Summary
This is ThinkNEO's open-source control plane server with 72 MCP tools covering spend tracking, policy enforcement, smart routing, and compliance auditing. It includes ThinkShield, a sub-1ms defense layer with detection rules for injection, auth abuse, and API scraping, plus a bidirectional bridge to Google's A2A protocol with 24 skills. The open repo gives you the tools and security middleware. The proprietary SaaS at thinkneo.ai adds governance orchestration, cryptographic audit chains, and tenant management. Reach for this when you need runtime guardrails and observability across multiple AI providers without building your own policy engine. Free tier offers 500 calls per month to test all tools.
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →
Tools
Public tool metadata for what this MCP can expose to an agent.
8 tools
thinkneo_check_spendCheck AI spend summary for a workspace, team, or project. Returns cost breakdown by provider, model, and time period. Requires authentication.5 params
Check AI spend summary for a workspace, team, or project. Returns cost breakdown by provider, model, and time period. Requires authentication.
Parameters* required
periodstringTime period for the report: today, this-week, this-month, last-month, or customdefault: this-month
end_datevalueEnd date for a custom period in ISO format (YYYY-MM-DD). Only used when period='custom'
group_bystringDimension to group costs by: provider, model, team, or projectdefault: provider
workspacestringWorkspace name or ID (e.g., 'prod-engineering', 'finance-team')
start_datevalueStart date for a custom period in ISO format (YYYY-MM-DD). Only used when period='custom'
thinkneo_evaluate_guardrailEvaluate a prompt or text against ThinkNEO guardrail policies before sending it to an AI provider. Returns risk assessment, violations found, and recommendations. Requires authentication.3 params
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.
Parameters* required
textstringThe prompt or text content to evaluate for policy violations (max 32,000 characters)
workspacestringWorkspace whose guardrail policies to apply for this evaluation
guardrail_modestringEvaluation mode: 'monitor' (log violations only) or 'enforce' (block the request on violation)default: monitor
thinkneo_check_policyCheck if a specific model, provider, or action is allowed by the governance policies configured for a workspace. Requires authentication.4 params
Check if a specific model, provider, or action is allowed by the governance policies configured for a workspace. Requires authentication.
Parameters* required
modelvalueAI model name to check (e.g., gpt-4o, claude-sonnet-4-6, gemini-2.0-flash)
actionvalueSpecific action to check (e.g., create-completion, use-tool, fine-tune)
providervalueAI provider to check (e.g., openai, anthropic, google, mistral)
workspacestringWorkspace name or ID whose governance policies to check against
thinkneo_get_budget_statusGet current budget utilization and enforcement status for a workspace. Shows spend vs limit, alert thresholds, and projected overage. Requires authentication.1 params
Get current budget utilization and enforcement status for a workspace. Shows spend vs limit, alert thresholds, and projected overage. Requires authentication.
Parameters* required
workspacestringWorkspace name or ID to retrieve current budget status for
thinkneo_list_alertsList active alerts and incidents for a workspace. Includes budget alerts, policy violations, guardrail triggers, and provider issues. Requires authentication.3 params
List active alerts and incidents for a workspace. Includes budget alerts, policy violations, guardrail triggers, and provider issues. Requires authentication.
Parameters* required
limitintegerMaximum number of alerts to return (1–100)default: 20
severitystringFilter alerts by severity level: critical, warning, info, or alldefault: all
workspacestringWorkspace name or ID to list active alerts for
thinkneo_get_compliance_statusGet compliance and audit readiness status for a workspace. Shows governance score, pending actions, and compliance gaps. Requires authentication.2 params
Get compliance and audit readiness status for a workspace. Shows governance score, pending actions, and compliance gaps. Requires authentication.
Parameters* required
frameworkstringCompliance framework to assess: soc2 (SOC 2 Type II), gdpr (GDPR), hipaa (HIPAA), or general (ThinkNEO AI governance)default: general
workspacestringWorkspace name or ID to evaluate compliance readiness for
thinkneo_provider_statusGet real-time health and performance status of AI providers routed through the ThinkNEO gateway. Shows latency, error rates, and availability. No authentication required.2 params
Get real-time health and performance status of AI providers routed through the ThinkNEO gateway. Shows latency, error rates, and availability. No authentication required.
Parameters* required
providervalueSpecific provider to check: openai, anthropic, google, mistral, xai, cohere, or together. Omit to get status for all providers.
workspacevalueWorkspace context for provider routing configuration (optional)
thinkneo_schedule_demoSchedule a demo or discovery call with the ThinkNEO team. Collects contact information and preferences. No authentication required.7 params
Schedule a demo or discovery call with the ThinkNEO team. Collects contact information and preferences. No authentication required.
Parameters* required
rolevalueContact's role: cto, cfo, security, engineering, or other
emailstringBusiness email address to receive follow-up from the ThinkNEO team
companystringCompany or organization name
contextvalueAdditional context such as current AI providers used, request volume, or specific use case
interestvaluePrimary area of interest: guardrails, finops, observability, governance, or full platform
contact_namestringFull name of the person requesting the demo
preferred_datesvaluePreferred meeting dates, times, and timezone (e.g., 'Tuesdays or Thursdays, 9-11am EST')
ThinkNEO MCP Server
Open MCP server with built-in defense layer (ThinkShield). Part of the ThinkNEO Platform — enterprise AI governance.
What This Is
An open-source MCP server providing 72 tools for AI governance, observability, and security:
- ThinkShield — Production defense layer: detection engine, 5 rule packs, runtime middleware. 145 tests, p99 < 1ms.
