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.
Available components
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
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
claude mcp add lazyants-transkribus -- npx -y @lazyants/transkribus-mcp-server
{
"mcpServers": {
"lazyants-transkribus": {
"command": "npx",
"args": [
"-y",
"@lazyants/transkribus-mcp-server"
]
}
}
} {
"servers": {
"lazyants-transkribus": {
"command": "npx",
"args": [
"-y",
"@lazyants/transkribus-mcp-server"
]
}
}
} codex mcp add lazyants-transkribus -- npx -y @lazyants/transkribus-mcp-server
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"lazyants-transkribus": {
"type": "local",
"command": [
"npx",
"-y",
"@lazyants/transkribus-mcp-server"
],
"enabled": true
}
}
} openclaw mcp add lazyants-transkribus --command npx --arg -y --arg @lazyants/transkribus-mcp-server
mcp_servers:
lazyants-transkribus:
command: "npx"
args: ["-y", "@lazyants/transkribus-mcp-server"] {
"McpServers": {
"lazyants-transkribus": {
"Transport": "stdio",
"Command": "npx",
"Arguments": [
"-y",
"@lazyants/transkribus-mcp-server"
]
}
}
} assistant mcp add lazyants-transkribus -t stdio -c npx -a -y @lazyants/transkribus-mcp-server
{
"mcpServers": {
"lazyants-transkribus": {
"command": "npx",
"args": [
"-y",
"@lazyants/transkribus-mcp-server"
]
}
}
} 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.
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 →
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 →
transkribus_page_get Get Page ~49
Get details of a specific page in a document.
| Name | Type | Req | Description |
|---|---|---|---|
| collId | integer | yes | Collection ID |
| id | integer | yes | Document ID |
| page | integer | yes | Page number |
No output schema declared.
No examples provided.
transkribus_page_get_curr_transcript Get Current Transcript ~50
Get the current transcript for a page.
| Name | Type | Req | Description |
|---|---|---|---|
| collId | integer | yes | Collection ID |
| id | integer | yes | Document ID |
| page | integer | yes | Page number |
No output schema declared.
No examples provided.
transkribus_page_get_image Get Page 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.
| Name | Type | Req | Description |
|---|---|---|---|
| collId | integer | yes | Collection ID |
| id | integer | yes | Document ID |
| maxBytes | integer | – | Reject an image larger than this many bytes (default 5000000) |
| page | integer | yes | Page number |
| size | string | – | Which image to fetch (default "thumb") |
No output schema declared.
No examples provided.
transkribus_page_get_metadata Get Page Metadata ~47
Get metadata for a specific page.
| Name | Type | Req | Description |
|---|---|---|---|
| collId | integer | yes | Collection ID |
| id | integer | yes | Document ID |
| page | integer | yes | Page number |
No output schema declared.
No examples provided.
transkribus_page_get_plaintext Get Page Plaintext ~51
Get the plain text content of a page transcript.
| Name | Type | Req | Description |
|---|---|---|---|
| collId | integer | yes | Collection ID |
| id | integer | yes | Document ID |
| page | integer | yes | Page number |
No output schema declared.
No examples provided.
transkribus_page_get_text Get Page Text (Transcript) ~49
Get the transcript text for a specific page.
| Name | Type | Req | Description |
|---|---|---|---|
| collId | integer | yes | Collection ID |
| id | integer | yes | Document ID |
| page | integer | yes | Page number |
No output schema declared.
No examples provided.
transkribus_page_get_transcript Get Page Transcript ~60
Get a specific transcript version for a page.
| Name | Type | Req | Description |
|---|---|---|---|
| collId | integer | yes | Collection ID |
| id | integer | yes | Document ID |
| page | integer | yes | Page number |
| transcriptId | integer | yes | Transcript ID |
No output schema declared.
No examples provided.
transkribus_page_is_locked Check Page Lock ~48
Check if a page is currently locked.
| Name | Type | Req | Description |
|---|---|---|---|
| collId | integer | yes | Collection ID |
| id | integer | yes | Document ID |
| page | integer | yes | Page number |
No output schema declared.
