# ThinkNEO Control Plane (remote · mcp.thinkneo.ai)

Enterprise AI Control Plane: governance, guardrails, spend tracking, compliance & smart routing.

- Trust score: 68/100 (medium)
- Change this week: +4
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- remote · `mcp.thinkneo.ai`: 68/100 (this document), [markdown](https://verifymcp.io/servers/ai-thinkneo-control-plane/mcp.md), [page](https://verifymcp.io/servers/ai-thinkneo-control-plane/mcp)

## Channel facts

- Endpoint: `https://mcp.thinkneo.ai/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.29.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-08-03.

- **Endpoint Security**: 63/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation check failed: no authorisation is required to call this server, and it exposes a tool marked destructive (thinkneo_rotate_key).
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 69/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (fair).
  - Context-footprint check failed: tool/resource definitions use about 7973 tokens (~113/item across 70 items; 68 tools + 2 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 27/100
  - Stability observed for 8 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### Claude

```bash
claude mcp add --transport http ai-thinkneo-control-plane https://mcp.thinkneo.ai/mcp
```

### Codex

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

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "ai-thinkneo-control-plane": {
      "type": "remote",
      "url": "https://mcp.thinkneo.ai/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add ai-thinkneo-control-plane --url https://mcp.thinkneo.ai/mcp --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  ai-thinkneo-control-plane:
    url: "https://mcp.thinkneo.ai/mcp"
```

### Other

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

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-08-03 (score 68, +1)

No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-07-31 (score 67, +1)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-30 (score 66, +1)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-29 (score 65, +1)

No change was recorded against any check on this day. Stability & Change Management went from 7 to 10. That category is still filling its 30-day observation window: 2 days of observed history at the previous scan, 3 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-07-27 (score 64, +1)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-26 (score 63)

First indexed and scored.

## MCP tools (68)

### `thinkneo_check_spend` (~95 tokens)

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.

Input parameters:

- `group_by` (string): Group costs by: provider, model, team, or project
- `period` (string): Time period: today, this-week, this-month, last-month
- `workspace` (string): Workspace name or ID

Output parameters:

- `result` (string)

### `thinkneo_complete` (~131 tokens)

Run a governed LLM completion through the ThinkNEO AI gateway. The request is authorized, classified, and policy-checked against your workspace governance BEFORE any provider is called — a blocked prompt never reaches the model. Tenant/workspace are derived from your API key.

Input parameters:

- `max_tokens` (integer): Max output tokens
- `model` (string): provider/model, e.g. 'anthropic/claude-haiku-4-5-20251001'
- `prompt` (string, required): The user prompt to complete
- `system`: Optional system instruction
- `temperature` (number): Sampling temperature

Output parameters:

- `result` (string)

### `thinkneo_read_memory` (~112 tokens)

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.

Input parameters:

- `filename`: Name of the memory file to read (e.g. 'user_fabio.md', 'project_thinkneodo_droplet.md'). Omit to get the MEMORY.md index with all available files.

Output parameters:

- `result` (string)

### `thinkneo_write_memory` (~178 tokens)

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.

Input parameters:

- `content` (string, required): Full markdown content to write to the file.
- `filename` (string, required): Name of the memory file to write (e.g. 'user_fabio.md', 'project_thinkneodo_droplet.md'). Must end in .md.

Output parameters:

- `result` (string)

### `thinkneo_evaluate_guardrail` (~117 tokens)

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.

Input parameters:

- `guardrail_mode` (string): Evaluation mode: 'monitor' (log violations only) or 'enforce' (block the request on violation)
- `text` (string, required): The prompt or text content to evaluate for policy violations (max 32,000 characters)
- `workspace` (string, required): Workspace whose guardrail policies to apply for this evaluation

Output parameters:

- `result` (string)

### `thinkneo_check` (~79 tokens)

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.

