transkribus_action_count
Get the total count of actions, optionally filtered by collection or type.
LABSCO SUMMARY
Loading all of it is the wrong first move.
300 tools is more than most clients will accept and far more than any one task needs. The split entry points exist precisely for that — transcription work is 47 tools, search is 16 — and choosing one is the difference between a working setup and a client that refuses to connect.
What it is
A wrapper over the Transkribus REST API for handwritten and printed text recognition. It covers collections and documents, page transcripts, recognition and layout-analysis runs, model training and management, search and keyword spotting, and the jobs, credits and uploads underneath all of it.
What you get
- 300 tools across 22 resource domains, published behind 8 entry points so you can load only the part your client has room for
- Collections and documents — create, list, search, duplicate and export collections; create documents from IIIF, METS, PDF or FTP; manage per-collection users, labels, tags and credits
- Pages and transcripts — read a page's plain text or a specific transcript version, post a new transcript, lock a page, move or replace pages
- Recognition — run ATR, OCR, CITlab HTR, PyLaia and TRHTR against a document, plus text-to-image alignment, and compute word error rate against ground truth
- Layout analysis — standard and advanced analysis, LA2 inference and table structure inference, with a cost estimate available first
- Training — CITlab HTR, LA2, PyLaia, P2PaLA and table-recognition training runs, with training and validation data and their statistics readable back
- Models — list, get, update, delete, and share a model into other collections
- Search — full text across transcriptions, keyword search, search and replace, tag search, and keyword-spotting queries with their hits
- Operations — jobs (create, list, restart, kill, undo, error detail), actions, users, credits and uploads
Requirements
The npm package @lazyants/transkribus-mcp-server over stdio. Authentication is session-based: set TRANSKRIBUS_USER and TRANSKRIBUS_PASSWORD and the server logs in and manages the session, or set TRANSKRIBUS_SESSION_ID if you already hold one — session IDs expire, so credentials are the choice for anything long-running. Pick a split binary rather than the full server if your client caps tool counts: transkribus-mcp-collections is 132 tools, admin 62, transcription 47, users 29, models 26, jobs 18, search 16. Scope is the legacy TrpServer REST API; the newer Processing API v2 is deliberately out of scope. This is an unofficial server, not affiliated with READ-COOP SCE.
Setup effort
One command plus credentials — npm install -g @lazyants/transkribus-mcp-server, then supply credentials
USE CASES
01
Running text recognition over a document
Kick off ATR or OCR against selected pages and follow the job until it finishes.
02
Getting a page's text back out
Read the plain text of the current transcript, or a specific earlier version of it.
03
Building a collection from material you already have
Create the collection, then ingest documents from PDFs or a IIIF manifest.
04
Measuring how good a model is on your handwriting
Compute the word error rate for a document and read the error rate recorded for the model.
05
Training a model on your own transcriptions
Start a PyLaia or CITlab training run and inspect the training set it was built from.
06
Finding a phrase across everything transcribed
Full-text search across transcriptions, or a keyword-spotting query with per-hit results.
07
Knowing what a run costs before starting it
Cost estimates for OCR, layout analysis and the document as a whole, before credits are spent.
300 tools
Counted once with only startup setup. Other versions, modes or optional credentials may expose a different list.
transkribus_action_info
Retrieve detailed information about a specific action.
transkribus_action_list
List actions with optional filtering by collection, type, and pagination.
transkribus_admin_authorize_users_for_job
Authorize specific users to run a job implementation.
transkribus_admin_get_job_log
Retrieve the log output for a specific job.
transkribus_admin_get_job_users
List users authorized to run a specific job implementation.
transkribus_admin_get_reports
Retrieve administrative reports by type and time period.
transkribus_admin_list_sessions
List all currently active user sessions.
transkribus_admin_move_field_model
Move a field recognition model to a different directory.
transkribus_admin_move_table_model
Move a table recognition model to a different directory.
transkribus_admin_rebuild_models_index
Rebuild the search index for all recognition models.
transkribus_auth_check_session
Check if the current Transkribus session is valid.
transkribus_auth_get_details
Get details of the currently authenticated user.
transkribus_auth_invalidate
Invalidate the current authentication session.
transkribus_auth_logout
Log out of the current Transkribus session.
transkribus_auth_refresh
Refresh the current authentication session token.
transkribus_coll_activity_recognition
Get recognition activity records for a collection.
transkribus_coll_activity_saves
Get save activity records for a collection.
