Mcp
Connects Claude to Tuteliq's child safety APIs with 50+ detection tools spanning text, voice, image, video, and document analysis. You get bullying detection, grooming pattern recognition, fraud analysis across 16 categories, synthetic content forensics with multi-signal pipelines, and identity verification flows. Context parameters let you calibrate scoring by age group, platform, and sender trust level to reduce false positives on institutional messages. Also exposes webhook management, usage tracking, GDPR compliance tools, and breach logging. Reach for this when building parental controls, content moderation systems, or compliance workflows that need age-appropriate threat detection with audit trails and crisis resource routing.
- tools
- 75
- auth
- Secret needed
- transport
- STDIO, HTTP
- env var
- 1
- last updated
- Nov 2, 2026
Tools
75 toolsPublic tool metadata for what this MCP can expose to an agent.
detect_bullyingAnalyze 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
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
No parameter schema in public metadata yet.
detect_groomingDetect grooming patterns and predatory behavior in conversations
Detect grooming patterns and predatory behavior in conversations
No parameter schema in public metadata yet.
detect_unsafeIdentify unsafe content (self-harm, violence, explicit material)
Identify unsafe content (self-harm, violence, explicit material)
No parameter schema in public metadata yet.
analyzeQuick comprehensive safety check (bullying + unsafe)
Quick comprehensive safety check (bullying + unsafe)
No parameter schema in public metadata yet.
analyse_multiRun multiple detection endpoints on a single piece of text in one call
Run multiple detection endpoints on a single piece of text in one call
No parameter schema in public metadata yet.
batch_analyzeAnalyze up to 50 items in a single request — all twelve detection types (bullying, grooming, unsafe, emotions, social_engineering, app_fraud, romance_scam, mule_recruitment, gambling_harm, coercive_control, vulnerability_exploitation, radicalisation) — ideal for bulk triage
Analyze up to 50 items in a single request — all twelve detection types (bullying, grooming, unsafe, emotions, social_engineering, app_fraud, romance_scam, mule_recruitment, gambling_harm, coercive_control, vulnerability_exploitation, radicalisation) — ideal for bulk triage
No parameter schema in public metadata yet.
analyze_emotionsAnalyze emotional content and mental state indicators — accepts single text or full conversations
Analyze emotional content and mental state indicators — accepts single text or full conversations
No parameter schema in public metadata yet.
get_action_planGenerate age-appropriate guidance for safety situations
Generate age-appropriate guidance for safety situations
No parameter schema in public metadata yet.
generate_reportCreate incident reports from conversations
Create incident reports from conversations
No parameter schema in public metadata yet.
detect_social_engineeringDetect social engineering tactics (pretexting, urgency fabrication, authority impersonation)
Detect social engineering tactics (pretexting, urgency fabrication, authority impersonation)
No parameter schema in public metadata yet.
detect_app_fraudDetect app-based fraud (fake investment platforms, phishing apps, subscription traps)
Detect app-based fraud (fake investment platforms, phishing apps, subscription traps)
No parameter schema in public metadata yet.
detect_romance_scamDetect romance scam patterns (love-bombing, financial requests, identity deception)
Detect romance scam patterns (love-bombing, financial requests, identity deception)
No parameter schema in public metadata yet.
detect_mule_recruitmentDetect money mule recruitment tactics (easy-money offers, bank account sharing)
Detect money mule recruitment tactics (easy-money offers, bank account sharing)
No parameter schema in public metadata yet.
detect_gambling_harmDetect gambling-related harm indicators (chasing losses, concealment, distress)
Detect gambling-related harm indicators (chasing losses, concealment, distress)
No parameter schema in public metadata yet.
detect_coercive_controlDetect coercive control patterns (isolation, financial control, monitoring, threats)
Detect coercive control patterns (isolation, financial control, monitoring, threats)
No parameter schema in public metadata yet.
detect_vulnerability_exploitationDetect exploitation of vulnerable individuals (elderly, disabled, financially distressed)
Detect exploitation of vulnerable individuals (elderly, disabled, financially distressed)
No parameter schema in public metadata yet.
detect_radicalisationDetect radicalisation indicators (extremist rhetoric, us-vs-them framing, ideological grooming)
Detect radicalisation indicators (extremist rhetoric, us-vs-them framing, ideological grooming)
No parameter schema in public metadata yet.
analyze_voiceTranscribe audio and run safety analysis on the transcript
Transcribe audio and run safety analysis on the transcript
No parameter schema in public metadata yet.
analyze_imageAnalyze images for visual safety + OCR text extraction
Analyze images for visual safety + OCR text extraction
No parameter schema in public metadata yet.
analyze_videoAnalyze video files for safety concerns via key frame extraction (supports mp4, mov, avi, webm, mkv)
Analyze video files for safety concerns via key frame extraction (supports mp4, mov, avi, webm, mkv)
No parameter schema in public metadata yet.
