# ThinkNEO Control Plane MCP server

Enterprise AI governance: spend, guardrails, policy, budgets, compliance, and provider health.

## Links
- Registry page: https://www.getdrio.com/mcp/ai-thinkneo-control-plane
- Repository: https://github.com/thinkneo-ai/mcp-server
- Website: https://thinkneo.ai

## Install
- Endpoint: https://mcp.thinkneo.ai/mcp
- Auth: Not captured

## Setup notes
- Remote endpoint: https://mcp.thinkneo.ai/mcp

## Tools
- thinkneo_check_spend - Check AI spend summary for a workspace, team, or project. Returns real cost breakdown by provider, model, and time period from the ThinkNEO AI gateway. Endpoint: https://mcp.thinkneo.ai/mcp
- thinkneo_read_memory - Read Claude Code project memory files. Without arguments, returns the MEMORY.md index listing all available memories. With a filename argument, returns the full content of that specific memory file. Use this to access project context, user preferences, feedback, and reference notes persisted across Claude Code sessions. Endpoint: https://mcp.thinkneo.ai/mcp
- thinkneo_write_memory - Write or update a Claude Code project memory file (.md). Persists project context, user preferences, feedback, and reference notes across Claude Code sessions. Filename must end in .md with lowercase alphanumeric characters. Path traversal is blocked. Requires authentication.Use this to persist project context, user preferences, feedback, and reference notes across Claude Code sessions. The filename must end in .md and contain only lowercase letters, digits, underscores, and hyphens (e.g. 'user_fabio.md', 'project_new_feature.md'). Path traversal is blocked. Endpoint: https://mcp.thinkneo.ai/mcp
- thinkneo_evaluate_guardrail - Evaluate a prompt or text against ThinkNEO guardrail policies before sending it to an AI provider. Returns risk assessment, violations found, and recommendations. Requires authentication. Endpoint: https://mcp.thinkneo.ai/mcp
- thinkneo_check - Free-tier prompt safety check. Analyzes text for prompt injection patterns and PII (credit card numbers, Brazilian CPF, US SSN, email, phone, passwords). Returns a safety assessment with specific warnings. No authentication required. Endpoint: https://mcp.thinkneo.ai/mcp
- thinkneo_check_policy - Check AI governance policies including model access, budget limits, data controls, and agent governance from the ThinkNEO gateway. Endpoint: https://mcp.thinkneo.ai/mcp
- thinkneo_get_budget_status - Check AI budget status including spend vs limit, forecast, and chargeback data from the ThinkNEO gateway. Endpoint: https://mcp.thinkneo.ai/mcp
- thinkneo_list_alerts - List active alerts for budget, policy, SLA, and security from the ThinkNEO gateway. Endpoint: https://mcp.thinkneo.ai/mcp
- thinkneo_get_compliance_status - Get compliance status including framework coverage (EU AI Act, ISO 42001, NIST AI RMF, SOC 2) and governance assessments from the ThinkNEO gateway. Endpoint: https://mcp.thinkneo.ai/mcp
- thinkneo_provider_status - Check the status of AI providers and gateway configuration from the ThinkNEO control plane. Endpoint: https://mcp.thinkneo.ai/mcp
- thinkneo_schedule_demo - Schedule a demo or discovery call with the ThinkNEO team. Collects contact information and preferences. No authentication required. Endpoint: https://mcp.thinkneo.ai/mcp
- thinkneo_usage - Check your ThinkNEO MCP usage stats and API key status. Endpoint: https://mcp.thinkneo.ai/mcp
- thinkneo_route_model - Route a task to the optimal AI model based on task type, quality threshold, and optional budget constraint. Returns model recommendation from live gateway. Endpoint: https://mcp.thinkneo.ai/mcp
