TextRazor integration: operations for AI agents
TextRazor connects to Type.com as an integration. This page lists the 28 operations documented for Claude and Codex in Type.com: 20 read, 1 write, 7 destructive.
About TextRazor
TextRazor vendor API references, subject to account permissions.
Categories: Analytics & Data
How to connect TextRazor to Type.com
- Access
- Organization connection: one shared account for the workspace.
To add the connection, follow the steps in Space connections.
Documented operations
28 operations. Your connection's permissions determine which operations are available. API references describe the vendor surface; they do not expand your connection's credentials or access.
28 operations listed.
Analysis
- Read
Analyze text or URL
Analyzes UTF-8 text or fetched URL content with selected extractors. POST is semantic read; usage/quota accounting is not a document deletion. Text limit 200kb; form-urlencoded request, not JSON.
POST /
Dictionaries
- Read
List dictionaries
GET /entities/ Returns a list of all Dictionary in your account.
GET /entities/ - Read
Get a dictionary
GET /entities/{ DICTIONARY_ID } Returns a Dictionary object by id.
GET /entities/{DICTIONARY_ID} - Read
List dictionary entries
GET /entities/{ DICTIONARY_ID }/_all?limit=20&offset=0 Returns all entities in this dictionary, along with paging information. Larger dictionaries can be too large to download all at once. Where possible it is recommended that you use limit and offset paramaters to control the TextRazor response, rather than filtering client side.
GET /entities/{DICTIONARY_ID}/_all - Read
Get a dictionary entry
GET /entities/{ DICTIONARY_ID }/{ ENTITY_ID } Gets a specific entity by id.
GET /entities/{DICTIONARY_ID}/{ENTITY_ID} - Write
Create a dictionary
Creates a dictionary from JSON properties. The source does not establish behavior when this dictionary id already exists; no safe-overwrite or rejection guarantee is inferred.
PUT /entities/{DICTIONARY_ID} - Destructive
Delete a dictionary and entries
DELETE /entities/{ DICTIONARY_ID } Deletes a dictionary and all its entries by id.
DELETE /entities/{DICTIONARY_ID} - Destructive
Add or replace dictionary entries
Conditional: an entry whose id matches an existing entry overwrites the old entry. Entries without id receive a generated id. JSON array input; full text/data key/value constraints retained.
POST /entities/{DICTIONARY_ID}/ - Destructive
Delete a dictionary entry
DELETE /entities/{ DICTIONARY_ID }/{ ENTITY_ID } Deletes a specific entity by id. For performance reasons it's always better to delete and recreate a whole dictionary rather than its individual entries one at a time.
DELETE /entities/{DICTIONARY_ID}/{ENTITY_ID}
Classifiers
- Read
List classifier categories
GET /categories/{ DICTIONARY_ID }/_all?limit=20&offset=0 Returns a list of all Categories for classifier with id classifier_id, along with paging information. Larger classifiers can be too large to download all at once. Where possible it is recommended that you use limit and offset paramaters to control the TextRazor response, rather than filtering client side. Source placeholder says DICTIONARY_ID for a category/classifier route; prose identifies it as classifier_id. Placeholder wording is retained rather than an invented dictionary relationship.
GET /categories/{DICTIONARY_ID}/_all - Read
Get a classifier category
GET /categories/{ DICTIONARY_ID }/{ CATEGORY_ID } Returns a Category object by id. Source placeholder says DICTIONARY_ID for a category/classifier route; prose identifies it as classifier_id. Placeholder wording is retained rather than an invented dictionary relationship.
GET /categories/{DICTIONARY_ID}/{CATEGORY_ID} - Destructive
Add or replace classifier categories (JSON)
application/json creates a classifier or adds categories to an existing classifier; matching category IDs are replaced. Maximum documented effect is conditional replacement.
PUT /categories/{CLASSIFIER_ID} - Destructive
Replace an entire classifier (CSV)
application/csv expects Category ID, Category Label, Category Query columns and replaces the entire existing classifier of that name. This differs materially from the JSON variant on the same PUT route.
PUT /categories/{CLASSIFIER_ID} - Destructive
Delete a classifier
DELETE /categories/{ CLASSIFIER_ID } Deletes a Classifier and all its Categories by id.
DELETE /categories/{CLASSIFIER_ID} - Destructive
Delete a classifier category
DELETE /categories/{ DICTIONARY_ID }/{ CATEGORY_ID } Deletes a Category object by id. For performance reasons it's always better to delete and recreate a whole classifier rather than its individual categories one at a time. Source placeholder says DICTIONARY_ID for a category/classifier route; prose identifies it as classifier_id. Placeholder wording is retained rather than an invented dictionary relationship.
DELETE /categories/{DICTIONARY_ID}/{CATEGORY_ID}
Account
- Read
Get account limits and usage
GET /account/ Returns a complete Account object.
GET /account/
Analysis capabilities
- Read
Extract named entities
Shared POST / analysis capability. Select extractors=entities. All documented options and complete response object fields are retained. Analysis is semantic read; stored dictionary/classifier management is separate.
POST / - Read
Extract document topics
Shared POST / analysis capability. Select extractors=topics. All documented options and complete response object fields are retained. Analysis is semantic read; stored dictionary/classifier management is separate.
POST / - Read
Tokenize and analyze words
Shared POST / analysis capability. Select extractors=words. All documented options and complete response object fields are retained. Analysis is semantic read; stored dictionary/classifier management is separate.
POST / - Read
Extract noun phrases
Shared POST / analysis capability. Select extractors=phrases. All documented options and complete response object fields are retained. Analysis is semantic read; stored dictionary/classifier management is separate.
POST / - Read
Extract dependency trees
Shared POST / analysis capability. Select extractors=dependency-trees. All documented options and complete response object fields are retained. Analysis is semantic read; stored dictionary/classifier management is separate.
POST / - Read
Extract relations
Shared POST / analysis capability. Select extractors=relations. All documented options and complete response object fields are retained. Analysis is semantic read; stored dictionary/classifier management is separate.
POST / - Read
Extract entailments
Shared POST / analysis capability. Select extractors=entailments. All documented options and complete response object fields are retained. Analysis is semantic read; stored dictionary/classifier management is separate.
POST / - Read
Extract word senses
Shared POST / analysis capability. Select extractors=senses. All documented options and complete response object fields are retained. Analysis is semantic read; stored dictionary/classifier management is separate.
POST / - Read
Detect spelling suggestions
Shared POST / analysis capability. Select extractors=spelling. All documented options and complete response object fields are retained. Analysis is semantic read; stored dictionary/classifier management is separate.
POST / - Read
Classify with default or custom classifiers
Shared POST / analysis capability. Use the corresponding documented classifiers, entityDictionaries or rules options; no nonexistent extractor token is invented. All documented options and complete response object fields are retained. Analysis is semantic read; stored dictionary/classifier management is separate.
POST / - Read
Match custom entity dictionaries
Shared POST / analysis capability. Use the corresponding documented classifiers, entityDictionaries or rules options; no nonexistent extractor token is invented. All documented options and complete response object fields are retained. Analysis is semantic read; stored dictionary/classifier management is separate.
POST / - Read
Evaluate custom Prolog extraction rules
Shared POST / analysis capability. Use the corresponding documented classifiers, entityDictionaries or rules options; no nonexistent extractor token is invented. All documented options and complete response object fields are retained. Analysis is semantic read; stored dictionary/classifier management is separate.
POST /
No operations match.
See How connections work for access and permissions, or browse all integrations.