Input parameters:

- `text` (string, required): The text or prompt to check for safety issues (max 50,000 characters)

Output parameters:

- `result` (string)

### `thinkneo_check_policy` (~45 tokens)

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

Input parameters:

- `workspace` (string): Workspace name or ID

Output parameters:

- `result` (string)

### `thinkneo_get_budget_status` (~44 tokens)

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

Input parameters:

- `workspace` (string): Workspace name or ID

Output parameters:

- `result` (string)

### `thinkneo_list_alerts` (~61 tokens)

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

Input parameters:

- `severity` (string): Filter by severity: critical, high, medium, low, all
- `workspace` (string): Workspace name or ID

Output parameters:

- `result` (string)

### `thinkneo_get_compliance_status` (~89 tokens)

Get compliance status including framework coverage (EU AI Act, ISO 42001, NIST AI RMF, SOC 2) and governance assessments from the ThinkNEO gateway.

Input parameters:

- `framework` (string): Filter by framework: eu-ai-act, iso-42001, nist-ai-rmf, soc2, all
- `workspace` (string): Workspace name or ID

Output parameters:

- `result` (string)

### `thinkneo_provider_status` (~92 tokens)

Get real-time health and performance status of AI providers routed through the ThinkNEO gateway. Shows latency, error rates, and availability. No authentication required.

Input parameters:

- `provider`: Specific provider to check: openai, anthropic, google, mistral, xai, cohere, or together. Omit to get status for all providers.
- `workspace`: Workspace context for provider routing configuration (optional)

Output parameters:

- `result` (string)

### `thinkneo_schedule_demo` (~178 tokens)

Schedule a demo or discovery call with the ThinkNEO team. Collects contact information and preferences. No authentication required.

Input parameters:

- `company` (string, required): Company or organization name
- `contact_name` (string, required): Full name of the person requesting the demo
- `context`: Additional context such as current AI providers used, request volume, or specific use case
- `email` (string, required): Business email address to receive follow-up from the ThinkNEO team
- `interest`: Primary area of interest: guardrails, finops, observability, governance, or full platform
- `preferred_dates`: Preferred meeting dates, times, and timezone (e.g., 'Tuesdays or Thursdays, 9-11am EST')
- `role`: Contact's role: cto, cfo, security, engineering, or other

Output parameters:

- `result` (string)

### `thinkneo_usage` (~55 tokens)

Returns usage statistics for your ThinkNEO API key. Shows calls today, this week, this month, monthly limit, remaining calls, top tools used, estimated cost, and current tier. Works without authentication (returns general info).

Output parameters:

- `result` (string)

### `thinkneo_route_model` (~255 tokens)

AI Smart Router — find the cheapest model that meets your quality threshold. Specify your task type and quality requirements, and ThinkNEO will recommend the optimal model with estimated cost and savings vs premium models. Supports 17+ models across Anthropic, OpenAI, Google, Meta, Mistral, DeepSeek, Alibaba, Cohere, and xAI. Requires authentication.

Input parameters:

- `budget_per_request`: Maximum budget per request in USD. Omit for no limit.
- `estimated_tokens` (integer): Estimated total tokens for the request (input + output). Default 1000.
- `max_latency_ms`: Maximum acceptable latency in milliseconds. Omit for no limit.
- `preferred_providers`: Comma-separated list of preferred providers (e.g., 'openai,anthropic'). These will be prioritized at similar cost.
- `quality_threshold` (integer): Minimum quality score required (0-100). Default 85 = enterprise-grade.
- `task_type` (string, required): The type of AI task: summarization, classification, code_generation, chat, analysis, translation, or embedding
- `text_sample`: Optional sample text for better routing. Helps estimate token count and task complexity. Max 500 characters.

Output parameters:

- `result` (string)

### `thinkneo_get_savings_report` (~90 tokens)

Get your AI cost savings report. Shows total requests routed, original cost (what you'd have paid with premium models), actual cost, total savings, savings percentage, breakdown by task type, and model distribution. Requires authentication.

Input parameters:

- `period` (string): Report period: '7d' (7 days), '30d' (30 days), or '90d' (90 days)

Output parameters:

- `result` (string)

### `thinkneo_simulate_savings` (~221 tokens)

Simulate how much your organization would save on AI costs using ThinkNEO Smart Router. Enter your current monthly AI spend and primary model, and see estimated monthly and annual savings with a recommended model mix. No authentication required — try it now!