No examples provided.
transkribus_page_list_locks List Page Locks ~48
List all locks on a page.
| Name | Type | Req | Description |
|---|---|---|---|
| collId | integer | yes | Collection ID |
| id | integer | yes | Document ID |
| page | integer | yes | Page number |
No output schema declared.
No examples provided.
transkribus_page_list_transcripts List Page Transcripts ~102
List all transcript versions for a page.
| Name | Type | Req | Description |
|---|---|---|---|
| collId | integer | yes | Collection ID |
| id | integer | yes | Document ID |
| index | integer | – | Start index (0-based) |
| nValues | integer | – | Number of results (-1 for all) |
| page | integer | yes | Page number |
| sortColumn | string | – | Column to sort by |
| sortDirection | string | – | Sort direction (asc/desc) |
No output schema declared.
No examples provided.
transkribus_page_lock Lock/Unlock Page ~67
Lock or unlock a page for editing.
| Name | Type | Req | Description |
|---|---|---|---|
| collId | integer | yes | Collection ID |
| id | integer | yes | Document ID |
| page | integer | yes | Page number |
| type | boolean | – | Whether to lock (true) or unlock (false) the page |
No output schema declared.
No examples provided.
transkribus_page_move Move Page ~106
Move a page to a different position within the document or to another document.
| Name | Type | Req | Description |
|---|---|---|---|
| collId | integer | yes | Collection ID |
| id | integer | yes | Document ID |
| moveTo | integer | yes | Target position to move the page to |
| moveToDocId | integer | – | Target document ID to move the page to |
| nrIsPageId | boolean | – | Treat page nr as page ID (default false) |
| page | integer | yes | Page number |
No output schema declared.
No examples provided.
transkribus_page_post_transcript Post Page Transcript ~118
Post a new transcript for a page.
| Name | Type | Req | Description |
|---|---|---|---|
| body | object | – | Transcript data |
| collId | integer | yes | Collection ID |
| id | integer | yes | Document ID |
| note | string | – | Note for the transcript |
| nrIsPageId | boolean | – | Treat page nr as page ID |
| page | integer | yes | Page number |
| parent | integer | – | Parent transcript ID |
| status | string | – | Transcript status |
| toolName | string | – | Tool name that created the transcript |
No output schema declared.
No examples provided.
transkribus_page_replace Replace Page ~47
Replace a page image in a document.
| Name | Type | Req | Description |
|---|---|---|---|
| collId | integer | yes | Collection ID |
| id | integer | yes | Document ID |
| page | integer | yes | Page number |
No output schema declared.
No examples provided.
transkribus_page_update_hide_on_sites Update Page Visibility ~96
Set whether a page is hidden on public sites.
| Name | Type | Req | Description |
|---|---|---|---|
| collId | integer | yes | Collection ID |
| hide | boolean | yes | Whether to hide the page on sites |
| hideOnSites | boolean | – | Whether to hide on sites |
| id | integer | yes | Document ID |
| nrIsPageId | boolean | – | Treat page nr as page ID |
| page | integer | yes | Page number |
No output schema declared.
No examples provided.
transkribus_page_update_status_v2 Update Page Status v2 ~106
Update page status using transcript ID (alternative endpoint).
| Name | Type | Req | Description |
|---|---|---|---|
| body | object | – | Status update data |
| collId | integer | yes | Collection ID |
| id | integer | yes | Document ID |
| note | string | – | Status note |
| nrIsPageId | boolean | – | Treat page nr as page ID |
| page | integer | yes | Page number |
| status | string | – | New status |
| transcriptId | integer | yes | Transcript ID |
No output schema declared.
No examples provided.
transkribus_page_update_transcript_status Update Transcript Status ~96
Update the status of a specific transcript version.
| Name | Type | Req | Description |
|---|---|---|---|
| collId | integer | yes | Collection ID |
| id | integer | yes | Document ID |
| note | string | – | Status note |
| nrIsPageId | boolean | – | Treat page nr as page ID |
| page | integer | yes | Page number |
| status | string | yes | New transcript status |
| transcriptId | integer | yes | Transcript ID |
No output schema declared.
