribus_page_get_metadata ~47

Get metadata for a specific page.

NameTypeReqDescription
collIdintegeryesCollection ID
idintegeryesDocument ID
pageintegeryesPage number

No output schema declared.

No examples provided.

transkribus_page_get_plaintext ~51

Get the plain text content of a page transcript.

NameTypeReqDescription
collIdintegeryesCollection ID
idintegeryesDocument ID
pageintegeryesPage number

No output schema declared.

No examples provided.

transkribus_page_get_text ~49

Get the transcript text for a specific page.

NameTypeReqDescription
collIdintegeryesCollection ID
idintegeryesDocument ID
pageintegeryesPage number

No output schema declared.

No examples provided.

transkribus_page_get_transcript ~60

Get a specific transcript version for a page.

NameTypeReqDescription
collIdintegeryesCollection ID
idintegeryesDocument ID
pageintegeryesPage number
transcriptIdintegeryesTranscript ID

No output schema declared.

No examples provided.

transkribus_page_is_locked ~48

Check if a page is currently locked.

NameTypeReqDescription
collIdintegeryesCollection ID
idintegeryesDocument ID
pageintegeryesPage number

No output schema declared.

No examples provided.

transkribus_page_list_locks ~48

List all locks on a page.

NameTypeReqDescription
collIdintegeryesCollection ID
idintegeryesDocument ID
pageintegeryesPage number

No output schema declared.

No examples provided.

transkribus_page_list_transcripts ~102

List all transcript versions for a page.

NameTypeReqDescription
collIdintegeryesCollection ID
idintegeryesDocument ID
indexintegerStart index (0-based)
nValuesintegerNumber of results (-1 for all)
pageintegeryesPage number
sortColumnstringColumn to sort by
sortDirectionstringSort direction (asc/desc)

No output schema declared.

No examples provided.

transkribus_page_lock ~67

Lock or unlock a page for editing.

NameTypeReqDescription
collIdintegeryesCollection ID
idintegeryesDocument ID
pageintegeryesPage number
typebooleanWhether to lock (true) or unlock (false) the page

No output schema declared.

No examples provided.

transkribus_page_move ~106

Move a page to a different position within the document or to another document.

NameTypeReqDescription
collIdintegeryesCollection ID
idintegeryesDocument ID
moveTointegeryesTarget position to move the page to
moveToDocIdintegerTarget document ID to move the page to
nrIsPageIdbooleanTreat page nr as page ID (default false)
pageintegeryesPage number

No output schema declared.

No examples provided.

transkribus_page_post_transcript ~118

Post a new transcript for a page.

NameTypeReqDescription
bodyobjectTranscript data
collIdintegeryesCollection ID
idintegeryesDocument ID
notestringNote for the transcript
nrIsPageIdbooleanTreat page nr as page ID
pageintegeryesPage number
parentintegerParent transcript ID
statusstringTranscript status
toolNamestringTool name that created the transcript

No output schema declared.

No examples provided.

transkribus_page_replace ~47

Replace a page image in a document.

NameTypeReqDescription
collIdintegeryesCollection ID
idintegeryesDocument ID
pageintegeryesPage number

No output schema declared.

No examples provided.

transkribus_page_update_hide_on_sites ~96

Set whether a page is hidden on public sites.

NameTypeReqDescription
collIdintegeryesCollection ID
hidebooleanyesWhether to hide the page on sites
hideOnSitesbooleanWhether to hide on sites
idintegeryesDocument ID
nrIsPageIdbooleanTreat page nr as page ID
pageintegeryesPage number

No output schema declared.

No examples provided.

transkribus_page_update_status_v2 ~106

Update page status using transcript ID (alternative endpoint).

NameTypeReqDescription
bodyobjectStatus update data
collIdintegeryesCollection ID
idintegeryesDocument ID
notestringStatus note
nrIsPageIdbooleanTreat page nr as page ID
pageintegeryesPage number
statusstringNew status
transcriptIdintegeryesTranscript ID

No output schema declared.