Input parameters:

- `monthly_ai_spend` (number, required): Your current monthly AI API spend in USD (e.g., 5000.00)
- `primary_model` (string): Your primary model: 'gpt-4o', 'claude-opus-4', 'claude-sonnet-4', 'gpt-4.1', or 'gemini-2.5-pro'
- `task_distribution`: JSON string of task distribution, e.g., '{"chat": 0.3, "summarization": 0.2, "code_generation": 0.2, "classification": 0.15, "analysis": 0.1, "translation": 0.05}'. Values should sum to ~1.0. Omit fo…

Output parameters:

- `result` (string)

### `thinkneo_evaluate_trust_score` (~144 tokens)

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. Returns a score, detailed breakdown, badge level (Platinum/Gold/Silver/Bronze/Unrated), and actionable recommendations. Score is valid for 30 days. Generates a public badge URL for embedding in websites and documentation. Part of the 'From Prompt to Proof' framework. Requires authentication.

Input parameters:

- `org_name` (string, required): Organization name for the trust score badge (e.g., 'Acme Corp')

Output parameters:

- `result` (string)

### `thinkneo_get_trust_badge` (~76 tokens)

Get a public AI Trust Score badge by report token. Returns the organization name, score, badge level, and validity period. Use the badge URL to embed the trust badge in websites and documentation. No authentication required.

Input parameters:

- `report_token` (string, required): The report token from a trust score evaluation (URL-safe string)

Output parameters:

- `result` (string)

### `thinkneo_registry_search` (~162 tokens)

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.

Input parameters:

- `category`: Filter by category: governance, security, data, development, productivity, communication, analytics, devops, finance, marketing, other
- `limit` (integer): Max results to return (1-100, default 20)
- `min_rating`: Minimum average rating (1.0-5.0)
- `query` (string): Search query — matches name, description, tags, and tool names
- `verified_only` (boolean): If true, return only verified packages

Output parameters:

- `result` (string)

### `thinkneo_registry_get` (~73 tokens)

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.

Input parameters:

- `name` (string, required): Package name (e.g. 'thinkneo-control-plane', 'filesystem', 'github')

Output parameters:

- `result` (string)

### `thinkneo_registry_publish` (~288 tokens)

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.

Input parameters:

- `categories`: Categories: governance, security, data, development, productivity, communication, analytics, devops, finance, marketing, other
- `description` (string, required): Short description of what this MCP server does (max 500 chars)
- `display_name` (string, required): Human-readable display name
- `endpoint_url` (string, required): MCP server endpoint URL (e.g. https://my-server.com/mcp)
- `license` (string): License (e.g. MIT, Apache-2.0)
- `name` (string, required): Package name (lowercase, hyphens allowed, e.g. 'my-mcp-server')
- `readme` (string): Full readme/documentation in markdown
- `repo_url` (string): Source code repository URL
- `tags`: Tags for discoverability (e.g. ['ai', 'governance', 'security'])
- `transport` (string): Transport type: streamable-http, sse, or stdio

Output parameters:

- `result` (string)

### `thinkneo_registry_review` (~121 tokens)

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.

Input parameters:

- `comment` (string): Review comment (max 2000 chars)
- `name` (string, required): Package name to review
- `rating` (integer, required): Rating from 1 (poor) to 5 (excellent)

Output parameters:

- `result` (string)

### `thinkneo_registry_install` (~95 tokens)

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.

Input parameters:

- `client_type` (string): Your MCP client: claude-desktop, cursor, windsurf, or custom
- `name` (string, required): Package name to install (e.g. 'thinkneo-control-plane')

Output parameters:

- `result` (string)

### `thinkneo_bridge_mcp_to_a2a` (~45 tokens)

Bridge MCP tool registry to A2A format. Shows tool-to-skill mappings.

Input parameters:

- `tool_name` (string): MCP tool name to bridge

Output parameters:

- `result` (string)

### `thinkneo_bridge_a2a_to_mcp` (~40 tokens)

Bridge A2A agents to MCP tool format.

Input parameters:

- `agent_name` (string): A2A agent name to map

Output parameters:

- `result` (string)

### `thinkneo_bridge_generate_agent_card` (~35 tokens)

Generate an A2A Agent Card from registry data.

