Install
$ agentstack add mcp-intutic-intutic Open-source listing, not yet scanned by AgentStack. Follow the source repository for install instructions.
Security review
⚠ Flagged1 finding(s); flagged for manual review. · v0.1.0 How review works →
- • Prompt-injection patterns
- • Secret / credential exfiltration
- • Dangerous shell & filesystem operations
- • Untrusted network calls
- • Known-malicious package signatures
- high Destructive filesystem operation.
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Intutic — The Circuit Breaker for AI Agents
Real-time security, secret DLP, and loop burn prevention for autonomous AI coding agents.
[](https://github.com/intutic/intutic) [](https://opensource.org/licenses/MIT) [](https://docs.intutic.ai) [](https://github.com/intutic/intutic/actions) [](https://github.com/intutic/intutic/pulls)
[Quickstart](#-30-second-quickstart) • [Architecture](#%EF%B8%8F-architecture) • [Key Features](#-key-features) • [Supported Harnesses](#-supported-harnesses) • Docs
💡 Why Intutic?
Existing AI observability tools (like LangSmith or Portkey) are passive. They record execution logs after an agent leaks a secret, deletes files, or loops into hundreds of dollars of API spend.
Intutic is an active, low-latency circuit breaker. It sits in the tool-call path between your AI agents and local shell/production APIs. Every tool execution passes through a sub-5ms policy evaluation chain — blocking dangerous commands before they run and steering agentic loops in real time.
🏗️ Architecture
Intutic runs as a high-performance local or self-hosted proxy (written in Rust) alongside a lightweight bidirectional config sync daemon (sync-daemon):
flowchart TD
subgraph DevEnvironment[" 💻 Developer Environment "]
Agent["🤖 AI Coding Agent(Claude Code, Cursor, Aider, LangGraph)"]
SOP["📝 Local SOP Rules(CLAUDE.md / .cursorrules / SKILL.md)"]
end
subgraph HotPathProxy[" ⚡ Intutic Hot-Path Proxy (:4000) "]
Engine["🔒 WASM Policy Engine(<5ms Evaluation Latency)"]
DLP["🔐 Secret DLP & Masking"]
PCAS["🛡️ PCAS Action PrimitivesBYPASS | ENHANCE | HIJACK | KILL"]
end
subgraph SyncDaemon[" 🔄 Sync Daemon "]
Reconcile["Bidirectional Config Reconciler(Harness Config Sync)"]
end
subgraph UpstreamProviders[" 🌐 Upstream Providers "]
Providers["Anthropic API / OpenAI / LiteLLM / Ollama"]
end
Agent -->|1. Tool Call / Prompt| HotPathProxy
SOP -->|2. Rule Sync| Reconcile
Reconcile -->|3. Hot-Reload Rules| Engine
HotPathProxy -->|4. Clean Request| UpstreamProviders
Engine -->|5. Block/Hijack Verdict| Agent
⚡ 30-Second Quickstart
1. Install the CLI & Native Proxy Gateway
# Install global CLI and native Rust proxy binary
npm install -g @intutic/cli @intutic/proxy
# Or run the native proxy directly on-demand
npx @intutic/proxy
2. Connect Your Workspace
Run intutic connect inside your project folder. This boots the local high-speed Rust proxy on port 4000 and auto-detects installed coding assistants:
intutic connect
3. Route Any Agent to Intutic
Point your favorite LLM client or agent framework to the local proxy:
export ANTHROPIC_BASE_URL="http://localhost:4000/v1"
export OPENAI_BASE_URL="http://localhost:4000/v1"
That's it! Your agent is now governed by real-time safety guardrails.
🔥 Key Features
| Feature | Description | | :--- | :--- | | ⚡ Sub-5ms WASM Engine | Policy evaluation overhead stays under 5ms, preserving typing speed and agent execution fluidity. | | 🛡️ Zero-Trust Tool Interception | Intercepts dangerous commands (rm -rf, git push --force, DROP TABLE) before they touch your system. | | 🔐 Secret DLP & Masking | Automatically redacts API keys ([REDACTED_SECRET]), AWS credentials, and tokens in prompts & tool payloads. | | 💰 Session Spend Ceilings | Prevents "loop burn" by enforcing token spending ceilings per session (e.g. $5.00 limit). | | 🔄 18+ Harness Adapters | Pre-configured support for Claude Code CLI, Cursor, Windsurf, Aider, Antigravity, and LangGraph. | | 🤖 Single & Multi-Agent Swarms | Governs single developer tools as well as multi-agent graph workflows (LangGraph, CrewAI, AutoGen). |
🛡️ The 4 PCAS Primitives
Every tool call and prompt evaluated by Intutic produces one of four PCAS Action Primitives:
┌──────────┐ ┌───────────┐ ┌────────────┐ ┌──────────┐
│ BYPASS │ │ ENHANCE │ │ HIJACK │ │ KILL │
└────┬─────┘ └─────┬─────┘ └─────┬──────┘ └────┬─────┘
│ │ │ │
▼ ▼ ▼ ▼
Direct Pass Inject Safety Redact Secrets Hard-Abort
(
[](https://github.com/intutic/intutic)
---
## 🏢 Enterprise & Commercial Licensing
For custom VPC deployments, enterprise-grade SSO/SAML, dedicated SLA support, or team compliance auditing, visit [intutic.ai](https://intutic.ai) or contact us at [support@intutic.ai](mailto:support@intutic.ai).
---
## 📄 License
This project is licensed under the [MIT License](LICENSE).
## Source & license
This open-source MCP server is cataloged on AgentStack and links to its original source — we do not rehost the code.
- **Author:** [intutic](https://github.com/intutic)
- **Source:** [intutic/intutic](https://github.com/intutic/intutic)
- **License:** MIT
- **Homepage:** https://intutic.ai
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.