fast-mcp-gatekeeper
by kartik-modi
README.md
# ๐ก๏ธ fast-mcp-gatekeeper
> **The Zero-Latency Security & Policy Proxy for Model Context Protocol (MCP)**
> Powered by TypeSafe AI's **Jev** System 1 Decision Model.
[](https://npmjs.org)
[](https://opensource.org/licenses/MIT)
[](https://typesafe.ai)
As coding assistants (Cursor, Claude Desktop, Antigravity) gain access to local tools via the **Model Context Protocol (MCP)**, granting unconstrained access to your filesystem, terminal, and database is risky.
Existing security checks run through heavy LLMs add **2,000โ3,000ms** of latency to *every single tool call*, crippling agent responsiveness.
**`fast-mcp-gatekeeper`** acts as an ultra-fast stdio proxy sitting between your MCP client and any MCP server. It inspects all JSON-RPC `tools/call` packets in **<50 milliseconds**, detecting path traversals, command injections, and credential leaks without slowing down your AI workflow.
---
## โจ Features
- โก **Sub-50ms Overhead:** Jev evaluates tool arguments in a single non-autoregressive pass.
- ๐ **Automatic Interception:** Returns standard MCP JSON-RPC `-32001` error codes before the downstream tool can ever execute.
- ๐ **Automatic Token Sanitization:** Redacts leaked API keys (`sk-...`, Bearer tokens, passwords) on the fly with the `redact` policy.
- ๐ **Universal Compatibility:** Works with any stdio-based MCP server (e.g. `@modelcontextprotocol/server-filesystem`, Postgres, Git, GitHub).
---
## ๐ Quick Setup with Claude Desktop or Cursor
In your `claude_desktop_config.json` or Cursor MCP settings, simply prepend `fast-mcp-gatekeeper --` to your server command:
```json
{
"mcpServers": {
"filesystem": {
"command": "npx",
"args": [
"-y",
"fast-mcp-gatekeeper",
"--",
"npx",
"-y",
"@modelcontextprotocol/server-filesystem",
"/Users/username/workspace"
]
}
}
}
```
---
## ๐งช CLI Inspection Demo
You can inspect any simulated tool call directly from the terminal:
```bash
npx fast-mcp-gatekeeper --inspect '{"name": "read_file", "arguments": {"path": "/etc/passwd"}}'
```
**Output:**
```json
{
"toolName": "read_file",
"isMalicious": true,
"maliciousProbability": 0.99,
"threatLevel": "critical",
"policy": "block",
"reason": "BLOCKED: High-risk security policy violation detected in tool 'read_file'.",
"latencyMs": 41
}
```
---
## ๐ License
MIT ยฉ Kartik Modi
This server cannot be deployed
Maintenance
ActivityMaintained
ResponsivenessNo issues