TextRazor is a natural language processing API that extracts meaning, entities, and relationships from text, powering advanced content analysis and sentiment detection
TextRazor is a natural language processing API that extracts meaning, entities, and relationships from text, powering advanced content analysis and sentiment detection On Nagent, TextRazor is exposed as a fully-configurable artificial intelligence integration that any agent can call — 6 actions, and API key authentication. No code is required to wire TextRazor into your workflow — connect it once via the External Integrations panel and reuse it across every agent you build.
Agent builders use TextRazor to automate the kinds of tasks artificial intelligence teams previously handled manually. Concrete examples — each one is a single agent step in Nagent — include:
Every action and trigger is paired with a structured input/output schema (visible in the sections below), so when you wire TextRazor into Helix — our agentic agent builder — the editor knows exactly what each step expects and produces. Configure once, deploy anywhere across your Nagent agents.
Every operation an agent can call against TextRazor, with input parameters and output schema. Drop these into any step of an agent built in Helix.
TEXTRAZOR_ACCOUNT_INFOThis tool retrieves comprehensive information about a TextRazor account, providing essential details about the account's status, usage, and limits. It returns an Account object containing properties such as the current subscription plan, concurrent request limits, and daily usage among others, making it crucial for monitoring API usage, managing requests, and ensuring compliance with subscription limits.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
TEXTRAZOR_CLASSIFY_TEXTThis tool will classify text into predefined categories using TextRazor's classification capabilities. It takes input text, optional cleanup mode and language, and returns a list of relevant categories with their confidence scores from the analysis. The tool supports various built-in classifiers including: - textrazor_iab: IAB QAG segments - textrazor_iab_content_taxonomy_3.0: IAB Content Taxonomy v3.0 (2022) - textrazor_mediatopics_2023Q1: Latest IPTC Media Topics (March 2023) - And other versions of these taxonomies
Input parameters
The text content to be classified (up to 200kb UTF-8 encoded text)
Comma-separated list of classifiers to use for text classification
Controls preprocessing cleanup mode (raw, stripTags, cleanHTML)
Force TextRazor to analyze content with specific language (ISO-639-2 code)
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
TEXTRAZOR_CUSTOM_CLASSIFIER_MANAGERThis tool manages custom classifiers in TextRazor, allowing users to create, update, and manage custom classification categories.
Input parameters
Maximum number of categories to return when listing categories.
Offset for pagination when listing categories.
The operation to perform on the classifier.
List of categories to create/update. Required for create_update operation.
The category ID when performing operations on a specific category.
The unique identifier for the classifier.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
TEXTRAZOR_DICTIONARY_MANAGERManage custom entity dictionaries in TextRazor for enhanced named entity recognition. This tool enables you to create and manage dictionaries of domain-specific entities (e.g., product names, company names, technical terms) that TextRazor will recognize in text analysis. Operations include: - Creating new dictionaries with configurable matching rules - Listing all available dictionaries - Retrieving dictionary details and configuration - Deleting dictionaries - Adding, retrieving, and removing dictionary entries Note: Dictionaries created here can be used in text analysis by specifying their IDs in the 'entityDictionaries' parameter of TextRazor analysis requests.
Input parameters
List of dictionary entries to add or delete. Required for 'add_entries' and 'delete_entries' operations. Each entry must have at least a 'text' field.
The operation to perform: 'create' creates a new dictionary, 'list' lists all dictionaries, 'get' retrieves dictionary details, 'delete' removes a dictionary, 'add_entries' adds entities to a dictionary, 'get_entries' retrieves all entries from a dictionary, 'delete_entries' removes specific entries from a dictionary.
The unique identifier for the dictionary. Required for all operations except 'list'. Use a descriptive name like 'tech_companies' or 'product_names'.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
TEXTRAZOR_EXTRACT_ENTITIESExtract named entities (people, places, companies, etc.) from text using TextRazor's entity extraction API. The tool will identify and classify named entities within the provided text, returning detailed information about each entity including its type, confidence score, and relevance score. The API returns many entities by default; filter by `relevanceScore` and `confidenceScore` thresholds to retain only meaningful results.
Input parameters
The text to analyze for entity extraction (max 200kb)
Controls preprocessing cleanup mode
ISO-639-2 language code to force analysis in a specific language
When True, entities in response may overlap
List of DBPedia types to filter entities
List of Freebase types to filter entities
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
TEXTRAZOR_TEXT_RAZOR_ANALYZE_CONTENTA comprehensive content analysis tool that combines multiple TextRazor extractors to perform a complete analysis of the input text. This action allows users to analyze text content with multiple extractors in a single API call.
Input parameters
The text content to be analyzed (up to 200kb UTF-8 encoded)
List of analysis features to perform Only extractors explicitly listed will run; omitted extractors produce no output in the response. Accepted values are exactly: 'entities', 'topics', 'words', 'phrases', 'dependency-trees', 'relations', 'entailments', 'senses'. Unsupported names cause an invalid request error.
Controls preprocessing cleanup mode
ISO-639-2 language code to force analysis in a specific language
Use document metadata in analysis
Return the cleaned text in response
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
No publicly available marketplace agent is found using this tool yet. There are 37 agents privately built on Nagent that already use TextRazor.
Build on Nagent
Connect TextRazor to any Nagent agent in minutes — no API key management, no boilerplate. Just configure and deploy.
The five questions agent builders ask before adopting a new integration.
Open the External Integrations panel inside Nagent (app.nagent.ai/externalIntegration), find TextRazor, and click "Connect Now." You'll authenticate with an API key — Nagent handles credential storage and refresh automatically. Once connected, TextRazor is available to any agent in your workspace.
No. Nagent provides no-code integration for every tool. Once TextRazor is connected, you configure its 6 actions directly in the agent builder UI — no API calls, no boilerplate, no schema management.
Helix — Nagent's agentic agent builder — lets you drop TextRazor steps into any workflow visually. Pick an action (e.g., one of those listed above), fill in the inputs (Helix knows the required vs. optional schema for each parameter), and connect it to upstream/downstream steps. Triggers run as the entry point of an agent, so when a TextRazor event fires, the agent kicks off automatically.
Every TextRazor action and trigger ships with a fully-typed schema — input parameters with name, type, required flag, and description, plus the output payload shape. The schemas are documented in the sections above. Helix uses these schemas to validate your configuration at build time and to type-check the data flowing between steps.
Yes. While TextRazor ships with 6 pre-built artificial intelligence actions, you can layer custom logic around them inside Helix — pre/post-processing steps, conditional branches, retries, or stitching TextRazor together with other connected tools. For deeper customization, talk to our team about Nagent's Agentic AI Lab — forward-deployed engineers who build TextRazor-based workflows tailored to your business.