- thinkneo_get_savings_report - Get AI cost savings report including current spend and projected savings from intelligent routing via the ThinkNEO gateway. Endpoint: https://mcp.thinkneo.ai/mcp
- thinkneo_simulate_savings - Simulate potential cost savings from ThinkNEO intelligent routing. No authentication required — enter your monthly AI spend to see projections. Endpoint: https://mcp.thinkneo.ai/mcp
- thinkneo_evaluate_trust_score - Evaluate the AI Trust Score (0-100) for a workspace based on live governance configuration: compliance mode, guardrails, audit trail, and framework coverage. Endpoint: https://mcp.thinkneo.ai/mcp
- thinkneo_get_trust_badge - Get a simplified AI Trust Badge with live gateway status. No authentication required. Endpoint: https://mcp.thinkneo.ai/mcp
- thinkneo_registry_search - Search the ThinkNEO MCP Marketplace — the npm for MCP tools. Discover MCP servers and tools by keyword, category, rating, or verified status. Returns name, description, tools count, rating, downloads, and verified badge. No authentication required. Endpoint: https://mcp.thinkneo.ai/mcp
- thinkneo_registry_get - Get full details for an MCP server package from the ThinkNEO Marketplace. Returns readme, full tools list, version history, reviews, security score, and installation instructions. No authentication required. Endpoint: https://mcp.thinkneo.ai/mcp
- thinkneo_registry_publish - Publish an MCP server to the ThinkNEO Marketplace. Validates the endpoint by calling initialize and tools/list, runs automated security scan for secrets and injection patterns, computes a security score (0-100), and stores the entry with version history. Validates the endpoint (calls initialize + tools/list), runs security scan (secrets detection, injection patterns), and stores the entry. Authentication required. Endpoint: https://mcp.thinkneo.ai/mcp
- thinkneo_registry_review - Rate and review an MCP server in the ThinkNEO Marketplace. One review per user per package (updates on repeat). Rating from 1 (poor) to 5 (excellent) with optional comment. Reviews affect the package average rating shown in search results. One review per user per package (updates on repeat). Authentication required. Endpoint: https://mcp.thinkneo.ai/mcp
- thinkneo_registry_install - Get installation config for an MCP server from the ThinkNEO Marketplace. Returns ready-to-use JSON config for Claude Desktop, Cursor, Windsurf, or custom clients. Tracks the download. No authentication required. Endpoint: https://mcp.thinkneo.ai/mcp
- thinkneo_bridge_mcp_to_a2a - Bridge MCP tool registry to A2A format. Shows tool-to-skill mappings. Endpoint: https://mcp.thinkneo.ai/mcp
- thinkneo_bridge_a2a_to_mcp - Bridge A2A agents to MCP tool format. Endpoint: https://mcp.thinkneo.ai/mcp
- thinkneo_bridge_generate_agent_card - Generate an A2A Agent Card from registry data. Endpoint: https://mcp.thinkneo.ai/mcp
- thinkneo_bridge_list_mappings - List all MCP <-> A2A bridge mappings for a tenant. Endpoint: https://mcp.thinkneo.ai/mcp
- thinkneo_start_trace - Start a new observability trace for an AI operation. Endpoint: https://mcp.thinkneo.ai/mcp
- thinkneo_get_trace - Get a full trace with spans from the ThinkNEO gateway observability system. Endpoint: https://mcp.thinkneo.ai/mcp
- thinkneo_get_observability_dashboard - Get a real-time observability dashboard from the ThinkNEO gateway. Endpoint: https://mcp.thinkneo.ai/mcp
- thinkneo_log_event - Log a custom observability event. Endpoint: https://mcp.thinkneo.ai/mcp
- thinkneo_end_trace - End an observability trace. Endpoint: https://mcp.thinkneo.ai/mcp
- thinkneo_value_baseline - Get value baseline metrics for a workspace: current spend, request volume, and average cost per request from live gateway data. Endpoint: https://mcp.thinkneo.ai/mcp