analyze_documentAnalyze PDF documents for safety concerns — per-page multi-endpoint detection with chain-of-custody hashing (max 50MB, 100 pages)
Analyze PDF documents for safety concerns — per-page multi-endpoint detection with chain-of-custody hashing (max 50MB, 100 pages)
No parameter schema in public metadata yet.
detect_synthetic_textDetect AI-generated text across 10 child-safety categories (synthetic CSAM, deepfake scripts, AI grooming)
Detect AI-generated text across 10 child-safety categories (synthetic CSAM, deepfake scripts, AI grooming)
No parameter schema in public metadata yet.
detect_synthetic_image6-signal forensic pipeline: vision AI, EXIF metadata, pixel stats, C2PA Content Credentials, watermarks, pHash
6-signal forensic pipeline: vision AI, EXIF metadata, pixel stats, C2PA Content Credentials, watermarks, pHash
No parameter schema in public metadata yet.
detect_synthetic_audioDual-signal forensics: transcript + mel spectrogram vision + quantitative audio statistics
Dual-signal forensics: transcript + mel spectrogram vision + quantitative audio statistics
No parameter schema in public metadata yet.
detect_synthetic_video5-track analysis: per-frame vision, temporal face consistency, lip-sync correlation, spectral audio, transcript
5-track analysis: per-frame vision, temporal face consistency, lip-sync correlation, spectral audio, transcript
No parameter schema in public metadata yet.
create_verification_sessionCreate a session for age or identity verification — returns a URL for the user to complete the flow
Create a session for age or identity verification — returns a URL for the user to complete the flow
No parameter schema in public metadata yet.
get_verification_sessionPoll session status — returns full document intelligence (MRZ, barcode, authenticity, face match, liveness)
Poll session status — returns full document intelligence (MRZ, barcode, authenticity, face match, liveness)
No parameter schema in public metadata yet.
cancel_verification_sessionCancel an active session (no credits consumed)
Cancel an active session (no credits consumed)
No parameter schema in public metadata yet.
get_incidents_overviewCounts by category, severity, source, status and platform over a window
Counts by category, severity, source, status and platform over a window
No parameter schema in public metadata yet.
list_incidentsPaginated, filterable incident list
Paginated, filterable incident list
No parameter schema in public metadata yet.
get_incidentFull detail for one incident, including the risk trajectory across messages
Full detail for one incident, including the risk trajectory across messages
No parameter schema in public metadata yet.
get_incident_trendsIncident volume bucketed by hour, day or week, split by severity
Incident volume bucketed by hour, day or week, split by severity
No parameter schema in public metadata yet.
moderation_queueModerator triage console: the unreviewed queue, the next item, and — optionally — your own analysis trace and recommended decision, rendered for human sign-off. Read-only
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
No parameter schema in public metadata yet.
review_incidentRecord a moderator decision (confirm / downgrade / escalate / reclassify / dismiss) with a signed receipt
Record a moderator decision (confirm / downgrade / escalate / reclassify / dismiss) with a signed receipt
No parameter schema in public metadata yet.
batch_review_incidentsApply one decision across many incidents in a single call
Apply one decision across many incidents in a single call
No parameter schema in public metadata yet.
get_audit_receiptFetch the signed receipt for a past inference
Fetch the signed receipt for a past inference
No parameter schema in public metadata yet.
get_audit_logsQuery the audit log
Query the audit log
No parameter schema in public metadata yet.
list_webhooksList all configured webhooks
List all configured webhooks
No parameter schema in public metadata yet.
create_webhookCreate a new webhook endpoint
Create a new webhook endpoint
No parameter schema in public metadata yet.
update_webhookUpdate webhook configuration
Update webhook configuration
No parameter schema in public metadata yet.
delete_webhookDelete a webhook
Delete a webhook
No parameter schema in public metadata yet.
test_webhookSend a test payload to verify webhook
Send a test payload to verify webhook
No parameter schema in public metadata yet.
regenerate_webhook_secretRegenerate webhook signing secret
Regenerate webhook signing secret
No parameter schema in public metadata yet.
get_pricingGet available pricing plans
Get available pricing plans
No parameter schema in public metadata yet.
get_pricing_detailsGet detailed pricing with features and limits
Get detailed pricing with features and limits
No parameter schema in public metadata yet.
get_usage_historyGet daily usage history
Get daily usage history
No parameter schema in public metadata yet.
get_usage_by_toolGet usage by tool/endpoint
Get usage by tool/endpoint
No parameter schema in public metadata yet.
get_usage_monthlyGet monthly usage with billing info
Get monthly usage with billing info
No parameter schema in public metadata yet.
get_usage_summaryGet today's usage: requests made, succeeded and failed, remaining today, and the rate limit
Get today's usage: requests made, succeeded and failed, remaining today, and the rate limit
No parameter schema in public metadata yet.
get_usage_quotaGet real-time rate-limit status — pre-flight check before batch runs
Get real-time rate-limit status — pre-flight check before batch runs
No parameter schema in public metadata yet.