- 72 MCP Tools — Governance, guardrails, FinOps, smart routing, observability, compliance, outcome validation, and more.
- 24 A2A Skills — Bidirectional MCP-A2A bridge for Google's Agent-to-Agent Protocol (v0.3.0, Linux Foundation).
- Apache-2.0 — Use it, fork it, contribute.
What This Is Not
- Not the full ThinkNEO Platform. Governance orchestration, cryptographic audit chain, tenant management, and enterprise integrations are proprietary and run at thinkneo.ai.
- Not a standalone security product. ThinkShield is the defense component of a larger governed platform.
Why Open
We open-source our defense layer because real security doesn't depend on hidden rules — it depends on tested, audited, continuously improved detection plus a strong governance moat around it.
Snort. Suricata. Falco. OWASP CRS. The security industry runs on open detection. We follow that tradition.
The detection is open. The governance is proprietary. That's where the moat is.
Architecture
Open Source (this repo) Proprietary (thinkneo.ai)
┌─────────────────────────────────┐ ┌──────────────────────────────────┐
│ │ │ │
MCP Clients ────>│ 72 MCP Tools │ │ Governance Orchestration │
(Claude, Cursor, │ ├── Guardrails & Safety │────>│ ├── Policy Engine (AIRGP) │
ChatGPT, etc.) │ ├── FinOps & Smart Routing │ │ ├── Cryptographic Audit Chain │
│ ├── Observability │ │ ├── Tenant Management │
A2A Agents ─────>│ ├── Compliance & Validation │ │ ├── Enterprise Integrations │
(Google A2A) │ └── MCP-A2A Bridge (24 skills) │ │ └── SLA & Support │
│ │ │ │
│ ThinkShield Defense Layer │ │ SHA-256 Hash Chain (949K+ rows) │
│ ├── Detection Engine │ │ Stripe Billing │
│ ├── 5 Rule Packs │ │ Resend Email │
│ └── ASGI Middleware │ │ Multi-tenant Auth │
│ │ │ │
└─────────────────────────────────┘ └──────────────────────────────────┘
Apache-2.0 License Commercial License
Quickstart
# Clone
git clone https://github.com/thinkneo-ai/mcp-server.git
cd mcp-server
# Install
pip install -r requirements.txt
# Run
python -m uvicorn src.server:app --host 0.0.0.0 --port 8081
# Test
python -m pytest tests/ -q
Or with Docker:
cd deploy
docker compose up -d
Connect from Claude Desktop, Cursor, or any MCP client:
https://mcp.thinkneo.ai/mcp
Free tier: 500 calls/month, auto-provisioned API key. All 72 tools available.
Components
| Directory | Description | License |
|---|---|---|
src/tools/ | 72 MCP tools — governance, security, FinOps, observability | Apache-2.0 |
src/thinkshield/ | Defense layer — detection engine, 5 rule packs | Apache-2.0 |
tests/thinkshield/ | ThinkShield test suite — 145 tests + attack/benign fixtures | Apache-2.0 |
agent.json | A2A Agent Card — 24 skills bridged from MCP | Apache-2.0 |
ThinkShield Rule Packs
| Pack | Detects |
|---|---|
injection | SQL injection, XSS, command injection, path traversal |
auth | Credential stuffing, brute force, token replay, privilege escalation |
abuse | Rate abuse, resource exhaustion, API scraping |
recon | Path probing, tool enumeration, method probing, fingerprinting |
headers | Header anomalies, spoofing, missing security headers |
MCP Tools (72)
Governance (6) | Guardrails (3) | FinOps (4) | Smart Router (4) | Trust Score (2) | Registry (5) | Bridge (4) | Observability (5) | Business Value (6) | A2A Control (4) | Optimization (1) | Outcome Validation (4) | Policy Engine (4) | Benchmarking (3) | Compliance (2) | Agent SLA (4) | Audit Export (3) | Cache (3) | Security (5) | Tokens (1) | Memory (2) | Scheduling (1) | Alerts (1)
Full tool reference: docs/quickstart.md
MCP Spec Compliance
Complete Model Context Protocol 2024-11-05 implementation. Forward-compatible with MCP 2025-03-26.
| Capability | Status | Details |
|---|---|---|
| tools | 72 tools, full annotations | destructiveHint, readOnlyHint, idempotentHint, openWorldHint |
| resources | 2 resources | Getting Started guide, Supported Providers |
| prompts | 2 prompts with completions | governance_audit, policy_preflight |
| logging | logging/setLevel | 8 levels, per-session, audit trail |
| completions | completion/complete | workspace (auth-scoped), provider, model (provider-aware) |
Ecosystem
This repo is part of the ThinkNEO ecosystem:
| Project | Description |
|---|---|
| ThinkNEO Platform | Enterprise AI governance platform |
| AIRGP | AI Runtime Governance Protocol — open standard |
| A2ASTC | A2A Security & Trust Conformance |
| ThinkNEO SMB Hub | Business applications for SMBs |
| Robotics Governance | Robot fleet governance dashboard |
Security
See SECURITY.md for vulnerability reporting.
Contributing
See CONTRIBUTING.md.
Related
| Server | Description | Tools |
|---|---|---|
| thinkneo-control-plane | Enterprise AI Control Plane (this repo) | 72 tools |
| thinkneo-mcp-smb-products | SMB standalone products — self-serve via TNC credits | 37 tools |
License
Apache-2.0 — see LICENSE.
About
ThinkNEO AI Technology Co., Ltd. — Hong Kong CR No. 2296774.
Built by the team behind the ThinkNEO Enterprise AI Control Plane, AIRGP protocol, and A2ASTC conformance suite.
Featured
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →