MCP Radar
Serveur MCP

Brainiall NLP

com.brainiall/nlp
IA et agents Connaissance et documentation Public et accessible MCP 2025-11-25

Ce que fait ce MCP

Provides NLP capabilities including sentiment, toxicity, PII and injection detection, entity extraction, translation, summarization, grounded QA, and managed knowledge-base retrieval.

Capacités

Outils

22 outils
analyze_sentiment
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' (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)
Lecture seule Accès externe Idempotent
Schéma d’entrée 
{'type': 'object', 'required': ['text'], 'properties': {'text': {'type': 'string', 'maxLength': 100000, 'description': 'Text to analyze for sentiment (positive/negative)'}, 'model': {'type': 'string', 'default': 'general', 'description': "Model variant: 'general' (default), 'financial', 'twitter'"}}}
analyze_toxicity
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: - 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
Lecture seule Accès externe Idempotent
Schéma d’entrée 
{'type': 'object', 'required': ['text'], 'properties': {'text': {'type': 'string', 'maxLength': 100000, 'description': 'Text to analyze for toxicity (hate speech, insults, threats)'}}}
answer_question
Answer Question About Text
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: answer (str|null), found (bool), supporting_spans (list of {text, start, end}).
Lecture seule Accès externe Idempotent
Schéma d’entrée 
{'type': 'object', 'required': ['text', 'question'], 'properties': {'text': {'type': 'string', 'maxLength': 50000, 'description': 'The text/document to answer from'}, 'question': {'type': 'string', 'maxLength': 1000, 'description': 'The question to answer'}}}
aspect_sentiment
Per-Aspect Sentiment
Sentiment per aspect. Brainiall Aspect Sentiment engine. Splits the text into sentences mentioning each aspect, classifies each, aggregates.
Lecture seule Accès externe Idempotent
Schéma d’entrée 
{'type': 'object', 'required': ['text', 'aspects'], 'properties': {'text': {'type': 'string', 'description': 'Input text'}, 'aspects': {'type': 'array', 'items': {'type': 'string'}, 'description': "Aspect terms to score (e.g. ['camera','battery','price'])"}}}
check_groundedness
Groundedness Detection (Hallucination Check)
Hallucination check: is a claim actually supported by a source text? Brainiall Groundedness engine. Returns {grounded, confidence, supporting_span, reason}.
Lecture seule Accès externe Idempotent
Schéma d’entrée 
{'type': 'object', 'required': ['claim', 'source'], 'properties': {'claim': {'type': 'string', 'maxLength': 4000, 'description': 'The claim to verify'}, 'source': {'type': 'string', 'maxLength': 20000, 'description': 'The source text the claim should be grounded in'}}}
check_nlp_service
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
Lecture seule Accès externe Idempotent
Schéma d’entrée 
{'type': 'object', 'properties': {}}
classify_text_custom
Custom Text Classification (zero-shot)
Zero-shot text classification — define your labels at call time. No training, no data upload. Brainiall Custom Classifier engine. Returns {top_label, scores, confidence}.
Lecture seule Accès externe Idempotent
Schéma d’entrée 
{'type': 'object', 'required': ['text', 'labels'], 'properties': {'text': {'type': 'string', 'description': 'Input text'}, 'labels': {'type': 'array', 'items': {'type': 'string'}, 'description': 'Your candidate labels (2-20 of them)'}, 'multi_label': {'type': 'boolean', 'default': False, 'description': 'If True, multiple labels can apply'}}}
detect_conversational_pii
Conversational PII Detection (multi-turn)
Multi-turn PII detection with cross-turn coreference. Brainiall Conversational PII engine. Same surface text + type across turns gets the same entity_id.
Lecture seule Accès externe Idempotent
Schéma d’entrée 
{'type': 'object', 'required': ['turns'], 'properties': {'turns': {'type': 'array', 'items': {'type': 'object', 'additionalProperties': True}, 'description': 'List of [role, content] dicts representing a dialogue'}}}
detect_language
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): 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
Lecture seule Accès externe Idempotent
Schéma d’entrée 
{'type': 'object', 'required': ['text'], 'properties': {'text': {'type': 'string', 'maxLength': 100000, 'description': 'Text to identify the language of'}, 'top_k': {'type': 'integer', 'default': 3, 'description': 'Number of top language predictions to return'}}}
detect_pii
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 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
Lecture seule Accès externe Idempotent
Schéma d’entrée 
