ZeroTrue MCP Server
OfficialThe ZeroTrue MCP Server integrates the ZeroTrue AI Detection API to detect AI-generated content across text, images, video, and audio.
Analyze text (
zerotrue_analyze_text): Submit plain text (up to 200,000 characters) to detect AI-generated content.Analyze a URL (
zerotrue_analyze_url): Point the server at any direct HTTP(S) URL (image, video, audio, or text file) for analysis.Analyze a local file (
zerotrue_analyze_local_file): Provide an absolute local file path; the server auto-detects the MIME type and uploads it — no manual encoding required.Analyze a Base64-encoded file (
zerotrue_analyze_file): Submit a Base64-encoded file (up to ~70 MB) with its filename and optional MIME type.Retrieve a previous result (
zerotrue_get_result): Look up any past analysis by its UUID without re-running the scan.Get API metadata (
zerotrue_get_api_info): Fetch supported file formats and API capabilities.
Optional flags (available on all analysis tools):
isDeepScan— enables more thorough analysis (may consume paid credits).isPrivateScan— keeps results private and not stored publicly (may consume paid credits).
Enables GitHub Copilot to analyze files, URLs, and text for AI-generated content.
Enables JetBrains IDEs to analyze local files and text for AI-generated content via ZeroTrue.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@ZeroTrue MCP Server analyze this text for AI-generated content"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
ZeroTrue MCP Server
Official Model Context Protocol server for the ZeroTrue AI Detection API. Detect AI-generated text, images, video, and audio from any MCP-compatible agent or IDE.
Quick Start
Requires a ZeroTrue API key. Get one at zerotrue.app.
ZEROTRUE_API_KEY=zt_your_key npx -y @zerotrue/mcp stdioRelated MCP server: Reality Defender MCP Server
Tools
Tool | Description |
| Detect AI-generated content in plain text |
| Analyze media or text at a direct HTTP(S) URL |
| Analyze a local file by path (preferred for desktop/CLI clients) |
| Analyze a Base64-encoded file |
| Retrieve a previous analysis result by ID |
| Return API metadata and supported formats |
All tools accept optional isDeepScan and isPrivateScan flags where applicable.
zerotrue_analyze_local_file
The recommended tool for local MCP clients. Pass an absolute path: the server validates the file, detects its MIME type, and uploads it as a multipart form to ZeroTrue. No manual Base64 encoding needed.
{ "path": "/Users/alex/Downloads/photo.png", "isPrivateScan": true }zerotrue_analyze_text
{ "text": "Paste the content here...", "isDeepScan": false }zerotrue_analyze_url
{ "url": "https://example.com/video.mp4", "isPrivateScan": true }zerotrue_get_result
{ "id": "246c6522-195d-45d3-af96-0f2360d2e0bc" }Response Format
Every tool returns a consistent JSON envelope:
{
"ok": true,
"data": {
"id": "246c6522-195d-45d3-af96-0f2360d2e0bc",
"status": "completed",
"result": {
"ai_probability": 0.998,
"human_probability": 0.002,
"result_type": "ai_generated",
"feedback": "High probability of AI generation detected"
}
}
}Errors use the same shape with ok: false:
{
"ok": false,
"error": {
"statusCode": 401,
"message": "ZeroTrue API key is required.",
"code": "ZEROTRUE_API_ERROR"
}
}Client Setup
[mcp_servers.zerotrue]
command = "npx"
args = ["-y", "@zerotrue/mcp", "stdio"]
[mcp_servers.zerotrue.env]
ZEROTRUE_API_KEY = "zt_your_key"Add to claude_desktop_config.json:
{
"mcpServers": {
"zerotrue": {
"command": "npx",
"args": ["-y", "@zerotrue/mcp", "stdio"],
"env": {
"ZEROTRUE_API_KEY": "zt_your_key"
}
}
}
}copilot mcp add zerotrue \
--transport stdio \
--env ZEROTRUE_API_KEY=zt_your_key \
--tools '*' \
--timeout 310000 \
-- npx -y @zerotrue/mcp stdio
Or add manually to your workspace .vscode/mcp.json:
{
"inputs": [
{
"id": "zerotrue-api-key",
"type": "promptString",
"description": "ZeroTrue API key",
"password": true
}
],
"servers": {
"zerotrue": {
"command": "npx",
"args": ["-y", "@zerotrue/mcp", "stdio"],
"env": {
"ZEROTRUE_API_KEY": "${input:zerotrue-api-key}"
}
}
}
}Add to your Cursor MCP settings:
{
"mcpServers": {
"zerotrue": {
"command": "npx",
"args": ["-y", "@zerotrue/mcp", "stdio"],
"env": {
"ZEROTRUE_API_KEY": "zt_your_key"
}
}
}
}Use the IDE MCP settings panel with a local stdio server:
{
"mcpServers": {
"zerotrue": {
"command": "npx",
"args": ["-y", "@zerotrue/mcp", "stdio"],
"env": {
"ZEROTRUE_API_KEY": "zt_your_key"
}
}
}
}Run the HTTP server:
ZEROTRUE_API_KEY=zt_your_key \
ZEROTRUE_MCP_PORT=8787 \
npx -y @zerotrue/mcp httpOr with Docker:
docker run -p 8787:8787 \
-e ZEROTRUE_API_KEY=zt_your_key \
zerotrue/mcpMCP endpoint: http://localhost:8787/mcp
Health check: http://localhost:8787/healthz
Point your MCP client to the endpoint above. For production, place the server behind HTTPS and add authentication.