No examples provided.
transkribus_processing_get_alto_xml Get Processing Result as ALTO XML ~53
Get a finished Processing API result as ALTO v4 XML. Returns 404 while the job is still running.
| Name | Type | Req | Description |
|---|---|---|---|
| processId | integer | yes | Process ID returned when the image was submitted |
No output schema declared.
No examples provided.
transkribus_processing_get_page_xml Get Processing Result as PAGE XML ~58
Get a finished Processing API result as PAGE XML (version 2013-07-15). Returns 404 while the job is still running.
| Name | Type | Req | Description |
|---|---|---|---|
| processId | integer | yes | Process ID returned when the image was submitted |
No output schema declared.
No examples provided.
transkribus_processing_get_status Get Processing 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.
| Name | Type | Req | Description |
|---|---|---|---|
| processId | integer | yes | Process ID returned when the image was submitted |
No output schema declared.
No examples provided.
transkribus_processing_submit_image Submit Image for Processing ~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).
| Name | Type | Req | Description |
|---|---|---|---|
| config | object | yes | How the image should be processed |
| content | object | – | Existing regions and lines. When supplied, line detection is skipped. |
| image | – | yes | The image to process: exactly one of imageUrl or base64 |
No output schema declared.
No examples provided.
transkribus_pylaia_recognize Run PyLaia Recognition ~343
Run PyLaia HTR recognition on a document using a specific model.
| Name | Type | Req | Description |
|---|---|---|---|
| allowConcurrentExecution | boolean | – | Allow concurrent execution (default false) |
| b2pBackend | string | – | Baseline to polygon backend (default "Legacy") |
| batchSize | integer | – | Batch size (default 10) |
| clearLines | boolean | – | Clear existing lines before recognition |
| collId | integer | yes | Collection ID |
| credits | string | – | Credits parameter |
| doLinePolygonSimplification | boolean | – | Simplify line polygons (default true) |
| doNotDeleteWorkDir | boolean | – | Do not delete working directory |
| doStructures | string | – | Structure analysis mode |
| doWordSeg | boolean | – | Perform word segmentation |
| docId | integer | yes | Document ID |
| keepOriginalLinePolygons | boolean | – | Keep original line polygons (default false) |
| languageModel | string | – | Language model to use |
| modelId | integer | yes | Model/HTR ID |
| nBest | integer | – | Number of best results (default 1) |
| pages | string | – | Page range (e.g. "1-5") |
| printedLanguageModel | string | – | Language model for printed text |
| printedModelId | integer | – | Printed text model ID |
| useExistingLinePolygons | boolean | – | Use existing line polygons (default false) |
| writeKwsIndex | boolean | – | Write KWS index (default false) |
| writeLineConfScore | boolean | – | Write line confidence scores |
| writeWordConfScores | boolean | – | Write word confidence scores |
No output schema declared.
No examples provided.
transkribus_pylaia_train Train PyLaia Model ~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).
