Skip to content

NLP Tools - Sentiment, NER, Toxicity & Language Detection

by fasuizu-br · remote · no sign-in to list tools · v1.1.0 · published by GitHub user fasuizu-br

Toxicity, sentiment, NER, PII detection, and language identification tools

Changes · 4
CompareRegistry entry

6 tools: 4 change things and 2 only read.

Scanned Oct 21, 2026

No check matched anything in the tool definitions. No finding is not a safety guarantee. How the checks work.

claude mcp add --transport http nlp-tools https://apim-ai-apis.azure-api.net/mcp/nlp/mcp

Tools

Open a tool for its reasons and full description. Descriptions are the publisher's own words, shown as they are.

6 tools

Changes things 4Claude Code: ask
  • check_nlp_serviceCheck health status of NLP API services and loaded models.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    Check health status of NLP API services and loaded models. Returns: dict with keys: - status (str): 'healthy' or error state - models (dict): Loaded model status per capability - version (str): API version

    Annotations the server declares

    • title: Check NLP Service
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • detect_languageDetect the language of text.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    Detect the language of text. Supports 176 languages using fastText. Sub-1ms inference latency. Returns ISO 639-1 codes with confidence scores. Args: text: Text to identify the language of. top_k: Number of top language predictions to return (default: 3). Returns: dict with keys: - language (str): Top predicted language ISO 639-1 code - confidence (float 0-1): Confidence for top prediction - predictions (list): Top-k predictions, each with: - language (str): ISO 639-1 code - confidence (float 0-1): Prediction confidence

    Annotations the server declares

    • title: Detect Language
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • detect_piiDetect personally identifiable information (PII) in text.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    Detect personally identifiable information (PII) in text. Finds emails, phone numbers, SSNs, credit cards, IP addresses, and person names. Optionally returns redacted text with PII replaced by type labels (e.g. [EMAIL], [PHONE]). BERT-NER + regex ensemble. Args: text: Text to scan for personally identifiable information. redact: If true, return redacted text with PII replaced by [TYPE]. Returns: dict with keys: - pii_found (list): Detected PII items, each containing: - text (str): The PII value found - type (str): PII type (EMAIL, PHONE, SSN, CREDIT_CARD, IP, PERSON) - start (int): Character offset start - end (int): Character offset end - score (float 0-1): Detection confidence - count (int): Total PII items found - redacted_text (str|null): Text with PII replaced (when redact=true) - has_pii (bool): Whether any PII was detected

    Annotations the server declares

    • title: Detect PII
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • extract_entitiesExtract named entities (NER) from text.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    Extract named entities (NER) from text. Identifies persons, organizations, locations, and miscellaneous entities with span offsets and confidence scores. BERT-NER based with sub-50ms latency. Args: text: Text to extract named entities from. Returns: dict with keys: - entities (list): Detected entities, each containing: - text (str): Entity text - label (str): Entity type (PER, ORG, LOC, MISC) - start (int): Character offset start - end (int): Character offset end - score (float 0-1): Confidence score - count (int): Total number of entities found

    Annotations the server declares

    • title: Extract Entities
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
Only reads 2Claude Code: allow
  • analyze_sentimentAnalyze text sentiment.No findings

    Why it is in this group

    • The name "analyze_sentiment" says "analyze": a word for reading.
    Description, as the server wrote it
    Analyze text sentiment. Returns positive/negative classification with confidence scores. DistilBERT-based with sub-10ms latency. Multiple domain-specific model variants available. Args: text: Text to analyze for sentiment (positive/negative). model: Model variant -- 'general' (default), 'financial', 'twitter'. Returns: dict with keys: - label (str): 'positive' or 'negative' - score (float 0-1): Confidence score for the predicted label - scores (dict): All label scores (positive, negative)

    Annotations the server declares

    • title: Analyze Sentiment
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • analyze_toxicityAnalyze text for toxic content.No findings

    Why it is in this group

    • The name "analyze_toxicity" says "analyze": a word for reading.
    Description, as the server wrote it
    Analyze text for toxic content. Returns scores for 6 categories: toxic, severe_toxic, obscene, threat, insult, identity_hate. Each score is 0.0-1.0. BERT-based classifier with sub-15ms latency on GPU. Args: text: Text to analyze for toxicity (hate speech, insults, threats). Returns: dict with keys: - toxic (float 0-1): Overall toxicity score - severe_toxic (float 0-1): Severe toxicity score - obscene (float 0-1): Obscenity score - threat (float 0-1): Threat score - insult (float 0-1): Insult score - identity_hate (float 0-1): Identity-based hate score - is_toxic (bool): Whether text exceeds toxicity threshold

    Annotations the server declares

    • title: Analyze Toxicity
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Install

Pinned to version 1.1.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http nlp-tools https://apim-ai-apis.azure-api.net/mcp/nlp/mcp

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__nlp-tools__analyze_toxicity",
      "mcp__nlp-tools__analyze_sentiment"
    ],
    "ask": [
      "mcp__nlp-tools__extract_entities",
      "mcp__nlp-tools__detect_pii",
      "mcp__nlp-tools__detect_language",
      "mcp__nlp-tools__check_nlp_service"
    ],
    "deny": []
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. It assumes the server is installed as nlp-tools. Review it before you use it.