Input parameters:

- `agent_id` (string, required): Agent ID from registry

Output parameters:

- `result` (string)

### `thinkneo_bridge_list_mappings` (~26 tokens)

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

Output parameters:

- `result` (string)

### `thinkneo_start_trace` (~143 tokens)

Start a new agent observability trace. Creates a session that tracks all tool calls, model calls, decisions, and errors for an AI agent run. Returns a session_id to use with thinkneo_log_event and thinkneo_end_trace. Requires authentication.

Input parameters:

- `agent_name` (string, required): Name of the agent being traced (e.g., 'marketing-agent', 'support-bot')
- `agent_type` (string): Type of agent: 'assistant', 'autonomous', 'workflow', 'pipeline', or 'generic'
- `metadata`: Optional dict with additional context (e.g., {"task": "email-draft", "user_id": "u123"})

Output parameters:

- `result` (string)

### `thinkneo_log_event` (~246 tokens)

Log an event within an active agent trace. Supports event types: tool_call, model_call, decision, error, pii_access, guardrail_triggered. Returns event_id and running session cost. Requires authentication.

Input parameters:

- `cost` (number): Estimated cost in USD for this event (e.g., 0.003 for an API call)
- `event_type` (string, required): Event type: 'tool_call', 'model_call', 'decision', 'error', 'pii_access', or 'guardrail_triggered'
- `input_summary`: Brief summary of the input (max 500 chars, truncated if longer)
- `latency_ms` (integer): Latency in milliseconds for this event
- `metadata`: Optional dict with additional event context
- `model_name`: Model used (for model_call events, e.g., 'gpt-4o', 'claude-sonnet-4-20250514')
- `output_summary`: Brief summary of the output (max 500 chars, truncated if longer)
- `session_id` (string, required): Session ID from thinkneo_start_trace
- `tool_name`: Name of the tool called (for tool_call events)

Output parameters:

- `result` (string)

### `thinkneo_end_trace` (~87 tokens)

End an active agent trace and get the session summary. Returns total cost, duration, tool/model call counts, and event count. Triggers post-session anomaly detection (cost spikes, error rate). Requires authentication.

Input parameters:

- `session_id` (string, required): Session ID from thinkneo_start_trace
- `status` (string): Final session status: 'success', 'failure', or 'timeout'

Output parameters:

- `result` (string)

### `thinkneo_get_trace` (~67 tokens)

Retrieve the full trace for an agent session. Returns the complete timeline of events (tool calls, model calls, decisions, errors), session metadata, total cost, duration, and any alerts triggered. Requires authentication.

Input parameters:

- `session_id` (string, required): Session ID to retrieve the trace for

Output parameters:

- `result` (string)

### `thinkneo_get_observability_dashboard` (~94 tokens)

Get the agent observability dashboard — aggregated metrics for your AI agents. Includes total sessions, events, cost, error rate, latency, top agents, top tools, active alerts, and cost trend over time. Like Datadog, but for AI agents. Requires authentication.

Input parameters:

- `period` (string): Time period: '1h', '24h', '7d', or '30d'

Output parameters:

- `result` (string)

### `thinkneo_set_baseline` (~199 tokens)

Define the pre-AI cost baseline for a business process. Example: 'customer_support_ticket costs $12 per ticket and takes 15 minutes without AI'. This baseline is used to calculate ROI when agents handle the same process. Call this once per process to establish the comparison point.

Input parameters:

- `avg_duration_minutes`: Average time in minutes for one unit without AI, e.g. 15
- `cost_per_unit_usd` (number, required): Pre-AI cost per unit in USD, e.g. 12.00 for a $12 support ticket
- `notes`: Additional context about this baseline
- `process_name` (string, required): Name of the business process, e.g. 'customer_support_ticket', 'loan_review', 'content_moderation'
- `unit_label` (string): What one unit represents, e.g. 'ticket', 'review', 'decision', 'document'
- `workspace` (string): Workspace identifier

Output parameters:

- `result` (string)

### `thinkneo_log_decision` (~271 tokens)

Log a business decision made by an AI agent. Tracks the AI cost and the business value generated. If a baseline exists for the process, value is auto-calculated from the baseline cost. Example: agent 'support-bot' resolved a 'customer_support_ticket' at $0.03 AI cost, replacing a $12 human-handled ticket. ROI: 400:1.