| Name | Type | Req | Description |
|---|---|---|---|
| baseModelId | integer | – | Base model ID for transfer learning |
| batch_size | integer | – | Batch size (default: 24). Shortcut for trainCtcPars --batch_size. |
| collId | integer | yes | Collection ID |
| createModelPars | object | – | Model 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… |
| customAbbrevsTraining | boolean | – | Enable custom abbreviations training |
| customTagTraining | boolean | – | Enable custom tag training |
| description | string | – | Description of the model |
| imgType | string | – | Image type |
| language | string | – | Language code (e.g. "rus", "deu", "eng") |
| learning_rate | number | – | Learning rate (default: 3.0E-4). Shortcut for trainCtcPars --learning_rate. |
| max_epochs | integer | – | Maximum training epochs (default: 100). Shortcut for trainCtcPars --max_epochs. |
| max_nondecreasing_epochs | integer | – | Early stopping patience (default: 20). Shortcut for trainCtcPars --max_nondecreasing_epochs. |
| modelName | string | – | Name for the new model |
| noTrainingDefaults | boolean | – | If 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). |
| omitLinesByTag | array | – | Tags of lines to omit from training |
| provider | string | – | Training provider (default: "PyLaia") |
| reverseText | boolean | – | Whether to reverse text direction |
| testList | array | – | Test page list |
| testListFile | string | – | Absolute path to JSON file containing test page list array of {docId, pageId} objects. Example: /tmp/transkribus-training/test_list.json |
| textFeatsCfg | object | – | TextFeats preprocessing config override. Merged with UI defaults (normheight=64, deslope/deslant=true, enh=true). Only specify fields you want to change. |
| trainCtcPars | object | – | CTC 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… |
| trainList | array | – | Training page list |
| trainListFile | string | – | Absolute path to JSON file containing training page list array of {docId, pageId} objects. Example: /tmp/transkribus-training/train_list.json |
| trainProperties | boolean | – | Enable training properties |
No output schema declared.
No examples provided.
transkribus_recog_add_to_collection Add Model to Collection ~58
Add a recognition model to another collection.
| Name | Type | Req | Description |
|---|---|---|---|
| collId | integer | yes | Collection ID |
| id | integer | yes | Resource ID |
| targetCollId | integer | yes | Target collection ID to add the model to |
No output schema declared.
No examples provided.
transkribus_recog_compute_error_rate Compute Error Rate ~60
Compute the error rate for a model in a collection.
| Name | Type | Req | Description |
|---|---|---|---|
| body | object | – | Additional error rate computation parameters |
| collId | integer | yes | Collection ID |
| modelId | integer | yes | Model/HTR ID |
No output schema declared.
No examples provided.
transkribus_recog_compute_sample Compute Sample ~44
Compute a recognition sample for a document in a collection.
| Name | Type | Req | Description |
|---|---|---|---|
| collId | integer | yes | Collection ID |
| docId | integer | yes | Document ID |
No output schema declared.
No examples provided.
transkribus_recog_compute_wer Compute WER ~90
Compute the Word Error Rate for a document.
| Name | Type | Req | Description |
|---|---|---|---|
| collId | integer | yes | Collection ID |
| docId | integer | yes | Document ID |
| hyp | string | – | Hypothesis transcript identifier |
| key | string | – | Transcript key |
| pages | string | – | Page range (e.g. "1-5") |
| ref | string | – | Reference transcript identifier |
No output schema declared.
No examples provided.
transkribus_recog_compute_wer_tasas Compute WER (TASAS) ~96
Compute the Word Error Rate using TASAS method for a document.
| Name | Type | Req | Description |
|---|---|---|---|
| collId | integer | yes | Collection ID |
| docId | integer | yes | Document ID |
| hyp | string | – | Hypothesis transcript identifier |
| key | string | – | Transcript key |
| pages | string | – | Page range (e.g. "1-5") |
| ref | string | – | Reference transcript identifier |
No output schema declared.
No examples provided.
transkribus_recog_delete Delete Recognition Model ~39
Delete a recognition model from a collection.
| Name | Type | Req | Description |
|---|---|---|---|
| collId | integer | yes | Collection ID |
| id | integer | yes | Resource ID |
No output schema declared.
No examples provided.
transkribus_recog_get Get Recognition Model ~41
Get details of a recognition model in a collection.
| Name | Type | Req | Description |
|---|---|---|---|
| collId | integer | yes | Collection ID |
| id | integer | yes | Resource ID |
No output schema declared.
No examples provided.
transkribus_recog_get_add_info Get Add Info ~43
Get information about adding a recognition model to collections.
| Name | Type | Req | Description |
|---|---|---|---|
| collId | integer | yes | Collection ID |
| id | integer | yes | Resource ID |
No output schema declared.