transkribus_coll_add_doc
Add an existing document to a collection.
transkribus_coll_add_docs
Add multiple existing documents to a collection.
transkribus_coll_add_favorite
Add a collection to the user favorites.
transkribus_coll_can_manage
Check if the current user can manage the specified collection.
transkribus_coll_count
Get the total number of collections accessible to the current user.
transkribus_coll_count_docs
Get the number of documents in a collection.
transkribus_coll_count_find_documents
Count documents matching the given search criteria.
transkribus_coll_create
Create a new collection with the given name.
transkribus_coll_create_doc_from_ftp
Ingest a document into a collection from an FTP source.
transkribus_coll_create_doc_from_iiif
Create a document in a collection from an IIIF manifest URL.
transkribus_coll_create_doc_from_mets
Create a document in a collection from METS metadata.
transkribus_coll_create_doc_from_mets_url
Create a document in a collection from a METS URL.
transkribus_coll_create_doc_from_pdf
Create a document in a collection from a PDF file.
transkribus_coll_create_iob_import
Create documents from an IOB import.
transkribus_coll_credit_add_package
Add a credit package to a collection.
transkribus_coll_credit_history
Get the credit usage history for a collection.
transkribus_coll_credit_list
List credit packages associated with a collection.
transkribus_coll_credit_remove_package
Remove a credit package from a collection.
transkribus_coll_credit_transactions
Get credit transaction records for a collection.
transkribus_coll_delete
Delete a collection by ID.
transkribus_coll_delete_empty
Delete a collection only if it is empty.
transkribus_coll_duplicate
Duplicate an entire collection.
transkribus_coll_duplicate_doc
Duplicate a document within a collection.
transkribus_coll_ead_metadata_import
Import EAD metadata into a collection.
transkribus_coll_export
Export documents from a collection in the specified format.
transkribus_coll_find_documents
Search for documents across collections using filters.
transkribus_coll_find_documents_old
Search for documents using the legacy endpoint.
transkribus_coll_find_documents_post
Search for documents across collections using a POST request body.
transkribus_coll_get_metadata
Get metadata for a collection.
transkribus_coll_get_recent
Get recently accessed items in a collection.
transkribus_coll_get_recent_collections
Get recently accessed collections.
transkribus_coll_get_recent_documents
Get recently accessed documents.
transkribus_coll_get_tag_defs
List tag definitions for a collection.
transkribus_coll_label_list
List all labels associated with a collection.
transkribus_coll_list
List all collections accessible to the current user.
transkribus_coll_list_by_name
Search for collections by name.
transkribus_coll_list_docs
List all documents in a collection with pagination.
transkribus_coll_list_docs_xml
List all documents in a collection in XML format.
transkribus_coll_list_for_user
List collections accessible to a specific user.
transkribus_coll_list_paged
List collections with pagination support.
transkribus_coll_list_xml
List all collections in XML format.
transkribus_coll_modify
Modify the properties of a collection.
transkribus_coll_remove_doc
Remove a document from a collection without deleting it.
transkribus_coll_remove_favorite
Remove a collection from the user favorites.
transkribus_coll_remove_user
Remove a user from a collection using the POST endpoint.
transkribus_coll_subscribe_get
Get the subscription status for a collection.
transkribus_coll_update_default_tag_defs
Update the default tag definitions across all collections.
transkribus_coll_update_metadata
Update the metadata for a collection.
transkribus_coll_update_tag_defs
Update tag definitions for a specific collection.
transkribus_coll_upload_doc
Upload a document to a collection.
transkribus_coll_upload_doc_multipart
Upload a document to a collection using multipart form data.
transkribus_coll_user_add
Add a new user to a collection with an optional role.
transkribus_coll_user_add_or_modify
Add a user to a collection or modify their role if they already exist.
transkribus_coll_user_count
Get the number of users in a collection.
transkribus_coll_user_get_list
Get the list of users with access to a collection.
transkribus_coll_user_list
List users of a collection with optional pagination.
transkribus_coll_user_remove
Remove a user from a collection by their user ID.
transkribus_coll_user_stats
Get user statistics for a collection.
transkribus_coll_user_update_role
Update the role of a user in a collection.
transkribus_credit_create
Create a new credit package.
transkribus_credit_get
Get details of a specific credit package by ID.
transkribus_credit_get_collections
List collections associated with a specific credit package.
transkribus_credit_get_costs
Get the credit cost information, optionally filtered by type.
transkribus_credit_get_history
Get the credit usage history with pagination.
