detect_prompt_injection — Brainiall NLP MCP Tool
detect_prompt_injection
(detect prompt injection) is one of 22 tools on the
Brainiall NLP
MCP server. Connect the server and your client discovers it on the handshake.
by client
How to call detect_prompt_injection from your client
- Claude Code Brainiall NLP detect_prompt_injection run in your project directory
- Claude Desktop Brainiall NLP detect_prompt_injection ~/Library/Application Support/Claude/claude_desktop_config.json
- Cursor Brainiall NLP detect_prompt_injection ~/.cursor/mcp.json
- VS Code Brainiall NLP detect_prompt_injection .vscode/mcp.json
- Zed Brainiall NLP detect_prompt_injection ~/.config/zed/settings.json
- Windsurf Brainiall NLP detect_prompt_injection ~/.codeium/windsurf/mcp_config.json
- Cline Brainiall NLP detect_prompt_injection ~/Library/Application Support/Code/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json
- Gemini CLI Brainiall NLP detect_prompt_injection ~/.gemini/settings.json
- Grok Brainiall NLP detect_prompt_injection .mcp.json (in your project root)
- ChatGPT Brainiall NLP detect_prompt_injection Settings → Connectors → Advanced → Developer mode
- Claude.ai Brainiall NLP detect_prompt_injection Settings → Connectors → Add custom connector
- LangChain Brainiall NLP detect_prompt_injection pip install langchain-mcp-adapters
Fastest route
claude mcp add --transport http nlp https://api.brainiall.com/mcp/nlp/mcpOther tools on this server
- analyze_toxicity
- analyze_sentiment
- extract_entities
- detect_pii
- detect_language
- check_nlp_service
- translate_text
- summarize_text
- answer_question
- knowledge_ingest
- knowledge_query
- knowledge_list_documents
- fraud_score
- fraud_feedback
- extract_key_phrases
- aspect_sentiment
- classify_text_custom
- link_entities_to_wikidata
- detect_conversational_pii
- check_groundedness
- detect_protected_material
This list was read from the server itself, by connecting to it and calling tools/list on 24 September 2026. It is what
the server actually exposes, not what its listing claims.
Mutating and Read-only are read off each tool's name, not its schema — a hint, not a guarantee. The registry stores tool names only; connect the server for its live schemas.