{'type': 'object', 'required': ['text'], 'properties': {'text': {'type': 'string', 'maxLength': 100000, 'description': 'Text to scan for personally identifiable information'}, 'redact': {'type': 'boolean', 'default': False, 'description': 'If true, return redacted text with PII replaced by [TYPE]'}}}
detect_prompt_injection
Prompt Shield (Jailbreak / Injection Detection)
Classify a prompt before it reaches your LLM. Brainiall Prompt Shield engine. Returns category (jailbreak | prompt_injection | data_exfiltration | impersonation | none), severity, reason, confidence.
Lecture seule Accès externe Idempotent
Schéma d’entrée 
{'type': 'object', 'required': ['prompt'], 'properties': {'prompt': {'type': 'string', 'maxLength': 20000, 'minLength': 1, 'description': 'The prompt text to classify (NOT executed)'}}}
detect_protected_material
Protected Material Detection
Detect copyrighted text in user input — famous lyrics, literary openings, proprietary code. Brainiall Protected Material engine. Returns matched spans with source attribution.
Lecture seule Accès externe Idempotent
Schéma d’entrée 
{'type': 'object', 'required': ['text'], 'properties': {'text': {'type': 'string', 'maxLength': 20000, 'description': 'Text to scan for copyrighted material'}}}
extract_entities
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 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
Lecture seule Accès externe Idempotent
Schéma d’entrée 
{'type': 'object', 'required': ['text'], 'properties': {'text': {'type': 'string', 'maxLength': 100000, 'description': 'Text to extract named entities from (persons, organizations, locations)'}}}
extract_key_phrases
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.
Lecture seule Accès externe Idempotent
Schéma d’entrée 
{'type': 'object', 'required': ['text'], 'properties': {'text': {'type': 'string', 'minLength': 1, 'description': 'Input text'}, 'top_k': {'type': 'integer', 'default': 10, 'maximum': 50, 'minimum': 1, 'description': 'Number of phrases to return'}, 'max_ngram': {'type': 'integer', 'default': 3, 'maximum': 4, 'minimum': 1, 'description': 'Max words per phrase (1-4)'}}}
fraud_feedback
Report Fraud Outcome (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), feedback_id (int).
Accès externe
Schéma d’entrée 
{'type': 'object', 'required': ['event_id', 'label'], 'properties': {'label': {'type': 'string', 'description': "The confirmed outcome: 'fraud' | 'legitimate' | 'chargeback' | 'dispute'"}, 'notes': {'anyOf': [{'type': 'string', 'maxLength': 2000}, {'type': 'null'}], 'default': None, 'description': 'Optional free-text notes'}, 'event_id': {'type': 'string', 'maxLength': 256, 'description': 'The event_id you passed to fraud_score (or your own identifier)'}}}
fraud_score
Score Event For Fraud Risk
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). Returns: dict with keys: fraud_probability (float), risk_level (str), decision (str), risk_score_points (float), risk_factors (list of {factor, weight, direction, detail}), decision_bands (dict).
Lecture seule Accès externe Idempotent
Schéma d’entrée 
{'type': 'object', 'properties': {'amount': {'anyOf': [{'type': 'number'}, {'type': 'null'}], 'default': None, 'description': 'The transaction amount'}, 'is_tor': {'anyOf': [{'type': 'boolean'}, {'type': 'null'}], 'default': None, 'description': 'Request originated from a Tor exit node'}, 'currency': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'default': None, 'description': 'ISO 4217 currency code'}, 'event_id': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'default': None, 'description': 'Your identifier for this event (echoed back; use with fraud_feedback)'}, 'avs_match': {'anyOf': [{'type': 'boolean'}, {'type': 'null'}], 'default': None, 'description': 'Whether the address-verification check matched'}, 'is_new_ip': {'anyOf': [{'type': 'boolean'}, {'type': 'null'}], 'default': None, 'description': 'First time seeing this IP'}, 'ip_country': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'default': None, 'description': 'ISO country code geolocated from the IP'}, 'card_country': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'default': None, 'description': 'ISO country code of the payment instrument'}, 'cvv_provided': {'anyOf': [{'type': 'boolean'}, {'type': 'null'}], 'default': None, 'description': 'Whether the CVV was provided'}, 'txn_count_1h': {'anyOf': [{'type': 'integer'}, {'type': 'null'}], 'default': None, 'description': 'Number of transactions on this account in the last hour'}, 'is_new_device': {'anyOf': [{'type': 'boolean'}, {'type': 'null'}], 'default': None, 'description': 'First time seeing this device'}, 