No examples provided.
transkribus_recog_get_atr Get ATR Info ~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 Get Model Costs ~77
Get the cost information for a recognition model.
| Name | Type | Req | Description |
|---|---|---|---|
| collId | integer | yes | Collection ID |
| credits | string | – | Credits parameter |
| id | integer | yes | Resource ID |
| nrOfPages | integer | – | Number of pages |
| writeKwsIndex | boolean | – | Write KWS index |
No output schema declared.
No examples provided.
transkribus_recog_get_error_rate Get Error Rate ~65
Get the error rate for a collection or model.
| Name | Type | Req | Description |
|---|---|---|---|
| collId | integer | – | Collection ID |
| key | string | – | Key identifier |
| modelId | integer | – | Model/HTR ID |
| ref | string | – | Reference identifier |
No output schema declared.
No examples provided.
transkribus_recog_get_ocr_costs Get OCR Costs ~98
Get the estimated OCR costs for a document.
| Name | Type | Req | Description |
|---|---|---|---|
| collId | integer | yes | Collection ID |
| doBlockSegOnly | boolean | – | Only do block segmentation |
| docId | integer | yes | Document ID |
| id | integer | – | Model ID |
| nrOfPages | integer | – | Number of pages |
| pages | string | – | Page range |
| type | string | – | OCR type |
No output schema declared.
No examples provided.
transkribus_recog_get_test_set Get Test Set ~56
Get the test set data for a recognition model.
| Name | Type | Req | Description |
|---|---|---|---|
| collId | integer | yes | Collection ID |
| id | integer | yes | Resource ID |
| nrOfTranscripts | integer | – | Number of transcripts |
No output schema declared.
No examples provided.
transkribus_recog_get_train_data Get Training Data ~69
Get the training data for a recognition model.
| Name | Type | Req | Description |
|---|---|---|---|
| collId | integer | yes | Collection ID |
| id | integer | yes | Resource ID |
| index | integer | – | Start index (0-based) |
| nValues | integer | – | Number of results (-1 for all) |
No output schema declared.
No examples provided.
transkribus_recog_get_train_set Get Training Set ~55
Get the training set for a recognition model.
| Name | Type | Req | Description |
|---|---|---|---|
| collId | integer | yes | Collection ID |
| id | integer | yes | Resource ID |
| nrOfTranscripts | integer | – | Number of transcripts |
No output schema declared.
No examples provided.
transkribus_recog_get_validation_gt_by_htr Get Validation GT by HTR ID ~73
Get validation ground truth data for a recognition model.
| Name | Type | Req | Description |
|---|---|---|---|
| collId | integer | yes | Collection ID |
| id | integer | yes | Resource ID |
| index | integer | – | Start index (0-based) |
| nValues | integer | – | Number of results (-1 for all) |
No output schema declared.
No examples provided.
transkribus_recog_list_by_collection List Models by Collection ~96
List recognition models available in a specific collection.
| Name | Type | Req | Description |
|---|---|---|---|
| collId | integer | yes | Collection ID |
| index | integer | – | Start index (0-based) |
| nValues | integer | – | Number of results (-1 for all) |
| prov | string | – | Filter by provider |
| sortColumn | string | – | Column to sort by |
| sortDirection | string | – | Sort direction: asc or desc |
No output schema declared.
No examples provided.
transkribus_recog_list_collections List Model Collections ~43
List collections that have access to a recognition model.
| Name | Type | Req | Description |
|---|---|---|---|
| collId | integer | yes | Collection ID |
| id | integer | yes | Resource ID |
No output schema declared.
No examples provided.
transkribus_recog_list_dicts List Dictionaries ~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 List Recognition Models ~130
List available recognition models with optional filtering.
| Name | Type | Req | Description |
|---|---|---|---|
| collId | integer | – | Filter by collection ID |
| filter | string | – | Filter string |
| index | integer | – | Start index (0-based) |
| nValues | integer | – | Number of results (-1 for all) |
| prov | string | – | Filter by provider (alternative) |
| provider | string | – | Filter by model provider |
| releaseLevel | integer | – | Filter by release level |
| sortColumn | string | – | Column to sort by |
| sortDirection | string | – | Sort direction: asc or desc |
No output schema declared.