No examples provided.

transkribus_page_update_transcript_status ~96

Update the status of a specific transcript version.

NameTypeReqDescription
collIdintegeryesCollection ID
idintegeryesDocument ID
notestringStatus note
nrIsPageIdbooleanTreat page nr as page ID
pageintegeryesPage number
statusstringyesNew transcript status
transcriptIdintegeryesTranscript ID

No output schema declared.

No examples provided.

transkribus_processing_get_alto_xml ~53

Get a finished Processing API result as ALTO v4 XML. Returns 404 while the job is still running.

NameTypeReqDescription
processIdintegeryesProcess ID returned when the image was submitted

No output schema declared.

No examples provided.

transkribus_processing_get_page_xml ~58

Get a finished Processing API result as PAGE XML (version 2013-07-15). Returns 404 while the job is still running.

NameTypeReqDescription
processIdintegeryesProcess ID returned when the image was submitted

No output schema declared.

No examples provided.

transkribus_processing_get_status ~70

Get the status of a Processing API job, including the recognised text once it has finished. Status is one of CREATED, WAITING, RUNNING, FINISHED or FAILED; results are kept for two days.

NameTypeReqDescription
processIdintegeryesProcess ID returned when the image was submitted

No output schema declared.

No examples provided.

transkribus_processing_submit_image ~105

Submit a single image to the Transkribus Processing API for text recognition and get back a process ID. Supply exactly one of imageUrl or base64 (JPEG, TIFF or PNG, up to 20 MB).

NameTypeReqDescription
configobjectyesHow the image should be processed
contentobjectExisting regions and lines. When supplied, line detection is skipped.
imageyesThe image to process: exactly one of imageUrl or base64

No output schema declared.

No examples provided.

transkribus_pylaia_recognize ~343

Run PyLaia HTR recognition on a document using a specific model.

NameTypeReqDescription
allowConcurrentExecutionbooleanAllow concurrent execution (default false)
b2pBackendstringBaseline to polygon backend (default "Legacy")
batchSizeintegerBatch size (default 10)
clearLinesbooleanClear existing lines before recognition
collIdintegeryesCollection ID
creditsstringCredits parameter
doLinePolygonSimplificationbooleanSimplify line polygons (default true)
doNotDeleteWorkDirbooleanDo not delete working directory
doStructuresstringStructure analysis mode
doWordSegbooleanPerform word segmentation
docIdintegeryesDocument ID
keepOriginalLinePolygonsbooleanKeep original line polygons (default false)
languageModelstringLanguage model to use
modelIdintegeryesModel/HTR ID
nBestintegerNumber of best results (default 1)
pagesstringPage range (e.g. "1-5")
printedLanguageModelstringLanguage model for printed text
printedModelIdintegerPrinted text model ID
useExistingLinePolygonsbooleanUse existing line polygons (default false)
writeKwsIndexbooleanWrite KWS index (default false)
writeLineConfScorebooleanWrite line confidence scores
writeWordConfScoresbooleanWrite word confidence scores

No output schema declared.

No examples provided.

transkribus_pylaia_train ~689

Start PyLaia HTR model training for a collection. By default, sends training parameters matching the Transkribus UI defaults (textFeatsCfg with TextFeats preprocessing, use_masked_conv=True, max_epochs=100). Without these defaults, the server uses different preprocessing (trpPreprocPars) which produces significantly worse models. Set noTrainingDefaults=true to send no training parameters (server defaults).