- thinkneo_value_log_decision - Log a governance decision to the ThinkNEO evidence store. Creates an immutable audit record for compliance and traceability. Endpoint: https://mcp.thinkneo.ai/mcp
- thinkneo_value_log_risk - Log a risk assessment to the ThinkNEO governance store. Records identified risks with severity for audit and mitigation tracking. Endpoint: https://mcp.thinkneo.ai/mcp
- thinkneo_value_decision_cost - Calculate the average cost per AI decision from real usage events. Helps quantify the cost of each AI-assisted decision in the workflow. Endpoint: https://mcp.thinkneo.ai/mcp
- thinkneo_value_agent_roi - Calculate ROI per AI agent using live registry and chargeback data. Shows cost vs. output value for each registered agent. Endpoint: https://mcp.thinkneo.ai/mcp
- thinkneo_value_business_impact - Get business impact metrics combining quality scorecards with spend data. Shows how AI governance translates to measurable business outcomes. Endpoint: https://mcp.thinkneo.ai/mcp
- thinkneo_a2a_log - Retrieve A2A (agent-to-agent) interaction logs from the live gateway. Shows which agents called which, actions performed, costs, and outcomes. Endpoint: https://mcp.thinkneo.ai/mcp
- thinkneo_a2a_policy - Retrieve A2A interaction policies from the live gateway. Shows allowed actions, rate limits, cost caps, and approval requirements. Endpoint: https://mcp.thinkneo.ai/mcp
- thinkneo_a2a_flow - Visualize agent-to-agent communication flow. Shows registered agents, their approval status, and interaction patterns from the live gateway. Endpoint: https://mcp.thinkneo.ai/mcp
- thinkneo_a2a_audit - Retrieve immutable audit trail for A2A interactions with hash verification. Each event is cryptographically chained for tamper detection. Endpoint: https://mcp.thinkneo.ai/mcp
- thinkneo_value_waste_detector - Detect AI spend waste signals: high fallback ratio, failed requests, unused budget allocations, and inefficient model usage patterns. Endpoint: https://mcp.thinkneo.ai/mcp
- thinkneo_outcome_validation - Validate AI outcomes using quality scorecards. Returns quality metrics, accuracy scores, and validation status from the ThinkNEO governance layer. Endpoint: https://mcp.thinkneo.ai/mcp
- thinkneo_policy_create - Create a governance policy. Requires authentication. Endpoint: https://mcp.thinkneo.ai/mcp
- thinkneo_policy_list - List all governance policies. Requires authentication. Endpoint: https://mcp.thinkneo.ai/mcp
- thinkneo_policy_evaluate - Evaluate a specific policy by ID. Requires authentication. Endpoint: https://mcp.thinkneo.ai/mcp
- thinkneo_policy_violations - Get policy violation counts from runtime metrics. Endpoint: https://mcp.thinkneo.ai/mcp
- thinkneo_benchmark_report - Get model quality scorecards from the live gateway. Endpoint: https://mcp.thinkneo.ai/mcp
- thinkneo_benchmark_compare - Compare models by cost, latency, and quality from live data. Endpoint: https://mcp.thinkneo.ai/mcp
- thinkneo_compliance_generate - Generate a compliance report for regulatory frameworks (EU AI Act, ISO 42001, SOC2, NIST). Exports from live audit data. Endpoint: https://mcp.thinkneo.ai/mcp
- thinkneo_sla_define - Define or update an SLA for an AI agent. Requires authentication. Endpoint: https://mcp.thinkneo.ai/mcp
- thinkneo_sla_status - Check current SLA status for agents. Requires authentication. Endpoint: https://mcp.thinkneo.ai/mcp
- thinkneo_sla_breaches - View SLA breach history and kill-switch data. Requires authentication. Endpoint: https://mcp.thinkneo.ai/mcp
- thinkneo_sla_dashboard - SLA overview dashboard combining registry, metrics, and approvals. Endpoint: https://mcp.thinkneo.ai/mcp