Input parameters:

- `agent_name` (string, required): Name of the AI agent that made the decision, e.g. 'support-bot', 'loan-reviewer'
- `ai_cost_usd` (number): Actual AI cost for this decision in USD, e.g. 0.03
- `confidence`: Confidence score 0.0-1.0
- `decision_type` (string, required): Type of decision, e.g. 'ticket_resolved', 'loan_approved', 'content_reviewed'
- `metadata`: JSON string with additional context
- `outcome` (string): Result: 'success', 'escalated', 'rejected', 'error'
- `process_name`: Links to a baseline process for auto ROI calculation
- `value_generated_usd`: Explicit business value in USD. If omitted and process_name has a baseline, auto-calculated.
- `workspace` (string): Workspace identifier

Output parameters:

- `result` (string)

### `thinkneo_log_risk_avoidance` (~195 tokens)

Log a risk event that was blocked or avoided by the governance layer. Quantifies the estimated dollar impact of the avoided risk. Examples: PII leak blocked (est. $50K GDPR fine), prompt injection prevented, policy violation caught before production. If estimated_impact_usd is not provided, a default is calculated from severity.

Input parameters:

- `agent_name`: Agent involved, if applicable
- `description`: Brief description of what was blocked
- `estimated_impact_usd`: Estimated cost if this risk had materialized in USD
- `risk_type` (string, required): Type: 'pii_leak', 'injection_blocked', 'policy_violation', 'spend_limit', 'compliance_breach', 'data_exfiltration'
- `severity` (string): Severity level: 'low', 'medium', 'high', 'critical'
- `workspace` (string): Workspace identifier

Output parameters:

- `result` (string)

### `thinkneo_decision_cost` (~113 tokens)

Analyze cost-per-decision for AI agents. Shows the actual AI cost for each decision, compared to the pre-AI baseline. Answers: 'How much does each AI decision cost?' and 'How does it compare to doing it without AI?'

Input parameters:

- `agent_name`: Filter by specific agent
- `period` (string): Time period: 'today', 'this-week', 'this-month', 'all'
- `process_name`: Filter by specific process
- `workspace` (string): Workspace identifier

Output parameters:

- `result` (string)

### `thinkneo_agent_roi` (~96 tokens)

Calculate ROI per AI agent. Shows value generated vs AI cost consumed, with daily trend, success rate, and comparison to pre-AI baseline. Answers: 'Is this agent generating or consuming value?' and 'What's the ROI trend?'

Input parameters:

- `agent_name`: Specific agent to analyze. If omitted, returns all agents.
- `days` (integer): Number of days to analyze
- `workspace` (string): Workspace identifier

Output parameters:

- `result` (string)

### `thinkneo_business_impact` (~101 tokens)

Executive business impact dashboard. Returns a single view of: total value generated by AI agents, total AI cost, net ROI, risk avoided in dollars, cost per decision, top performing agents, and risk event summary. This is the report a CxO needs to justify AI investment.

Input parameters:

- `period` (string): Time period: 'this-week', 'this-month', 'this-quarter', 'all'
- `workspace` (string): Workspace identifier

Output parameters:

- `result` (string)

### `thinkneo_a2a_log` (~62 tokens)

Retrieve A2A (agent-to-agent) interaction logs from the live gateway. Shows which agents called which, actions performed, costs, and outcomes.

Input parameters:

- `limit` (integer): Max events to return
- `workspace` (string): Workspace identifier

Output parameters:

- `result` (string)

### `thinkneo_a2a_policy` (~46 tokens)

Retrieve A2A interaction policies from the live gateway. Shows allowed actions, rate limits, cost caps, and approval requirements.

Input parameters:

- `workspace` (string): Workspace identifier

Output parameters:

- `result` (string)

### `thinkneo_a2a_flow` (~45 tokens)

Visualize agent-to-agent communication flow. Shows registered agents, their approval status, and interaction patterns from the live gateway.

Input parameters:

- `workspace` (string): Workspace identifier

Output parameters:

- `result` (string)

### `thinkneo_a2a_audit` (~56 tokens)

Retrieve immutable audit trail for A2A interactions with hash verification. Each event is cryptographically chained for tamper detection.