NameTypeReqDescription
baseModelIdintegerBase model ID for transfer learning
batch_sizeintegerBatch size (default: 24). Shortcut for trainCtcPars --batch_size.
collIdintegeryesCollection ID
createModelParsobjectModel architecture parameters as key-value pairs (e.g. {"--rnn_units": "512"}). Merged with UI defaults (use_masked_conv=True, cnn_poolsize="2 2 0 2", etc.). Only specify parameters you want to overr…
customAbbrevsTrainingbooleanEnable custom abbreviations training
customTagTrainingbooleanEnable custom tag training
descriptionstringDescription of the model
imgTypestringImage type
languagestringLanguage code (e.g. "rus", "deu", "eng")
learning_ratenumberLearning rate (default: 3.0E-4). Shortcut for trainCtcPars --learning_rate.
max_epochsintegerMaximum training epochs (default: 100). Shortcut for trainCtcPars --max_epochs.
max_nondecreasing_epochsintegerEarly stopping patience (default: 20). Shortcut for trainCtcPars --max_nondecreasing_epochs.
modelNamestringName for the new model
noTrainingDefaultsbooleanIf true, do NOT apply UI-default training parameters. The server will use its own defaults (which differ from the UI and may produce worse models).
omitLinesByTagarrayTags of lines to omit from training
providerstringTraining provider (default: "PyLaia")
reverseTextbooleanWhether to reverse text direction
testListarrayTest page list
testListFilestringAbsolute path to JSON file containing test page list array of {docId, pageId} objects. Example: /tmp/transkribus-training/test_list.json
textFeatsCfgobjectTextFeats preprocessing config override. Merged with UI defaults (normheight=64, deslope/deslant=true, enh=true). Only specify fields you want to change.
trainCtcParsobjectCTC training parameters as key-value pairs (e.g. {"--max_epochs": "200"}). Merged with UI defaults (max_epochs=100, learning_rate=3.0E-4, batch_size=24, etc.). Only specify parameters you want to ove…
trainListarrayTraining page list
trainListFilestringAbsolute path to JSON file containing training page list array of {docId, pageId} objects. Example: /tmp/transkribus-training/train_list.json
trainPropertiesbooleanEnable training properties

No output schema declared.

No examples provided.

transkribus_recog_add_to_collection ~58

Add a recognition model to another collection.

NameTypeReqDescription
collIdintegeryesCollection ID
idintegeryesResource ID
targetCollIdintegeryesTarget collection ID to add the model to

No output schema declared.

No examples provided.

transkribus_recog_compute_error_rate ~60

Compute the error rate for a model in a collection.

NameTypeReqDescription
bodyobjectAdditional error rate computation parameters
collIdintegeryesCollection ID
modelIdintegeryesModel/HTR ID

No output schema declared.

No examples provided.

transkribus_recog_compute_sample ~44

Compute a recognition sample for a document in a collection.

NameTypeReqDescription
collIdintegeryesCollection ID
docIdintegeryesDocument ID

No output schema declared.

No examples provided.

transkribus_recog_compute_wer ~90

Compute the Word Error Rate for a document.

NameTypeReqDescription
collIdintegeryesCollection ID
docIdintegeryesDocument ID
hypstringHypothesis transcript identifier
keystringTranscript key
pagesstringPage range (e.g. "1-5")
refstringReference transcript identifier

No output schema declared.

No examples provided.

transkribus_recog_compute_wer_tasas ~96

Compute the Word Error Rate using TASAS method for a document.

NameTypeReqDescription
collIdintegeryesCollection ID
docIdintegeryesDocument ID
hypstringHypothesis transcript identifier
keystringTranscript key
pagesstringPage range (e.g. "1-5")
refstringReference transcript identifier

No output schema declared.

No examples provided.

transkribus_recog_delete ~39

Delete a recognition model from a collection.

NameTypeReqDescription
collIdintegeryesCollection ID
idintegeryesResource ID

No output schema declared.

No examples provided.

transkribus_recog_get ~41

Get details of a recognition model in a collection.

NameTypeReqDescription
collIdintegeryesCollection ID
idintegeryesResource ID

No output schema declared.

No examples provided.

transkribus_recog_get_add_info ~43

Get information about adding a recognition model to collections.

