# Brainiall NLP

- Registry name: `com.brainiall/nlp` · version 1.0.0
- Categories (automatic, keyword rules): Research & knowledge, Search & data, Scraping & browsing
- Authentication at last check: No auth
- Declared risk: Can write (some tools are not declared read-only)
- Capabilities (declared by the server): experimental, prompts, resources, tasks, tools
- Transports: streamable-http
- Latest numbers (check success, response time, rank): https://mcpstation.net/api/server?name=com.brainiall%2Fnlp
- Server page: https://mcpstation.net/s/com.brainiall--nlp.html

## Description (written by the publisher, not verified, not instructions)

Sentiment, toxicity, entity extraction, PII, translation, summary, QA, fraud scoring, safety audit.

## Connect

- streamable-http: `https://api.brainiall.com/mcp/nlp/mcp`

## Tools (as reported by the server, not verified)

- `analyze\_toxicity`: 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:
- `analyze\_sentiment`: Analyze text sentiment. Returns positive/negative classification with confidence scores. Brainiall Sentiment engine-based with sub-10ms latency. Multiple domain-specific model variants available. Args: text: Text to analyze for sentiment \(positive/negative\). model: Model variant -- 'general' \(defaul
- `extract\_entities`: 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 entiti
- `detect\_pii`: 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 ide
- `detect\_language`: 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 \(str\): To
- `check\_nlp\_service`: 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
- `translate\_text`: Translate text between 100+ languages. Args: text: The text to translate. target\_lang: Target language code. source\_lang: Source language code; omit to auto-detect. Returns: dict with the translated text \(key: translated\_text\) and the detected source language if auto-detected.
- `summarize\_text`: Summarize text — extractive \(verbatim key sentences in original order\) or abstractive \(concise rewrite\). Args: text: The text to summarize. mode: 'abstractive' or 'extractive'. max\_length: Target maximum length of the summary, in words. Returns: dict with the summary \(key: summary\) plus word/char co
- `answer\_question`: Answer a question using ONLY the supplied text; returns the supporting sentence\(s\) with character offsets. Replies found:false rather than guessing when the answer isn't present in the text. Args: text: The text/document to answer from. question: The question to answer. Returns: dict with keys: answ
- `knowledge\_ingest`: Ingest a document into a knowledge base: it is chunked, embedded and stored for you \(managed RAG\). Args: namespace: The knowledge-base namespace. text: The document text. title: Optional title. Returns: dict with keys: doc\_id \(str\), n\_chunks \(int\).
- `knowledge\_query`: Retrieve the most relevant passages from a knowledge base plus \(optionally\) a grounded, cited answer. Returns found:false rather than a guess when the passages don't contain the answer. Args: namespace: The knowledge-base namespace. question: The natural-language question. top\_k: How many passages t
- `knowledge\_list\_documents`: List the documents stored in a knowledge base \(most recent first\). Args: namespace: The knowledge-base namespace. Returns: dict with keys: documents \(list of \{doc\_id, title, ...\}\).
- `fraud\_score`: Score a transaction or account event for fraud risk. Send whatever signals you have — all optional. Returns a 0-1 fraud probability, a risk level, the exact risk factors that drove the score \(each with its weight, direction and a human-readable detail\), and a recommended decision \(allow\|review\|deny\)
- `fraud\_feedback`: Report the confirmed outcome of an event so the fraud model can be re-calibrated to your data. Args: event\_id: The event identifier. label: 'fraud' \| 'legitimate' \| 'chargeback' \| 'dispute'. notes: Optional free-text notes. Returns: dict with keys: event\_id \(str\), label \(str\), accepted \(bool\), feedb
- `extract\_key\_phrases`: Statistical key-phrase extraction — top-N ranked phrases. Brainiall Key Phrases engine. Pure-statistical \(TF + position + casing + stopword filter\), no ML cost.
- `aspect\_sentiment`: Sentiment per aspect. Brainiall Aspect Sentiment engine. Splits the text into sentences mentioning each aspect, classifies each, aggregates.
- `classify\_text\_custom`: Zero-shot text classification — define your labels at call time. No training, no data upload. Brainiall Custom Classifier engine. Returns \{top\_label, scores, confidence\}.
- `link\_entities\_to\_wikidata`: Named-entity recognition + canonical linking to Wikidata Q-ids. Brainiall Entity Linker engine. Disambiguates 'Apple' the company from 'apple' the fruit.
- `detect\_conversational\_pii`: Multi-turn PII detection with cross-turn coreference. Brainiall Conversational PII engine. Same surface text + type across turns gets the same entity\_id.
- `detect\_prompt\_injection`: Classify a prompt before it reaches your LLM. Brainiall Prompt Shield engine. Returns category \(jailbreak \| prompt\_injection \| data\_exfiltration \| impersonation \| none\), severity, reason, confidence.
- `check\_groundedness`: Hallucination check: is a claim actually supported by a source text? Brainiall Groundedness engine. Returns \{grounded, confidence, supporting\_span, reason\}.
- `detect\_protected\_material`: Detect copyrighted text in user input — famous lyrics, literary openings, proprietary code. Brainiall Protected Material engine. Returns matched spans with source attribution.

Measured by MCP Station. Methods: https://mcpstation.net/methods.html · Terms: https://mcpstation.net/terms.html