Input parameters:

- `trace_id`: Filter by trace ID
- `workspace` (string): Workspace identifier

Output parameters:

- `result` (string)

### `thinkneo_detect_waste` (~108 tokens)

Detect waste and inefficiency in AI operations. Analyzes agent performance, A2A communication overhead, error costs, unused capacity, and cost outliers. Returns specific actionable findings like 'you are losing $3,200/month on error retries' or 'this flow is 5x more expensive than your best-performing flow'. This is the diagnostic tool that creates the buying trigger.

Input parameters:

- `days` (integer): Analysis window in days
- `workspace` (string): Workspace identifier

Output parameters:

- `result` (string)

### `thinkneo_register_claim` (~375 tokens)

Register an action claim from an AI agent. The agent declares it performed an action (e.g., sent an email, created a PR, wrote a file) and ThinkNEO will verify it actually happened. Returns a claim_id for tracking. Part of the Outcome Validation Loop — 'From Prompt to Proof'. Requires authentication.

Input parameters:

- `action` (string, required): Type of action claimed: 'email_sent', 'http_request', 'file_written', 'db_insert', 'pr_created', 'payment_processed', 'message_sent', 'api_call', 'task_completed', 'data_exported', 'notification_sent…
- `agent_name`: Name of the agent making the claim (e.g., 'marketing-agent')
- `evidence_type` (string, required): How to verify the claim: 'http_status' (check URL response), 'file_exists' (check file path), 'db_row_exists' (check database row), 'webhook' (wait for callback), 'smtp_delivery' (check email deliver…
- `metadata`: Optional verification context. For http_status: {expected_status: 200, method: 'GET'}. For file_exists: {expected_hash: 'sha256...'}. For db_row_exists: {where_column: 'id', where_value: '123'}.
- `session_id`: Optional observability session_id to link this claim to a trace
- `target` (string, required): Target of the action — what was acted upon. Examples: 'user@example.com' (email), 'https://api.example.com/endpoint' (http), '/opt/data/report.pdf' (file), 'usage_log' (db table)
- `ttl_hours` (integer): Hours until claim expires if not verified (default 24, max 168)

Output parameters:

- `result` (string)

### `thinkneo_verify_claim` (~111 tokens)

Trigger verification of a registered action claim. Runs the appropriate verification adapter (HTTP check, file check, database check, etc.) and returns the result with evidence. If already verified, returns cached result (use force=true to re-verify). Part of the Outcome Validation Loop — 'From Prompt to Proof'. Requires authentication.

Input parameters:

- `claim_id` (string, required): UUID of the claim to verify (from thinkneo_register_claim)
- `force` (boolean): Force re-verification even if already verified/failed

Output parameters:

- `result` (string)

### `thinkneo_get_proof` (~76 tokens)

Retrieve the immutable proof record for a verified claim. Includes the original claim, verification evidence, verifier identity, and a SHA-256 proof hash for tamper detection. This is the 'proof' in 'From Prompt to Proof'. Requires authentication.

Input parameters:

- `claim_id` (string, required): UUID of the claim to get proof for

Output parameters:

- `result` (string)

### `thinkneo_verification_dashboard` (~75 tokens)

Aggregated outcome verification metrics — verification rates, failure patterns, agent reliability rankings, and daily trends. Shows how reliably your AI agents are delivering verified outcomes. 'Datadog for AI outcomes'. Requires authentication.

Input parameters:

- `period` (string): Time period: '24h', '7d', or '30d'

Output parameters:

- `result` (string)

### `thinkneo_benchmark_report` (~79 tokens)

View the outcome benchmark matrix — real quality scores per provider/model/task_type based on verified outcomes, not static estimates. Shows verification rates, sample counts, and rankings. Requires authentication.

Input parameters:

- `task_type`: Filter by task type: 'summarization', 'code_generation', 'classification', 'translation', etc. Leave empty for all.

Output parameters:

- `result` (string)

### `thinkneo_benchmark_compare` (~99 tokens)

Compare providers side-by-side for a specific task type. Shows quality scores, verification rates, and rankings based on real outcomes. Requires authentication.

Input parameters:

- `providers`: Optional list of providers to compare (e.g., ['anthropic', 'openai']). Leave empty for all.