'txn_count_24h': {'anyOf': [{'type': 'integer'}, {'type': 'null'}], 'default': None, 'description': 'Number of transactions on this account in the last 24h'}, 'is_proxy_or_vpn': {'anyOf': [{'type': 'boolean'}, {'type': 'null'}], 'default': None, 'description': 'Request originated from a proxy/VPN/datacenter IP'}, 'account_age_days': {'anyOf': [{'type': 'number'}, {'type': 'null'}], 'default': None, 'description': 'Age of the account in days'}, 'prior_chargebacks': {'anyOf': [{'type': 'integer'}, {'type': 'null'}], 'default': None, 'description': 'Number of prior chargebacks on this account'}, 'avg_txn_amount_30d': {'anyOf': [{'type': 'number'}, {'type': 'null'}], 'default': None, 'description': "The account's avg transaction amount over the last 30 days (for amount-anomaly scoring)"}, 'distinct_cards_24h': {'anyOf': [{'type': 'integer'}, {'type': 'null'}], 'default': None, 'description': 'Distinct cards used on this account in 24h'}, 'distinct_countries_24h': {'anyOf': [{'type': 'integer'}, {'type': 'null'}], 'default': None, 'description': 'Distinct countries seen on this account in 24h'}}}
knowledge_ingest
Ingest Document Into Knowledge Base
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).
Accès externe
Schéma d’entrée 
{'type': 'object', 'required': ['namespace', 'text'], 'properties': {'text': {'type': 'string', 'maxLength': 200000, 'description': 'The document text to ingest'}, 'title': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'default': None, 'description': 'Optional title for the document'}, 'namespace': {'type': 'string', 'maxLength': 128, 'description': 'The knowledge-base namespace to ingest into (alphanumeric/hyphen)'}}}
knowledge_list_documents
List Knowledge Base 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, ...}).
Lecture seule Accès externe Idempotent
Schéma d’entrée 
{'type': 'object', 'required': ['namespace'], 'properties': {'namespace': {'type': 'string', 'maxLength': 128, 'description': 'The knowledge-base namespace'}}}
knowledge_query
Query Knowledge Base
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 to retrieve. rerank: Re-order retrieved passages before answering. synthesize: Also return a grounded answer. Returns: dict with keys: answer (str|null), found (bool), passages (list), synthesized (bool), reranked (bool), ...
Lecture seule Accès externe Idempotent
Schéma d’entrée 
{'type': 'object', 'required': ['namespace', 'question'], 'properties': {'top_k': {'type': 'integer', 'default': 6, 'maximum': 50, 'minimum': 1, 'description': 'How many passages to retrieve'}, 'rerank': {'type': 'boolean', 'default': False, 'description': 'Re-order the retrieved passages before answering'}, 'question': {'type': 'string', 'maxLength': 2000, 'description': 'The natural-language question'}, 'namespace': {'type': 'string', 'maxLength': 128, 'description': 'The knowledge-base namespace to query'}, 'synthesize': {'type': 'boolean', 'default': True, 'description': 'Also return a concise answer grounded only in the retrieved passages'}}}
link_entities_to_wikidata
Entity Linking (Wikidata)
Named-entity recognition + canonical linking to Wikidata Q-ids. Brainiall Entity Linker engine. Disambiguates 'Apple' the company from 'apple' the fruit.
Lecture seule Accès externe Idempotent
Schéma d’entrée 
{'type': 'object', 'required': ['text'], 'properties': {'text': {'type': 'string', 'description': 'Input text'}, 'max_entities': {'type': 'integer', 'default': 20, 'maximum': 100, 'minimum': 1, 'description': 'Max entities to return'}}}
summarize_text
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 counts.
Lecture seule Accès externe Idempotent
Schéma d’entrée 
{'type': 'object', 'required': ['text'], 'properties': {'mode': {'type': 'string', 'default': 'abstractive', 'description': "'abstractive' (concise rewrite) or 'extractive' (most important sentences, verbatim)"}, 'text': {'type': 'string', 'maxLength': 50000, 'description': 'The text to summarize'}, 'max_length': {'type': 'integer', 'default': 150, 'maximum': 1000, 'minimum': 10, 'description': 'Target maximum length of the summary, in words'}}}
translate_text
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.
Lecture seule Accès externe Idempotent
Schéma d’entrée 
{'type': 'object', 'required': ['text', 'target_lang'], 'properties': {'text': {'type': 'string', 'maxLength': 50000, 'description': 'The text to translate'}, 'source_lang': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'default': None, 'description': 'Source language code; omit to auto-detect'}, 'target_lang': {'type': 'string', 'description': "Target language code (e.g. 'pt', 'es', 'fr', 'de', 'ja')"}}}
Historique

