AI & Machine Learning

thinkneo.ai

Provides tools for managing AI spend, executing governed completions, and evaluating guardrails within the ThinkNEO AI gateway.

1 endpoint68 known toolsFirst detected May 29, 2026Last detected July 25, 2026

ENDPOINT 1

https://mcp.thinkneo.ai/mcp

No auth detected

MCP server metadata

Name: ThinkNEO Control Plane
Version: 1.28.0

Capabilities

experimentalloggingpromptsresourcestoolscompletions

Server instructions

You are connected to the ThinkNEO Enterprise AI Control Plane MCP server. ThinkNEO is the governance layer between your AI applications and providers (OpenAI, Anthropic, Google, Mistral, and more). Available tools: - thinkneo_read_memory: Read Claude Code project memory files (index or specific file) [public] - thinkneo_write_memory: Write/update project memory files [public] - thinkneo_check: Free prompt safety check — detects injection & PII [free] - thinkneo_usage: Your usage stats — calls, limits, cost [free] - thinkneo_check_spend: AI cost breakdown by provider/model/team [auth required] - thinkneo_evaluate_guardrail: Pre-flight prompt safety evaluation [auth required] - thinkneo_check_policy: Verify model/provider/action is allowed [auth required] - thinkneo_get_budget_status: Budget utilization and enforcement [auth required] - thinkneo_list_alerts: Active alerts and incidents [auth required] - thinkneo_get_compliance_status: SOC2/GDPR/HIPAA readiness [auth required] - thinkneo_provider_status: Real-time provider health [public] - thinkneo_schedule_demo: Book a demo with the ThinkNEO team [public] - thinkneo_route_model: AI Smart Router — find cheapest model for your task [auth required] - thinkneo_get_savings_report: View your AI cost savings report [auth required] - thinkneo_simulate_savings: Simulate how much you'd save — free lead gen tool [public] - thinkneo_evaluate_trust_score: Get your AI Trust Score (0-100) with badge [auth required] - thinkneo_get_trust_badge: Look up a public trust score badge by token [public] MCP Marketplace (Registry): - thinkneo_registry_search: Search the MCP Marketplace — discover servers by keyword/category [public] - thinkneo_registry_get: Get full details for an MCP server package [public] - thinkneo_registry_publish: Publish your MCP server to the marketplace [auth required] - thinkneo_registry_review: Rate and review an MCP server [auth required] - thinkneo_registry_install: Get installation config for any MCP client [public] Free tier: 500 calls/month, auto-provisioned API key. For authenticated tools, users must supply a ThinkNEO API key as Bearer token. To get your ThinkNEO API key, visit https://thinkneo.ai/pricing Visit https://thinkneo.ai or contact hello@thinkneo.ai to get started.

Known tools 68

thinkneo_check_spend

Check AI spend summary for a workspace, team, or project.

Inferred read-only

thinkneo_complete

Run a governed LLM completion through the ThinkNEO AI gateway.

Inferred read-only

thinkneo_read_memory

Read Claude Code project memory files.

Inferred read-only

thinkneo_write_memory

Write or update a Claude Code project memory file (.

Potential side effects

thinkneo_evaluate_guardrail

Evaluate a prompt or text against ThinkNEO guardrail policies before sending it to an AI provider.

Inferred read-only

thinkneo_check

Free-tier prompt safety check.

Inferred read-only

thinkneo_check_policy

Check AI governance policies including model access, budget limits, data controls, and agent governance from the ThinkNEO gateway.

Inferred read-only

thinkneo_get_budget_status

Check AI budget status including spend vs limit, forecast, and chargeback data from the ThinkNEO gateway.

Inferred read-only

thinkneo_list_alerts

List active alerts for budget, policy, SLA, and security from the ThinkNEO gateway.

Inferred read-only

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.

Inferred read-only

thinkneo_provider_status

Get real-time health and performance status of AI providers routed through the ThinkNEO gateway.

Inferred read-only

thinkneo_schedule_demo

Schedule a demo or discovery call with the ThinkNEO team.

Inferred read-only

thinkneo_usage

Returns usage statistics for your ThinkNEO API key.

Inferred read-only

thinkneo_route_model

AI Smart Router — find the cheapest model that meets your quality threshold.

Inferred read-only

thinkneo_get_savings_report

Get your AI cost savings report.

Inferred read-only

thinkneo_simulate_savings

Simulate how much your organization would save on AI costs using ThinkNEO Smart Router.

Inferred read-only

thinkneo_evaluate_trust_score

Evaluate your organization AI Trust Score (0-100) across 10 dimensions: Guardrails, PII Protection, Injection Defense, Audit Trail, Compliance, Model Governance, Cost Controls, Outcome Validation, Observability, and Smart Routing.

Inferred read-only

thinkneo_get_trust_badge

Get a public AI Trust Score badge by report token.

Inferred read-only

thinkneo_registry_search

Search the ThinkNEO MCP Marketplace — the npm for MCP tools.

Inferred read-only

thinkneo_registry_get

Get full details for an MCP server package from the ThinkNEO Marketplace.

Inferred read-only

thinkneo_registry_publish

Publish an MCP server to the ThinkNEO Marketplace.

Potential side effects

thinkneo_registry_review

Rate and review an MCP server in the ThinkNEO Marketplace.

Inferred read-only

thinkneo_registry_install

Get installation config for an MCP server from the ThinkNEO Marketplace.

Inferred read-only

thinkneo_bridge_mcp_to_a2a

Bridge MCP tool registry to A2A format.

Inferred read-only

thinkneo_bridge_a2a_to_mcp

Bridge A2A agents to MCP tool format.

Inferred read-only

thinkneo_bridge_generate_agent_card

Generate an A2A Agent Card from registry data.