- `task_type` (string, required): Task type to compare: 'summarization', 'code_generation', 'classification', 'translation', 'analysis', 'chat'

Output parameters:

- `result` (string)

### `thinkneo_router_explain` (~101 tokens)

Explain why the Smart Router would choose a specific model for a task type. Shows both benchmark-based (real outcomes) and static quality estimates, and explains the reasoning behind the recommendation. Requires authentication.

Input parameters:

- `quality_threshold` (integer): Minimum quality score required (0-100, default 85)
- `task_type` (string, required): Task type: 'summarization', 'code_generation', 'classification', 'translation', 'analysis', 'chat'

Output parameters:

- `result` (string)

### `thinkneo_compliance_generate` (~87 tokens)

Generate a compliance report for regulatory frameworks (EU AI Act, ISO 42001, SOC2, NIST). Exports from live audit data.

Input parameters:

- `format` (string): Output format: ndjson or csv
- `framework` (string): Framework: eu-ai-act, iso-42001, soc2, nist
- `workspace` (string): Workspace identifier

Output parameters:

- `result` (string)

### `thinkneo_sla_define` (~284 tokens)

Define or update an SLA (Service Level Agreement) for an AI agent. Set accuracy, quality, cost, safety, or latency thresholds with automatic breach detection and configurable actions (alert, escalate, disable, switch_model). Like SRE SLOs but for AI agent outcomes. Requires authentication.

Input parameters:

- `agent_name` (string, required): Agent name to set SLA for (e.g., 'support-bot', 'finance-agent')
- `breach_action` (string): Action on breach: 'alert' (notify), 'escalate' (notify + flag), 'disable' (stop agent), 'switch_model' (fallback model)
- `metric` (string, required): Metric to monitor: 'accuracy' (outcome verification rate %), 'response_quality' (avg quality score), 'cost_efficiency' (cost per verified outcome), 'safety' (guardrail pass rate %), 'latency' (avg re…
- `threshold` (number, required): Target threshold value (e.g., 95.0 for 95% accuracy)
- `threshold_direction` (string): 'min' = actual must be >= threshold (for accuracy, quality). 'max' = actual must be <= threshold (for cost, latency).
- `window` (string): Rolling window: '1h', '24h', '7d', or '30d'

Output parameters:

- `result` (string)

### `thinkneo_sla_status` (~65 tokens)

Check current SLA status for all agents or a specific agent. Shows actual metric values vs thresholds, healthy/breached status, and error budget remaining. Automatically records breaches. Requires authentication.

Input parameters:

- `agent_name`: Optional: specific agent name. Leave empty for all agents.

Output parameters:

- `result` (string)

### `thinkneo_sla_breaches` (~65 tokens)

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

Input parameters:

- `agent_name`: Filter by agent name
- `days` (integer): Days to look back (default 30)

Output parameters:

- `result` (string)

### `thinkneo_sla_dashboard` (~42 tokens)

SLA overview dashboard — all agents, current status, error budgets, and recent breaches (7d). The SRE dashboard for AI agents. Requires authentication.

Output parameters:

- `result` (string)

### `thinkneo_audit_export` (~76 tokens)

Export audit events from the live gateway. Supports JSON and CSV formats with date range filtering for SIEM integration.

Input parameters:

- `end_date`: End date ISO format
- `format` (string): Output format: ndjson or csv
- `start_date`: Start date ISO format
- `workspace` (string): Workspace identifier

Output parameters:

- `result` (string)

### `thinkneo_compare_models` (~63 tokens)

Compare available AI models from the live gateway catalog.

Input parameters:

- `models` (string, required): Comma-separated model IDs to compare (e.g. gpt-4o,claude-sonnet-4-20250514,gemini-2.5-flash)

Output parameters:

- `result` (string)

### `thinkneo_count_tokens` (~33 tokens)

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

Input parameters:

- `text` (string, required): Text to estimate tokens for

Output parameters:

- `result` (string)

### `thinkneo_optimize_prompt` (~33 tokens)

Analyze prompt and suggest optimizations with live metrics context.

Input parameters:

- `prompt` (string, required): Prompt text to analyze

Output parameters:

- `result` (string)

### `thinkneo_rotate_key` (~37 tokens)

Instruct the gateway to rotate an API key.