- thinkneo_audit_export - Export audit events from the live gateway. Supports JSON and CSV formats with date range filtering for SIEM integration. Endpoint: https://mcp.thinkneo.ai/mcp
- thinkneo_compare_models - Compare available AI models from the live gateway catalog. Endpoint: https://mcp.thinkneo.ai/mcp
- thinkneo_count_tokens - Estimate token count for text (chars/4 approximation). Endpoint: https://mcp.thinkneo.ai/mcp
- thinkneo_optimize_prompt - Analyze prompt and suggest optimizations with live metrics context. Endpoint: https://mcp.thinkneo.ai/mcp
- thinkneo_rotate_key - Instruct the gateway to rotate an API key. Endpoint: https://mcp.thinkneo.ai/mcp
- thinkneo_manage_secrets - Check connector grants and secrets status from the gateway. Endpoint: https://mcp.thinkneo.ai/mcp
- thinkneo_cache_status - Get semantic cache stats from the live gateway runtime metrics. Endpoint: https://mcp.thinkneo.ai/mcp
- thinkneo_detect_injection - Detect prompt injection attempts in text using guardrail patterns. Also retrieves live guardrails_blocked stats from the gateway. Endpoint: https://mcp.thinkneo.ai/mcp
- thinkneo_detect_pii_intl - Detect international PII in text. Supports US (SSN), Brazil (CPF/CNPJ), EU (IBAN, NIF), Singapore (NRIC), India (Aadhaar/PAN), and global patterns. Endpoint: https://mcp.thinkneo.ai/mcp
- thinkneo_signup - Sign up for ThinkNEO MCP free tier or retrieve current account if already authenticated. Idempotent: existing valid token returns current account info, no duplicate created. After signup, configure your MCP client with: Authorization: Bearer <api_key> Endpoint: https://mcp.thinkneo.ai/mcp
- thinkneo_subscribe - Subscribe to ThinkNEO MCP Pro ($490/mo) or Enterprise ($4999/mo). Returns a Stripe Checkout URL — open in browser to complete payment. Requires free-tier API key. After payment, run thinkneo_status to verify activation. Endpoint: https://mcp.thinkneo.ai/mcp
- thinkneo_billing_status - Show current ThinkNEO MCP subscription tier, quota usage, billing status, and subscription period. Requires API key. Endpoint: https://mcp.thinkneo.ai/mcp
- thinkneo_upgrade - Upgrade ThinkNEO MCP subscription. Free → Pro/Enterprise: creates new Stripe Checkout session. Pro → Enterprise: in-place upgrade with proration. Requires API key. Endpoint: https://mcp.thinkneo.ai/mcp
- thinkneo_cancel - Cancel ThinkNEO MCP subscription at the end of the current billing period. Subscription remains active until period end, then reverts to free tier. Requires API key with active paid subscription. Endpoint: https://mcp.thinkneo.ai/mcp

## Resources
- thinkneo://docs/getting-started - ThinkNEO Getting Started Guide Quick-start guide for connecting your AI applications to the ThinkNEO control plane. MIME type: text/plain
- thinkneo://docs/supported-providers - ThinkNEO Supported AI Providers List of AI providers supported by the ThinkNEO gateway with available models. MIME type: application/json

## Prompts
- thinkneo_governance_audit - AI Governance Audit Run a full governance audit for a workspace: check budget status, list active alerts, and review compliance readiness. Arguments: workspace
- thinkneo_policy_preflight - Policy Pre-flight Check Pre-flight check before switching to a new AI model or provider: verify it's allowed by workspace policy and evaluate guardrail compliance. Arguments: workspace, provider, model, sample_prompt

## Metadata
- Owner: ai.thinkneo
- Version: 1.0.2
- Runtime: Streamable Http
- Transports: HTTP
- License: Not captured
- Language: Not captured
- Stars: Not captured
- Updated: Mar 23, 2026
- Source: https://registry.modelcontextprotocol.io