No examples provided.
transkribus_recog_remove_from_collection Remove Model from Collection ~41
Remove a recognition model from a collection.
| Name | Type | Req | Description |
|---|---|---|---|
| collId | integer | yes | Collection ID |
| id | integer | yes | Resource ID |
No output schema declared.
No examples provided.
transkribus_recog_run_atr Run ATR ~68
Run Automatic Text Recognition on a document or specific pages.
| Name | Type | Req | Description |
|---|---|---|---|
| collId | integer | yes | Collection ID |
| docId | integer | yes | Document ID |
| modelId | integer | – | Model/HTR ID |
| pageNr | integer | – | Page number |
No output schema declared.
No examples provided.
transkribus_recog_run_htr_citlab Run HTR (CITlab) ~189
Run CITlab HTR recognition on a document using a specific model.
| Name | Type | Req | Description |
|---|---|---|---|
| allowConcurrentExecution | boolean | – | Allow concurrent execution (default false) |
| collId | integer | yes | Collection ID |
| credits | string | – | Credits parameter |
| dict | string | – | Dictionary to use |
| doLinePolygonSimplification | boolean | – | Simplify line polygons (default true) |
| doStoreConfMats | boolean | – | Store confidence matrices (default true) |
| doStructures | boolean | – | Run structure analysis |
| docId | integer | yes | Document ID |
| keepOriginalLinePolygons | boolean | – | Keep original line polygons (default false) |
| modelId | integer | yes | Model/HTR ID |
| pages | string | – | Page range (e.g. "1-5") |
| tempDict | string | – | Temporary dictionary |
No output schema declared.
No examples provided.
transkribus_recog_run_ocr Run OCR ~126
Run OCR on a document or specific pages in a collection.
| Name | Type | Req | Description |
|---|---|---|---|
| collId | integer | yes | Collection ID |
| doBlockSegOnly | boolean | – | Only do block segmentation (default false) |
| docId | integer | yes | Document ID |
| id | integer | – | Model ID |
| language | string | – | Language for OCR |
| ocrType | string | – | OCR type (default "Legacy") |
| pages | string | – | Page range (e.g. "1-5") |
| typeFace | string | – | Type face for OCR |
No output schema declared.
No examples provided.
transkribus_recog_run_trhtr Run TRHTR ~169
Run TRHTR recognition using a specific model in a collection.
| Name | Type | Req | Description |
|---|---|---|---|
| allowConcurrentExecution | boolean | – | Allow concurrent execution |
| b2pBackend | string | – | B2P backend type |
| collId | integer | yes | Collection ID |
| credits | string | – | Credits parameter |
| doLinePolygonSimplification | boolean | – | Simplify line polygons |
| doNotDeleteWorkDir | boolean | – | Do not delete work directory |
| id | integer | – | Document ID |
| modelId | integer | yes | Model/HTR ID |
| modelName | string | – | Model name |
| pages | string | – | Page range (e.g. "1-5") |
| useExistingLinePolygons | boolean | – | Use existing line polygons |
No output schema declared.
No examples provided.
transkribus_recog_text2image Run Text2Image ~86
Run Text2Image alignment using a specific model in a collection.
| Name | Type | Req | Description |
|---|---|---|---|
| body | object | yes | Text2Image parameters |
| collId | integer | yes | Collection ID |
| credits | string | – | Credits parameter |
| doNotDeleteWorkDir | boolean | – | Do not delete work directory |
| modelId | integer | yes | Model/HTR ID |
No output schema declared.
No examples provided.
transkribus_recog_text2image_citlab Text2Image (CITlab) ~50
Run CITlab Text2Image alignment for a collection.
| Name | Type | Req | Description |
|---|---|---|---|
| body | object | yes | Text2Image configuration parameters |
| collId | integer | yes | Collection ID |
No output schema declared.
No examples provided.
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.