get_policyGet the account's detection policy (per-category flag/block thresholds, auto-moderation)
Get the account's detection policy (per-category flag/block thresholds, auto-moderation)
No parameter schema in public metadata yet.
set_policyUpdate the account's detection policy configuration
Update the account's detection policy configuration
No parameter schema in public metadata yet.
list_policy_rulesList all automation rules (block/flag/escalate/notify/log_only on matching detections)
List all automation rules (block/flag/escalate/notify/log_only on matching detections)
No parameter schema in public metadata yet.
create_policy_ruleCreate a rule that labels matching detections with an action for your own system to apply
Create a rule that labels matching detections with an action for your own system to apply
No parameter schema in public metadata yet.
get_policy_ruleGet full detail of a single rule
Get full detail of a single rule
No parameter schema in public metadata yet.
update_policy_ruleUpdate any subset of a rule's fields (e.g., pause with `enabled: false`)
Update any subset of a rule's fields (e.g., pause with `enabled: false`)
No parameter schema in public metadata yet.
delete_policy_rulePermanently delete a rule
Permanently delete a rule
No parameter schema in public metadata yet.
evaluate_policy_rulesDry-run rules against a hypothetical detection result
Dry-run rules against a hypothetical detection result
No parameter schema in public metadata yet.
get_detection_settingsSee which detection endpoints are enabled/disabled + default context
See which detection endpoints are enabled/disabled + default context
No parameter schema in public metadata yet.
update_detection_settingsEnable/disable endpoints, set default context
Enable/disable endpoints, set default context
No parameter schema in public metadata yet.
reset_detection_settingsReset to defaults (all endpoints enabled)
Reset to defaults (all endpoints enabled)
No parameter schema in public metadata yet.
get_intelligence_trendsAnonymised network-wide threat trends by endpoint/category/age/platform/geo
Anonymised network-wide threat trends by endpoint/category/age/platform/geo
No parameter schema in public metadata yet.
get_emerging_threatsEmerging threat patterns over a recent window
Emerging threat patterns over a recent window
No parameter schema in public metadata yet.
get_weekly_digestWeekly digest: summary, top categories, notable changes
Weekly digest: summary, top categories, notable changes
No parameter schema in public metadata yet.
get_risk_trendsAnonymised global risk trends
Anonymised global risk trends
No parameter schema in public metadata yet.
delete_account_dataDelete all account data (Right to Erasure)
Delete all account data (Right to Erasure)
No parameter schema in public metadata yet.
export_account_dataExport all account data as JSON (Data Portability)
Export all account data as JSON (Data Portability)
No parameter schema in public metadata yet.
record_consentRecord user consent for data processing
Record user consent for data processing
No parameter schema in public metadata yet.
get_consent_statusGet current consent status
Get current consent status
No parameter schema in public metadata yet.
withdraw_consentWithdraw a previously granted consent
Withdraw a previously granted consent
No parameter schema in public metadata yet.
rectify_dataCorrect user data (Right to Rectification)
Correct user data (Right to Rectification)
No parameter schema in public metadata yet.
log_breachLog a new data breach (starts 72-hour notification clock)
Log a new data breach (starts 72-hour notification clock)
No parameter schema in public metadata yet.
list_breachesList all data breaches, optionally filtered by status
List all data breaches, optionally filtered by status
No parameter schema in public metadata yet.
get_breachGet details of a specific data breach
Get details of a specific data breach
No parameter schema in public metadata yet.
update_breach_statusUpdate breach status and notification progress
Update breach status and notification progress
No parameter schema in public metadata yet.
Sponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageConfiguration
TUTELIQ_API_KEY*secretTuteliq API key from tuteliq.ai
Readme
Tuteliq
Tuteliq MCP Server
MCP server for Tuteliq - AI-powered child safety tools for Claude
API Docs • Dashboard • Trust • Changelog • Discord
What is this?
Tuteliq MCP Server brings AI-powered child safety tools directly into Claude, Cursor, and other MCP-compatible AI assistants. Ask Claude to check messages for bullying, detect grooming patterns, or generate safety action plans.
Details
- Repository
- github.com/tuteliq/mcp
- Category
- Media & Entertainment
- Package
@tuteliq/mcp- Transport
- STDIO, HTTP
- Auth
- Required
- Registry
- MCP registry, active
Related Media & Entertainment MCP servers
View all
Prunacharlesrapp/pruna-mcp-serverUltra-fast image generation, editing, upscaling, and video generation via Pruna AI.2stars
Ap Mcp Serverrbonestell/ap-mcp-serverModel Context Protocol (MCP) server for the Associated Press Media API0stars
Solnksolnk-dev/solnk-mcpLet AI agents draft, schedule and publish social posts to 9 platforms, reviewed before going live.2stars
Adseezyadseezy/adseezy-mcpVideo ads, UGC creator ads and ad hooks for your own products, with OAuth sign-in.1stars