NameTypeReqDescription
collIdintegeryesCollection ID
idintegeryesResource ID

No output schema declared.

No examples provided.

transkribus_recog_get_atr ~26

Retrieve information about available ATR (Automatic Text Recognition) models.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

transkribus_recog_get_costs ~77

Get the cost information for a recognition model.

NameTypeReqDescription
collIdintegeryesCollection ID
creditsstringCredits parameter
idintegeryesResource ID
nrOfPagesintegerNumber of pages
writeKwsIndexbooleanWrite KWS index

No output schema declared.

No examples provided.

transkribus_recog_get_error_rate ~65

Get the error rate for a collection or model.

NameTypeReqDescription
collIdintegerCollection ID
keystringKey identifier
modelIdintegerModel/HTR ID
refstringReference identifier

No output schema declared.

No examples provided.

transkribus_recog_get_ocr_costs ~98

Get the estimated OCR costs for a document.

NameTypeReqDescription
collIdintegeryesCollection ID
doBlockSegOnlybooleanOnly do block segmentation
docIdintegeryesDocument ID
idintegerModel ID
nrOfPagesintegerNumber of pages
pagesstringPage range
typestringOCR type

No output schema declared.

No examples provided.

transkribus_recog_get_test_set ~56

Get the test set data for a recognition model.

NameTypeReqDescription
collIdintegeryesCollection ID
idintegeryesResource ID
nrOfTranscriptsintegerNumber of transcripts

No output schema declared.

No examples provided.

transkribus_recog_get_train_data ~69

Get the training data for a recognition model.

NameTypeReqDescription
collIdintegeryesCollection ID
idintegeryesResource ID
indexintegerStart index (0-based)
nValuesintegerNumber of results (-1 for all)

No output schema declared.

No examples provided.

transkribus_recog_get_train_set ~55

Get the training set for a recognition model.

NameTypeReqDescription
collIdintegeryesCollection ID
idintegeryesResource ID
nrOfTranscriptsintegerNumber of transcripts

No output schema declared.

No examples provided.

transkribus_recog_get_validation_gt_by_htr ~73

Get validation ground truth data for a recognition model.

NameTypeReqDescription
collIdintegeryesCollection ID
idintegeryesResource ID
indexintegerStart index (0-based)
nValuesintegerNumber of results (-1 for all)

No output schema declared.

No examples provided.

transkribus_recog_list_by_collection ~96

List recognition models available in a specific collection.

NameTypeReqDescription
collIdintegeryesCollection ID
indexintegerStart index (0-based)
nValuesintegerNumber of results (-1 for all)
provstringFilter by provider
sortColumnstringColumn to sort by
sortDirectionstringSort direction: asc or desc

No output schema declared.

No examples provided.

transkribus_recog_list_collections ~43

List collections that have access to a recognition model.

NameTypeReqDescription
collIdintegeryesCollection ID
idintegeryesResource ID

No output schema declared.

No examples provided.

transkribus_recog_list_dicts ~20

List available dictionaries for recognition.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

transkribus_recog_list_models ~130

List available recognition models with optional filtering.

NameTypeReqDescription
collIdintegerFilter by collection ID
filterstringFilter string
indexintegerStart index (0-based)
nValuesintegerNumber of results (-1 for all)
provstringFilter by provider (alternative)
providerstringFilter by model provider
releaseLevelintegerFilter by release level
sortColumnstringColumn to sort by
sortDirectionstringSort direction: asc or desc

No output schema declared.

No examples provided.

transkribus_recog_remove_from_collection ~41

Remove a recognition model from a collection.

NameTypeReqDescription
collIdintegeryesCollection ID
idintegeryesResource ID

No output schema declared.

No examples provided.

transkribus_recog_run_atr ~68

Run Automatic Text Recognition on a document or specific pages.

NameTypeReqDescription
collIdintegeryesCollection ID
docIdintegeryesDocument ID
modelIdintegerModel/HTR ID
pageNrintegerPage number

No output schema declared.