transkribus_credit_get_package_transactions
List credit transactions for a specific credit package.
transkribus_credit_get_products
List available credit products for purchase.
transkribus_credit_get_transactions
List credit transactions with pagination.
transkribus_credit_handle_order
Process a credit order by ID.
transkribus_credit_list_by_user
List credit packages for the current user.
transkribus_credit_manage
Create or update credit history entries.
transkribus_credit_update
Update an existing credit package by ID.
transkribus_crowd_delete_messages
Delete messages from the crowd project of a collection.
transkribus_crowd_delete_milestones
Delete milestones from the crowd project of a collection.
transkribus_crowd_get_project
Get the crowd project details for a collection.
transkribus_crowd_post_message
Store a new message in the crowd project of a collection.
transkribus_crowd_post_milestone
Store a new milestone in the crowd project of a collection.
transkribus_crowd_post_project
Create or update the crowd project configuration for a collection.
transkribus_crowdsource_count
Get the total count of crowdsourcing projects.
transkribus_crowdsource_get_details
Get crowdsourcing details for a collection.
transkribus_crowdsource_list
List available crowdsourcing projects.
transkribus_crowdsource_subscribe
Subscribe to a crowdsourcing project for a collection.
transkribus_crowdsource_unsubscribe
Unsubscribe from a crowdsourcing project for a collection.
transkribus_doc_delete
Delete a document from a collection.
transkribus_doc_export
Export a document in the specified format.
transkribus_doc_get_costs
Get the processing costs for a document.
transkribus_doc_get_editorial_declaration
Get the editorial declaration for a document.
transkribus_doc_get_fulldoc
Get the full document including all pages and transcripts.
transkribus_doc_get_fulldoc_xml
Get the full document in XML format.
transkribus_doc_get_image_names
Get the image file names for all pages in a document.
transkribus_doc_get_metadata
Get metadata for a document.
transkribus_doc_get_mets
Get the METS metadata for a document.
transkribus_doc_get_page_ids
Get the page IDs for all pages in a document.
transkribus_doc_get_pages
Get all pages for a document.
transkribus_doc_get_stat
Get document statistics summary.
transkribus_doc_get_stats
Get detailed statistics for a document.
transkribus_doc_get_test_set
Get the test set data for a document.
transkribus_doc_get_train_data
Get the training data for a document.
transkribus_doc_get_transcript_ids
Get all transcript IDs for a document.
transkribus_doc_get_validation_data
Get the validation data for a document.
transkribus_doc_has_affiliation
Check if a document has an affiliation.
transkribus_doc_kws_search
Search for keywords within a document.
transkribus_doc_list_collections
List all collections a document belongs to.
transkribus_doc_list_collections_paged
List all collections a document belongs to with pagination.
transkribus_doc_list_pages
List pages in a document with pagination.
transkribus_doc_move_pages_by_image_names
Move pages within a document based on image names.
transkribus_doc_post_editorial_declaration
Create or update the editorial declaration for a document.
transkribus_doc_remove_from_collection
Remove a document from a collection without deleting it.
transkribus_doc_update_metadata
Update metadata for a document.
transkribus_doc_update_metadata_v2
Update document metadata using the v2 endpoint.
transkribus_doc_update_transcript
Update a transcript for a specific page in a document.
transkribus_du_recognize
Run Document Understanding recognition on a document using a specific model.
transkribus_editdecl_delete_feature
Delete an editorial declaration feature from a collection.
transkribus_editdecl_delete_option
Delete an option from an editorial declaration feature.
transkribus_editdecl_list_features
List all editorial declaration features for a collection.
transkribus_editdecl_post_feature
Store a new editorial declaration feature in a collection.
transkribus_editdecl_post_option
Store a new option for an editorial declaration feature.
transkribus_elearning_count
Get the total count of e-learning courses.
transkribus_elearning_list
List available e-learning courses.
transkribus_elearning_subscribe
Subscribe to an e-learning course for a collection.
transkribus_elearning_unsubscribe
Unsubscribe from an e-learning course for a collection.
transkribus_file_check
Check the status or existence of a file at a given path.
transkribus_file_list_dirs
List directories at a given path on the server.
transkribus_file_list_files
List files at a given path on the server.
transkribus_job_count
Get the total number of jobs, optionally filtered by status or type.
transkribus_job_create
Create a new processing job.
transkribus_job_get
Get details of a specific job by ID.
transkribus_job_get_credit_transactions
Get credit transactions associated with a specific job.