Input parameters:

- `key_prefix` (string, required): First 8 chars of the key to rotate

Output parameters:

- `result` (string)

### `thinkneo_manage_secrets` (~21 tokens)

Check connector grants and secrets status from the gateway.

Output parameters:

- `result` (string)

### `thinkneo_cache_status` (~21 tokens)

Get semantic cache stats from the live gateway runtime metrics.

Output parameters:

- `result` (string)

### `thinkneo_detect_injection` (~47 tokens)

Detect prompt injection attempts in text using guardrail patterns. Also retrieves live guardrails_blocked stats from the gateway.

Input parameters:

- `text` (string, required): Text to analyze for injection attempts

Output parameters:

- `result` (string)

### `thinkneo_check_pii_international` (~226 tokens)

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). Required for LGPD/GDPR/HIPAA compliance. No authentication required.

Input parameters:

- `countries` (array): Filter by country codes (BR, US, UK, CA, EU, DE, FR, ES, IT, AR, MX, AU, IN, CN, JP, INTL). Empty = all.
- `text` (string, required): Text to scan for PII (max 100,000 chars)

Output parameters:

- `result` (string)

### `thinkneo_alert_rule_list` (~86 tokens)

List your configurable Monitor Agent alert rules. Each rule watches a metric (e.g. an API key reaching a % of its budget, workspace spend, error rate) and notifies your channels (email/discord/whatsapp) when it fires. Requires an admin API key.

Input parameters:

- `workspace` (string): Workspace id (optional — defaults to the API key's workspace)

Output parameters:

- `result` (string)

### `thinkneo_alert_rule_create` (~287 tokens)

Create a Monitor Agent alert rule. Example: notify by email when API key 'X' reaches 75% of its budget → metric=key_spend_pct_of_budget, operator=gte, threshold=75, scope_value=<api_key_id>, budget_usd=<key budget>. Requires an admin API key.

Input parameters:

- `budget_usd` (number): Key budget in USD — required for key_spend_pct_of_budget
- `channels` (string): Comma-separated: email, discord_webhook, whatsapp
- `cooldown_minutes` (integer): Minimum minutes between firings
- `metric` (string, required): One of: key_spend_24h_usd, key_spend_30d_usd, key_spend_pct_of_budget, workspace_error_rate_pct, workspace_max_rps, workspace_requests, workspace_spend_24h_usd, workspace_spend_30d_usd
- `name` (string, required): Human-readable rule name
- `operator` (string): Comparison: gte, gt, lte, lt, eq
- `scope_value` (string): API key id — required for key_* metrics
- `severity` (string): low, medium, high, critical
- `threshold` (number, required): Threshold value to compare the metric against
- `workspace` (string): Workspace id (optional — defaults to the API key's workspace)

Output parameters:

- `result` (string)

### `thinkneo_alert_rule_delete` (~67 tokens)

Delete a Monitor Agent alert rule by its rule_id. Requires an admin API key.

Input parameters:

- `rule_id` (string, required): The rule_id to delete (from thinkneo_alert_rule_list)
- `workspace` (string): Workspace id (optional — defaults to the API key's workspace)

Output parameters:

- `result` (string)

### `thinkneo_alert_rule_test` (~77 tokens)

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

Input parameters:

- `rule_id` (string, required): The rule_id to test (from thinkneo_alert_rule_list)
- `workspace` (string): Workspace id (optional — defaults to the API key's workspace)

Output parameters:

- `result` (string)

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/ai-thinkneo-control-plane/mcp#diagnostics

## Score history

- 2026-08-03: 68
- 2026-08-02: 67
- 2026-08-01: 67
- 2026-07-31: 67
- 2026-07-30: 66
- 2026-07-29: 65
- 2026-07-28: 64
- 2026-07-27: 64
- 2026-07-26: 63

## Links

- Remote endpoint: https://mcp.thinkneo.ai/mcp
- Repository: https://github.com/thinkneo-ai/mcp-server
- Website: https://thinkneo.ai/
- Changelog RSS feed: https://verifymcp.io/servers/ai-thinkneo-control-plane/mcp/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/ai-thinkneo-control-plane/mcp/changelog.json
- HTML version of this page: https://verifymcp.io/servers/ai-thinkneo-control-plane/mcp