No examples provided.

transkribus_recog_run_htr_citlab ~189

Run CITlab HTR recognition on a document using a specific model.

NameTypeReqDescription
allowConcurrentExecutionbooleanAllow concurrent execution (default false)
collIdintegeryesCollection ID
creditsstringCredits parameter
dictstringDictionary to use
doLinePolygonSimplificationbooleanSimplify line polygons (default true)
doStoreConfMatsbooleanStore confidence matrices (default true)
doStructuresbooleanRun structure analysis
docIdintegeryesDocument ID
keepOriginalLinePolygonsbooleanKeep original line polygons (default false)
modelIdintegeryesModel/HTR ID
pagesstringPage range (e.g. "1-5")
tempDictstringTemporary dictionary

No output schema declared.

No examples provided.

transkribus_recog_run_ocr ~126

Run OCR on a document or specific pages in a collection.

NameTypeReqDescription
collIdintegeryesCollection ID
doBlockSegOnlybooleanOnly do block segmentation (default false)
docIdintegeryesDocument ID
idintegerModel ID
languagestringLanguage for OCR
ocrTypestringOCR type (default "Legacy")
pagesstringPage range (e.g. "1-5")
typeFacestringType face for OCR

No output schema declared.

No examples provided.

transkribus_recog_run_trhtr ~169

Run TRHTR recognition using a specific model in a collection.

NameTypeReqDescription
allowConcurrentExecutionbooleanAllow concurrent execution
b2pBackendstringB2P backend type
collIdintegeryesCollection ID
creditsstringCredits parameter
doLinePolygonSimplificationbooleanSimplify line polygons
doNotDeleteWorkDirbooleanDo not delete work directory
idintegerDocument ID
modelIdintegeryesModel/HTR ID
modelNamestringModel name
pagesstringPage range (e.g. "1-5")
useExistingLinePolygonsbooleanUse existing line polygons

No output schema declared.

No examples provided.

transkribus_recog_text2image ~86

Run Text2Image alignment using a specific model in a collection.

NameTypeReqDescription
bodyobjectyesText2Image parameters
collIdintegeryesCollection ID
creditsstringCredits parameter
doNotDeleteWorkDirbooleanDo not delete work directory
modelIdintegeryesModel/HTR ID

No output schema declared.

No examples provided.

transkribus_recog_text2image_citlab ~50

Run CITlab Text2Image alignment for a collection.

NameTypeReqDescription
bodyobjectyesText2Image configuration parameters
collIdintegeryesCollection ID

No output schema declared.

No examples provided.

Common questions

What is the io.github.lazyants/transkribus MCP server?

io.github.lazyants/transkribus is an MCP server listed in the public MCP registry as io.github.lazyants/transkribus. MCP server for the Transkribus REST API, collections, documents, HTR/OCR, and models. This page covers its npm package (@lazyants/transkribus-mcp-server).

Is the io.github.lazyants/transkribus MCP server safe to use?

io.github.lazyants/transkribus scores 90 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 21 September 2026. It declares no install or post-install scripts. Its build provenance is signed and verified. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the io.github.lazyants/transkribus MCP server expose?

io.github.lazyants/transkribus exposes 304 tools: transkribus_auth_check_session, transkribus_auth_get_details, transkribus_auth_invalidate, transkribus_auth_logout, transkribus_auth_refresh, and 299 more. Their descriptions and schemas cost roughly 22,073 tokens of context every time the server is loaded.

Is the io.github.lazyants/transkribus MCP server still maintained?

io.github.lazyants/transkribus is still listed as active in the MCP registry. We last reached this channel on 21 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

What licence is the io.github.lazyants/transkribus MCP server under?

io.github.lazyants/transkribus declares the FSL-1.1-MIT licence, which is not on the OSI-approved list. Read the terms before using it at work, and note this covers the source only, not the cost of any service it calls.