MCP
未认领MCP server with 41 AI-powered tools for child safety, fraud detection, and content moderation. Detects bullying, grooming, sextortion, romance scams, social engineering, and more. For Claude, Cursor, and MCP-compatible AI assistants.
01 / 选择客户端
03 / 添加配置
claude mcp add --transport stdio 'tuteliq-mcp' -- 'npx' '-y' '@tuteliq/mcp'04 / 在客户端中确认
打开客户端的 MCP 设置，确认服务器已连接并列出工具。复制配置不代表连接成功。
更多AI & ML服务器
浏览完整目录安全概况
已认领和已认证的服务器每周接受一次静态扫描，显示代码能触及的范围（外部服务、环境变量、shell 命令、代理配置目录）以及带有已知公告的依赖。认领此列表即可获得。 安全概况的工作原理
40 个工具中显示 40 个
文档中列出的工具 (40)
内容来自项目文档。服务器握手不会验证每个工具的说明或行为。
analyse_multi
Run multiple detection endpoints on a single piece of text in one call
analyze
Quick comprehensive safety check (bullying + unsafe)
analyze_document
Analyze PDF documents for safety concerns — per-page multi-endpoint detection with chain-of-custody hashing (max 50MB, 100 pages)
analyze_emotions
Analyze emotional content and mental state indicators — accepts single text or full conversations
analyze_image
Analyze images for visual safety + OCR text extraction
analyze_video
Analyze video files for safety concerns via key frame extraction (supports mp4, mov, avi, webm, mkv)
analyze_voice
Transcribe audio and run safety analysis on the transcript
batch_analyze
Analyze up to 50 items in a single request — all twelve detection types (bullying, grooming, unsafe, emotions, socialengineering, appfraud, romancescam, mulerecruitment, gamblingharm, coercivecontrol, vulnerabilityexploitation, radicalisation) — ideal for bulk triage
batch_review_incidents
Apply one decision across many incidents in a single call
cancel_verification_session
Cancel an active session (no credits consumed)
create_verification_session
Create a session for age or identity verification — returns a URL for the user to complete the flow
create_webhook
Create a new webhook endpoint
detect_app_fraud
Detect app-based fraud (fake investment platforms, phishing apps, subscription traps)
detect_bullying
Analyze text for bullying, harassment, and gaming toxicity — including coded slang, emoji, and deliberate filter evasion, with context that tells trash-talk apart from genuine harm
detect_coercive_control
Detect coercive control patterns (isolation, financial control, monitoring, threats)
detect_gambling_harm
Detect gambling-related harm indicators (chasing losses, concealment, distress)
detect_grooming
Detect grooming patterns and predatory behavior in conversations
detect_mule_recruitment
Detect money mule recruitment tactics (easy-money offers, bank account sharing)
detect_radicalisation
Detect radicalisation indicators (extremist rhetoric, us-vs-them framing, ideological grooming)
detect_romance_scam
Detect romance scam patterns (love-bombing, financial requests, identity deception)
detect_social_engineering
Detect social engineering tactics (pretexting, urgency fabrication, authority impersonation)
detect_synthetic_audio
Dual-signal forensics: transcript + mel spectrogram vision + quantitative audio statistics
detect_synthetic_image
6-signal forensic pipeline: vision AI, EXIF metadata, pixel stats, C2PA Content Credentials, watermarks, pHash
detect_synthetic_text
Detect AI-generated text across 10 child-safety categories (synthetic CSAM, deepfake scripts, AI grooming)
detect_synthetic_video
5-track analysis: per-frame vision, temporal face consistency, lip-sync correlation, spectral audio, transcript
detect_unsafe
Identify unsafe content (self-harm, violence, explicit material)
detect_vulnerability_exploitation
Detect exploitation of vulnerable individuals (elderly, disabled, financially distressed)
generate_report
Create incident reports from conversations
get_action_plan
Generate age-appropriate guidance for safety situations
get_audit_logs
Query the audit log
get_audit_receipt
Fetch the signed receipt for a past inference
get_incident
Full detail for one incident, including the risk trajectory across messages
get_incident_trends
Incident volume bucketed by hour, day or week, split by severity
get_incidents_overview
Counts by category, severity, source, status and platform over a window
get_verification_session
Poll session status — returns full document intelligence (MRZ, barcode, authenticity, face match, liveness)
list_incidents
Paginated, filterable incident list
list_webhooks
List all configured webhooks
moderation_queue
Moderator triage console: the unreviewed queue, the next item, and — optionally — your own analysis trace and recommended decision, rendered for human sign-off. Read-only
review_incident
Record a moderator decision (confirm / downgrade / escalate / reclassify / dismiss) with a signed receipt
update_webhook
Update webhook configuration