Inferred read-only

thinkneo_bridge_list_mappings

List all MCP <-> A2A bridge mappings for a tenant.

Inferred read-only

thinkneo_start_trace

Start a new agent observability trace.

Inferred read-only

thinkneo_log_event

Log an event within an active agent trace.

Inferred read-only

thinkneo_end_trace

End an active agent trace and get the session summary.

Inferred read-only

thinkneo_get_trace

Retrieve the full trace for an agent session.

Inferred read-only

thinkneo_get_observability_dashboard

Get the agent observability dashboard — aggregated metrics for your AI agents.

Inferred read-only

thinkneo_set_baseline

Define the pre-AI cost baseline for a business process.

Inferred read-only

thinkneo_log_decision

Log a business decision made by an AI agent.

Inferred read-only

thinkneo_log_risk_avoidance

Log a risk event that was blocked or avoided by the governance layer.

Inferred read-only

thinkneo_decision_cost

Analyze cost-per-decision for AI agents.

Inferred read-only

thinkneo_agent_roi

Calculate ROI per AI agent.

Inferred read-only

thinkneo_business_impact

Executive business impact dashboard.

Inferred read-only

thinkneo_a2a_log

Retrieve A2A (agent-to-agent) interaction logs from the live gateway.

Inferred read-only

thinkneo_a2a_policy

Retrieve A2A interaction policies from the live gateway.

Inferred read-only

thinkneo_a2a_flow

Visualize agent-to-agent communication flow.

Inferred read-only

thinkneo_a2a_audit

Retrieve immutable audit trail for A2A interactions with hash verification.

Inferred read-only

thinkneo_detect_waste

Detect waste and inefficiency in AI operations.

Inferred read-only

thinkneo_register_claim

Inferred read-only

thinkneo_verify_claim

Trigger verification of a registered action claim.

Inferred read-only

thinkneo_get_proof

Retrieve the immutable proof record for a verified claim.

Inferred read-only

thinkneo_verification_dashboard

Aggregated outcome verification metrics — verification rates, failure patterns, agent reliability rankings, and daily trends.

Inferred read-only

thinkneo_benchmark_report

View the outcome benchmark matrix — real quality scores per provider/model/task_type based on verified outcomes, not static estimates.

Inferred read-only

thinkneo_benchmark_compare

Compare providers side-by-side for a specific task type.

Inferred read-only

thinkneo_router_explain

Explain why the Smart Router would choose a specific model for a task type.

Inferred read-only

thinkneo_compliance_generate

Generate a compliance report for regulatory frameworks (EU AI Act, ISO 42001, SOC2, NIST).

Inferred read-only

thinkneo_sla_define

Define or update an SLA (Service Level Agreement) for an AI agent.

Potential side effects

thinkneo_sla_status

Check current SLA status for all agents or a specific agent.

Inferred read-only

thinkneo_sla_breaches

View SLA breach history — which SLAs were breached, by which agents, actual vs threshold values, and resolution status.

Inferred read-only

thinkneo_sla_dashboard

SLA overview dashboard — all agents, current status, error budgets, and recent breaches (7d).

Inferred read-only

thinkneo_audit_export

Export audit events from the live gateway.

Inferred read-only

thinkneo_compare_models

Compare available AI models from the live gateway catalog.

Inferred read-only

thinkneo_count_tokens

Estimate token count for text (chars/4 approximation).

Inferred read-only

thinkneo_optimize_prompt

Analyze prompt and suggest optimizations with live metrics context.

Inferred read-only

thinkneo_rotate_key

Instruct the gateway to rotate an API key.

Inferred read-only

thinkneo_manage_secrets

Check connector grants and secrets status from the gateway.

Inferred read-only

thinkneo_cache_status

Get semantic cache stats from the live gateway runtime metrics.

Inferred read-only

thinkneo_detect_injection

Detect prompt injection attempts in text using guardrail patterns.

Inferred read-only

thinkneo_check_pii_international

Detect international PII across 30+ document types from 15+ countries: Brazil (CPF, CNPJ, RG, PIS), USA (SSN, EIN, ITIN, Passport), UK (NINO, UTR), Canada (SIN), EU (IBAN, VAT), Germany (Tax-ID), France (INSEE), Spain (DNI/NIE), Italy (Codice Fiscale), Argentina (CUIT), Mexico (CURP/RFC), Australia (TFN/ABN), India (Aadhaar/PAN), China (ID), Japan (My Number), and credit cards (Luhn validated).

Inferred read-only

thinkneo_alert_rule_list

List your configurable Monitor Agent alert rules.

Inferred read-only

thinkneo_alert_rule_create

Create a Monitor Agent alert rule.

Potential side effects

thinkneo_alert_rule_delete

Delete a Monitor Agent alert rule by its rule_id.

Potential side effects

thinkneo_alert_rule_test

Send a test notification through a rule's configured channels to confirm delivery (email/discord/whatsapp).

Potential side effects

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.thinkneo-control-plane]
url = "https://mcp.thinkneo.ai/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "thinkneo-control-plane": {
      "type": "http",
      "url": "https://mcp.thinkneo.ai/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: thinkneo-control-plane
Remote MCP URL: https://mcp.thinkneo.ai/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "thinkneo-control-plane": {
      "url": "https://mcp.thinkneo.ai/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "thinkneo-control-plane": {
      "type": "http",
      "url": "https://mcp.thinkneo.ai/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "thinkneo-control-plane",
  "transport": "streamable-http",
  "url": "https://mcp.thinkneo.ai/mcp"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

TRUST AND VERIFICATION EVIDENCE

Loading Trust v2 evidence…

Checking the associated registrable domain. The BuiltWith key remains server-side.

Indexed

Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.