transkribus_job_get_errors
Get error details for a specific job.
transkribus_job_kill
Kill a running job by ID.
transkribus_job_list
List jobs with pagination, optionally filtered by status or type.
transkribus_job_restart_all_by_user
Restart all jobs for a specific user.
transkribus_job_undo
Undo the results of a completed job.
transkribus_job_update
Update properties of an existing job.
transkribus_kws_create_query
Create a new keyword spotting query.
transkribus_kws_get_hits
Get hits for a keyword spotting query.
transkribus_kws_get_keywords
Get keywords for a keyword spotting query.
transkribus_kws_get_result_data
Get result data for a keyword spotting query.
transkribus_kws_list_queries
List keyword spotting queries.
transkribus_la_analyze
Run layout analysis on document pages.
transkribus_la_analyze_advanced
Run advanced layout analysis with additional parameters.
transkribus_la_get_costs
Get the cost estimate for layout analysis on a document.
transkribus_la_la2_inference
Run LA2 model inference on document pages.
transkribus_la_table_inference
Run table structure inference on document pages.
transkribus_label_assign_documents
Assign documents to a label.
transkribus_label_assign_pages
Assign pages to a label.
transkribus_label_create
Create a new label.
transkribus_label_delete
Delete a label by ID.
transkribus_label_get
Get a label by ID.
transkribus_label_list
List all labels.
transkribus_label_remove_all_documents
Remove all documents from a label.
transkribus_label_remove_all_pages
Remove all pages from a label.
transkribus_label_remove_documents
Remove documents from a label.
transkribus_label_remove_pages
Remove pages from a label.
transkribus_label_replace_document_assignments
Replace label assignments for a specific document.
transkribus_label_replace_page_assignments
Replace label assignments for a specific page.
transkribus_label_update
Update an existing label by ID.
transkribus_model_add_collection
Add a collection to a model by type and model ID.
transkribus_model_add_collection_by_id
Add a collection to a model by model ID and collection ID.
transkribus_model_delete
Delete a model by its ID.
transkribus_model_delete_by_type
Delete a model by its type and ID.
transkribus_model_get
Get details of a model by its ID.
transkribus_model_get_by_type
Get models filtered by type with optional query parameters.
transkribus_model_get_details
Get detailed information about a model by type and ID.
transkribus_model_get_field_params
Get the field parameters for a model by type and ID.
transkribus_model_get_train_data
Get the training data for a model by type and ID.
transkribus_model_get_train_data_docs
Get the documents used as training data for a model.
transkribus_model_get_train_data_stats
Get statistics about the training data for a model.
transkribus_model_get_validation_data
Get the validation data for a model by type and ID.
transkribus_model_get_validation_data_docs
Get the documents used as validation data for a model.
transkribus_model_get_validation_data_stats
Get statistics about the validation data for a model.
transkribus_model_list
List available models with optional pagination and filtering.
transkribus_model_list_collections
List collections associated with a model by type and ID.
transkribus_model_list_collections_by_id
List collections associated with a model by its ID.
transkribus_model_remove_collection
Remove a collection from a model by type, model ID, and collection ID.
transkribus_model_remove_collection_by_id
Remove a collection from a model by model ID and collection ID.
transkribus_model_update
Update a model by posting updated model data.
transkribus_model_update_by_type
Update a model by its type and ID.
transkribus_p2pala_train
Start P2PaLA layout analysis model training for a collection.
transkribus_page_add
Add a new page to a document at the specified position.
transkribus_page_assign_plaintext
Assign plain text content to a page as a new transcript.
transkribus_page_count_transcripts
Get the number of transcripts for a page.
transkribus_page_delete
Delete a page from a document.
transkribus_page_delete_transcript
Delete a specific transcript version from a page.
transkribus_page_get
Get details of a specific page in a document.
transkribus_page_get_curr_transcript
Get the current transcript for a page.
transkribus_page_get_metadata
Get metadata for a specific page.
transkribus_page_get_plaintext
Get the plain text content of a page transcript.
transkribus_page_get_text
Get the transcript text for a specific page.
transkribus_page_get_transcript
Get a specific transcript version for a page.
transkribus_page_is_locked
Check if a page is currently locked.
transkribus_page_list_locks
List all locks on a page.
transkribus_page_list_transcripts
List all transcript versions for a page.
transkribus_page_lock
Lock or unlock a page for editing.
transkribus_page_move
Move a page to a different position within the document or to another document.