Configuration
Variable | Default | Description |
| (required) | ZeroTrue API key ( |
|
| ZeroTrue API base URL |
|
| Request timeout in milliseconds |
|
| Max local file size (default 100 MB) |
|
| Transport mode: |
|
| HTTP bind host |
|
| HTTP bind port |
|
| HTTP MCP path |
Example Prompts
Is this text AI-generated? "The quantum entanglement of..."Analyze https://example.com/profile.jpg with ZeroTrue and summarize the result.Use ZeroTrue to check /Downloads/video.mp4. Keep the scan private.Get ZeroTrue result 246c6522-195d-45d3-af96-0f2360d2e0bc and explain the verdict.Security
Store
ZEROTRUE_API_KEYin your MCP client config, never in source control.Prefer
stdiomode for personal use: your key never leaves your machine.zerotrue_analyze_local_filecan only access files readable by the MCP server process.For HTTP deployments, do not expose the
/mcpendpoint publicly without authentication and rate limiting.
Troubleshooting
ZeroTrue API key is required - Set ZEROTRUE_API_KEY in the environment where the MCP server starts.
File is not readable or does not exist - Use an absolute path and confirm the MCP server process has read access.
fetch failed - Check connectivity: curl https://api.zerotrue.app/api/v1/info. If details.cause.code is present, use it to diagnose DNS, TLS, or proxy issues.
Stale tool behavior after an update - Restart the MCP client. Most clients keep MCP subprocesses alive between tool calls.
Requirements
Node.js
>= 20.11
License
Available Tools
6 toolszerotrue_analyze_fileAnalyze FileA
Analyze a base64-encoded file using ZeroTrue. Prefer zerotrue_analyze_local_file for local files and zerotrue_analyze_url for remote files.
Inputs: filename (required), base64 (required), mimeType, isDeepScan, +1 more.
zerotrue_analyze_local_fileAnalyze Local FileA
Analyze a local file path readable by the MCP server. Best option for local desktop/CLI MCP clients.
Inputs: path (required), isDeepScan, isPrivateScan.
zerotrue_analyze_textAnalyze TextC
Analyze plain text for AI-generated content using ZeroTrue.
Inputs: text (required), isDeepScan, isPrivateScan.
zerotrue_analyze_urlAnalyze URLB
Analyze content at a direct HTTP(S) URL using ZeroTrue.
Inputs: url (required), isDeepScan, isPrivateScan.
zerotrue_get_api_infoGet API InfoA
Return ZeroTrue public API metadata and supported formats.
Inputs: no named parameters.
zerotrue_get_resultGet Analysis ResultA
Retrieve a ZeroTrue analysis result by ID.
Inputs: id (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 6 tools
Each tool has a distinct purpose: analyzing files from different sources (local, URL, base64), analyzing text, retrieving API info, and getting results. Descriptions clearly differentiate them, reducing ambiguity.
All tools follow a consistent pattern: 'zerotrue_' prefix + verb_noun in snake_case (e.g., zerotrue_analyze_file, zerotrue_get_result). No mixing of conventions.
With 6 tools, the server is well-scoped for its purpose of analyzing content for AI-generated material. Each tool provides necessary functionality without redundancy.
The toolset covers the full workflow: analyzing files (local, URL, base64), analyzing text, retrieving results, and accessing API metadata. No obvious gaps exist for the stated domain.
Maintenance
Related MCP Connectors
AI video, image and audio generation with 140+ AI models from any MCP agent
Use AI models for chat, image, and video generation from Claude Code and other MCP hosts.
Generate AI video, images and audio, and browse your history, from any MCP client.
Generate AI images and videos from any compatible MCP client.
Related MCP Servers
- AlicenseBqualityDmaintenanceEnables AI-generated text detection using the GPTZero API. Provides confidence scores and detailed analysis to identify whether text was written by humans or AI, with multilingual support.212 npm2MIT
- AlicenseNot gradedqualityDmaintenanceEnables LLMs to analyze images, videos, audio, and text files for AI-generated content using the Reality Defender API, with support for user file uploads and direct URL analysis.1Apache 2.0
- AlicenseAqualityDmaintenanceAn MCP server that enables AI assistants to analyze images for AI-generated content using noise maps, error level analysis, frequency analysis, spectral decay, color analysis, and metadata inspection.7MIT
- AlicenseAqualityDmaintenanceEnables detection of AI-generated content in images, videos, audio, and text via the AI or Not API. Supports media analysis tools for deepfakes, synthetic voices, and AI-written text.21MIT