Modifications récentes des outils

Ajouté
detect_protected_material
21 September 2026 02:47
Ajouté
check_groundedness
21 September 2026 02:47
Ajouté
detect_prompt_injection
21 September 2026 02:47
Ajouté
detect_conversational_pii
21 September 2026 02:47
Ajouté
link_entities_to_wikidata
21 September 2026 02:47
Ajouté
classify_text_custom
21 September 2026 02:47
Ajouté
aspect_sentiment
21 September 2026 02:47
Ajouté
extract_key_phrases
21 September 2026 02:47
Ajouté
fraud_feedback
21 September 2026 02:47
Ajouté
fraud_score
21 September 2026 02:47
Ajouté
knowledge_list_documents
21 September 2026 02:47
Ajouté
knowledge_query
21 September 2026 02:47
Ajouté
knowledge_ingest
21 September 2026 02:47
Ajouté
answer_question
21 September 2026 02:47
Ajouté
summarize_text
21 September 2026 02:47
Ajouté
translate_text
21 September 2026 02:47
Ajouté
check_nlp_service
21 September 2026 02:47
Ajouté
detect_language
21 September 2026 02:47
Ajouté
detect_pii
21 September 2026 02:47
Ajouté
extract_entities
21 September 2026 02:47
Ajouté
analyze_sentiment
21 September 2026 02:47
Ajouté
analyze_toxicity
21 September 2026 02:47
Découvrir

Serveurs MCP similaires

agent4.io

io.agent4/agent4-tenant

Manages grounded business agents, knowledge bases, skills, connected MCP tools, public shares, and structured interactive storyli…

Hipocampo MCP

io.github.carrasquelalex1/hipocampo

Provides bilingual semantic memory, embeddings, graph links, code indexing and search, context preload, deduplication, compressio…

branchly

io.branchly/branchly

Manages an AI application’s knowledge-base content, prompts, tools, data sources, retrieval context, sessions, and usage analytic…

TestGraph

io.github.BBCBasic/testgraph

Supports governed semantic classification, shared AI deliberations, evidence-backed subject enrichment, structured memory, and re…

Santismm Knowledge — Harness Engineering, Agentic AI & Governance

com.santismm/knowledge

Provides searchable and citable knowledge about harness engineering, agentic AI, enterprise patterns, architectures, governance, …

WikiKV Agent Exchange

com.wikikv/wikikv

Provides citation-backed knowledge retrieval, private RAG collections, and coordination workflows for agents exchanging evidence …

api

com.docimprint/api

Extracts, summarizes, translates, searches, and fact-checks documents and web pages, with evidence bundles, citations, receipts, …

Gonka Second Opinion (multi-model)

io.github.bystray/gonka-mcp-server

Runs LLM inference and multi-model second opinions through Gonka, exposes model pricing and trial access, and searches Gonka docu…