transkribus_page_post_transcript
Post a new transcript for a page.
transkribus_page_replace
Replace a page image in a document.
transkribus_page_update_hide_on_sites
Set whether a page is hidden on public sites.
transkribus_page_update_status_v2
Update page status using transcript ID (alternative endpoint).
transkribus_page_update_transcript_status
Update the status of a specific transcript version.
transkribus_pylaia_recognize
Run PyLaia HTR recognition on a document using a specific model.
transkribus_pylaia_train
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).
transkribus_recog_add_to_collection
Add a recognition model to another collection.
transkribus_recog_compute_error_rate
Compute the error rate for a model in a collection.
transkribus_recog_compute_sample
Compute a recognition sample for a document in a collection.
transkribus_recog_compute_wer
Compute the Word Error Rate for a document.
transkribus_recog_compute_wer_tasas
Compute the Word Error Rate using TASAS method for a document.
transkribus_recog_delete
Delete a recognition model from a collection.
transkribus_recog_get
Get details of a recognition model in a collection.
transkribus_recog_get_add_info
Get information about adding a recognition model to collections.
transkribus_recog_get_atr
Retrieve information about available ATR (Automatic Text Recognition) models.
transkribus_recog_get_costs
Get the cost information for a recognition model.
transkribus_recog_get_error_rate
Get the error rate for a collection or model.
transkribus_recog_get_ocr_costs
Get the estimated OCR costs for a document.
transkribus_recog_get_test_set
Get the test set data for a recognition model.
transkribus_recog_get_train_data
Get the training data for a recognition model.
transkribus_recog_get_train_set
Get the training set for a recognition model.
transkribus_recog_get_validation_gt_by_htr
Get validation ground truth data for a recognition model.
transkribus_recog_list_by_collection
List recognition models available in a specific collection.
transkribus_recog_list_collections
List collections that have access to a recognition model.
transkribus_recog_list_dicts
List available dictionaries for recognition.
transkribus_recog_list_models
List available recognition models with optional filtering.
transkribus_recog_remove_from_collection
Remove a recognition model from a collection.
transkribus_recog_run_atr
Run Automatic Text Recognition on a document or specific pages.
transkribus_recog_run_htr_citlab
Run CITlab HTR recognition on a document using a specific model.
transkribus_recog_run_ocr
Run OCR on a document or specific pages in a collection.
transkribus_recog_run_trhtr
Run TRHTR recognition using a specific model in a collection.
transkribus_recog_text2image
Run Text2Image alignment using a specific model in a collection.
transkribus_recog_text2image_citlab
Run CITlab Text2Image alignment for a collection.
transkribus_recog_text2image_matching
Run Text2Image matching using a specific model in a collection.
transkribus_recog_train_htr_citlab
Start CITlab HTR model training for a collection.
transkribus_recog_train_la_citlab
Start CITlab Layout Analysis model training for a collection.
transkribus_recog_train_la2
Start Layout Analysis 2 model training for a collection.
transkribus_recog_train_table
Start table recognition model training for a collection.
transkribus_recog_update
Update a recognition model in a collection.
transkribus_search_fulltext
Search across document transcriptions using a fulltext query.
transkribus_search_keyword
Search for documents matching a keyword.
transkribus_search_replace
Search for a term and replace it across documents.
transkribus_search_replace_in_collection
Search for a term and replace it within a specific collection.
transkribus_search_reset_index
Reset the search index, optionally for a specific collection.
transkribus_search_tags
Search for tags, optionally filtered by collection or tag name.
transkribus_server_available_files
List available client files on the server.
transkribus_server_bug_report
Submit a bug report to the Transkribus server.
transkribus_server_client_version
Get the current Transkribus client version.
transkribus_server_download_client_file
Download a specific client file by name.
transkribus_server_download_client_file_new
Download a specific client file using the new endpoint.
transkribus_server_download_gui
Download the latest Transkribus GUI version.
transkribus_server_get_events
Retrieve server events and notifications.
transkribus_server_version
Get the current Transkribus server version.
transkribus_stat_get_coll
Get statistics for a collection.
transkribus_stat_get_coll_stats
Get collection statistics using the new stats endpoint.
transkribus_stat_get_page_status
Get the page status overview for a collection.
transkribus_stat_get_pages_filtered
Get collection pages with filtering via POST body.
transkribus_stat_get_storage_usage
Get storage usage details for a collection.
transkribus_stat_update_page_status
Update the status of pages in a collection.
transkribus_system_db_status
Check the status of the Transkribus database.
