Brainiall NLP is a remote MCP server that gives an AI agent 22 tools, among them analyze_sentiment, analyze_toxicity, answer_question. It answers at https://api.brainiall.com/mcp/nlp/mcp over streamable HTTP, and it listed its tools to an anonymous client, so no sign-in was needed for that. Our probes reached it 7 of 10 times since 4 September 2026; the last check, on 18 October 2026, succeeded.
Sentiment, toxicity, entity extraction, PII, translation, summary, QA, fraud scoring, safety audit.
Description as the publisher wrote it.
| Tool | What it does |
|---|---|
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 (p Inputs: text, model |
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 toxicit Inputs: text |
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. que Inputs: text, question |
aspect_sentiment | Sentiment per aspect. Brainiall Aspect Sentiment engine. Splits the text into sentences mentioning each aspect, classifies each, aggregates. Inputs: text, aspects |
check_groundedness | Hallucination check: is a claim actually supported by a source text? Brainiall Groundedness engine. Returns {grounded, confidence, supporting_span, reason}. Inputs: claim, source |
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 |
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}. Inputs: text, labels, multi_label |
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. Inputs: turns |
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 Inputs: text, top_k |
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 + Inputs: text, redact |
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. Inputs: prompt |
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. Inputs: text |
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. Inputs: text |
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. Inputs: text, top_k, max_ngram |
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 wi Inputs: event_id, label, notes |
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-read Inputs: amount, currency, avg_txn_amount_30d, txn_count_1h, txn_count_24h, distinct_cards_24h |
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_chunk Inputs: namespace, text, title |
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, ...}). Inputs: namespace |
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. questio Inputs: namespace, question, top_k, rerank, synthesize |
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. Inputs: text, max_entities |
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. Ret Inputs: text, mode, max_length |
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 detec Inputs: text, target_lang, source_lang |
Every block below points at https://api.brainiall.com/mcp/nlp/mcp. Pick your client and copy.
claude mcp add --transport http brainiall-nlp https://api.brainiall.com/mcp/nlp/mcp
{
"mcpServers": {
"brainiall-nlp": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://api.brainiall.com/mcp/nlp/mcp"]
}
}
}{
"mcpServers": {
"brainiall-nlp": {
"url": "https://api.brainiall.com/mcp/nlp/mcp"
}
}
}{
"servers": {
"brainiall-nlp": {
"type": "http",
"url": "https://api.brainiall.com/mcp/nlp/mcp"
}
}
}{
"context_servers": {
"brainiall-nlp": {
"url": "https://api.brainiall.com/mcp/nlp/mcp"
}
}
}{
"mcpServers": {
"brainiall-nlp": {
"serverUrl": "https://api.brainiall.com/mcp/nlp/mcp"
}
}
}{
"mcpServers": {
"brainiall-nlp": {
"url": "https://api.brainiall.com/mcp/nlp/mcp"
}
}
}name: Brainiall NLP
version: 0.0.1
schema: v1
mcpServers:
- name: Brainiall NLP
type: streamable-http
url: https://api.brainiall.com/mcp/nlp/mcp{
"mcpServers": {
"brainiall-nlp": {
"httpUrl": "https://api.brainiall.com/mcp/nlp/mcp"
}
}
}{
"mcpServers": {
"brainiall-nlp": {
"type": "http",
"url": "https://api.brainiall.com/mcp/nlp/mcp"
}
}
}{
"mcpServers": {
"brainiall-nlp": {
"url": "https://api.brainiall.com/mcp/nlp/mcp"
}
}
}goose://extension?url=https%3A%2F%2Fapi.brainiall.com%2Fmcp%2Fnlp%2Fmcp&type=streamable_http&id=brainiall-nlp&name=Brainiall%20NLP
It answered our last check on 18 October 2026 in 781 ms. Over 10 checks since 4 September 2026 it answered 7. Status here comes from Neuronto's own probes, not from the publisher.
Yes. It is published by brainiall.com and served from api.brainiall.com, the vendor's own domain: https://api.brainiall.com/mcp/nlp/mcp.
22, as returned by the server's own tools/list on 31 August 2026: analyze_sentiment, analyze_toxicity, answer_question, aspect_sentiment, check_groundedness, check_nlp_service, classify_text_custom, detect_conversational_pii, and 14 more.
It answered our last check on 18 October 2026 in 781 ms. Over 10 checks since 4 September 2026 it answered 7.
Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://api.brainiall.com/mcp/nlp/mcp. The exact JSON is above, with the same setup for Claude Code, Claude Desktop, VS Code, Windsurf, Zed, Gemini CLI and the rest.
It listed its tools to an anonymous client, so reading the tool list needs no key. Individual tools can still ask for credentials in their own inputs.
Publisher: com.brainiall. Endpoint host: api.brainiall.com. ARD identifier: urn:air:com.brainiall:mcp:nlp.
First indexed 31 August 2026. The tools are exactly what the server returned; nothing on this page
is inferred from its name. Ranking in Neuronto search is never for sale.