Trustloop
About
Governance and audit layer for MCP tool calls. TrustLoop intercepts every AI agent action, logs it to a tamper-evident audit trail, blocks unsafe tools via kill-switch, and anchors proof to the blockchain. Drop it into any MCP setup in minutes, no code changes required.
Details
- Author
- SMJAI
- Downloads
- 280
- Categories
- Developer Tools, Security, AI
Jump to
- Kill-switch to block specific tools by name
- Audit log capturing timestamp, tool, arguments, and status
- Blockchain anchoring of audit log hashes for tamper-evident compliance
- Multi‑tenant isolation of logs and governance rules
- Built for EU AI Act and similar global mandates
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
TrustloopCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
Add the server to your claude_desktop_config.json with the provided URL and your API key, then configure policy rules to govern agent tool usage. Get your API key at trustloop.live.
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"trustloop": {
"trustloop": {
"url": "https://trustloop-production.up.railway.app/sse?api_key=<YOUR_TRUSTLOOP_API_KEY>"
}
}
}
}McpServers
{
"trustloop": {
"url": "https://trustloop-production.up.railway.app/sse?api_key=<YOUR_TRUSTLOOP_API_KEY>"
}
}What is TrustLoop?
TrustLoop is an MCP governance proxy that sits between your AI agent and its tools. Every tool call is intercepted before it executes — logged, checked against your policy rules, and either allowed or blocked.
Features
Kill-switch — Block specific tools by name before they can cause harm
Audit log — Every tool call captured with timestamp, tool name, arguments, and status
Blockchain anchoring — SHA-256 hash of audit logs recorded on-chain for tamper-evident compliance
Multi-tenant — Each customer gets isolated logs and governance rules
EU AI Act or smiilar global mandate ready — Built for teams that need demonstrable oversight of AI agent actions
Quick Setup
Add to your claude_desktop_config.json:
{
"mcpServers": {
"trustloop": {
"url": "https://trustloop-production.up.railway.app/sse?api_key=YOUR_KEY"
}
}
}
Get your API key at trustloop.live.
| Tool| Description|
|--------|--------|
| read_file| Read file contents (read-only)|
| write_file| Write content to a file|
| delete_all_files| Blocked by default — governance policy|
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