transkribus_system_fimagestore
Check the status of the Transkribus image store.
transkribus_upload_bulk_update_doc_metadata
Bulk update document metadata for uploads.
transkribus_upload_bulk_update_isad_metadata
Bulk update ISAD(G) metadata for uploads.
transkribus_upload_create_from_mets
Create upload from METS file.
transkribus_upload_create_s3
Create an upload from an S3 source.
transkribus_upload_create_structure
Create upload document structure.
transkribus_upload_delete
Delete an upload by ID.
transkribus_upload_get_bulk_doc_metadata
Retrieve bulk document metadata for uploads.
transkribus_upload_get_bulk_isad_metadata
Retrieve bulk ISAD(G) metadata for uploads.
transkribus_upload_get_status
Get the status of an upload by ID.
transkribus_upload_page
Upload a page to an existing upload.
transkribus_upload_update_metadata
Update metadata for an existing upload.
transkribus_user_activity_recognition
Get recognition activity history for a specific user.
transkribus_user_activity_saves
Get save activity history for a specific user.
transkribus_user_count_my_docs
Get the total number of documents owned by the current user.
transkribus_user_delete
Delete a user by ID.
transkribus_user_find
Search for users by username/email.
transkribus_user_get
Get details of a specific user by ID.
transkribus_user_get_job_acl
Get the job access control list for the current user.
transkribus_user_get_stats
Get usage statistics for the current user.
transkribus_user_get_storage
Get storage usage information for a specific user.
transkribus_user_init
Initialize or set up a user account by ID.
transkribus_user_is_allowed_for_job
Check if the current user is allowed to run a specific job type.
transkribus_user_list
List all users with pagination.
transkribus_user_list_my_docs
List documents owned by the current user with pagination.
transkribus_user_list_tag_defs
List all tag definitions for the current user.
transkribus_user_update_tag_defs
Create or update tag definitions for the current user.
BEFORE YOU INSTALL
What to know first
Tools you get
300 tools when we connected. The split entry points expose smaller sets instead, such as transkribus-mcp-collections with 132 and transkribus-mcp-search with 16.
Requires
- npx on PATH
- TRANSKRIBUS_USER in your environment
- TRANSKRIBUS_PASSWORD in your environment
Optional
TRANSKRIBUS_SESSION_ID in your environment
CONTEXT COST
Heavy Standing cost
Rated by the size of the 300 tool definitions that ride along on every turn, not by how many there are
INSTALLATION
Connect your client
Server setup
TERMINAL
npm install -g @lazyants/transkribus-mcp-serverMCP Clients
Claude Code, Claude Desktop
JSON
{
"mcpServers": {
"transkribus": {
"command": "npx",
"args": [
"-y",
"@lazyants/transkribus-mcp-server"
],
"env": {
"TRANSKRIBUS_USER": "<YOUR_TRANSKRIBUS_USER>",
"TRANSKRIBUS_PASSWORD": "<YOUR_TRANSKRIBUS_PASSWORD>"
}
}
}
}The configuration on this page does not set TRANSKRIBUS_SESSION_ID; the project's instructions set it with an export line. An app opened from its icon or dock does not see variables exported in a terminal, so to supply TRANSKRIBUS_SESSION_ID, use the block's "env" section.
Claude Code — split servers
CLAUDE CODE — SPLIT SERVERS · JSON
{
"mcpServers": {
"transkribus-collections": {
"command": "npx",
"args": [
"-y",
"-p",
"@lazyants/transkribus-mcp-server",
"transkribus-mcp-collections"
],
"env": {
"TRANSKRIBUS_USER": "<YOUR_TRANSKRIBUS_USER>",
"TRANSKRIBUS_PASSWORD": "<YOUR_TRANSKRIBUS_PASSWORD>"
}
},
"transkribus-transcription": {
"command": "npx",
"args": [
"-y",
"-p",
"@lazyants/transkribus-mcp-server",
"transkribus-mcp-transcription"
],
"env": {
"TRANSKRIBUS_USER": "<YOUR_TRANSKRIBUS_USER>",
"TRANSKRIBUS_PASSWORD": "<YOUR_TRANSKRIBUS_PASSWORD>"
}
}
}
}The configuration on this page does not set TRANSKRIBUS_SESSION_ID; the project's instructions set it with an export line. An app opened from its icon or dock does not see variables exported in a terminal, so to supply TRANSKRIBUS_SESSION_ID, use the block's "env" section.
