How do I use MCP Content Credentials Server?

1. Click on "Install Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@MCP Content Credentials Server check if this photo from my Downloads is AI-generated" 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.

MCP Content Credentials Server

by noga7

Overview Schema Related Servers Score Discussions

JavaScript

Hybrid

MCP Content Credentials Server

MCP (Model Context Protocol) server for reading C2PA Content Credentials from images and videos. Detects credentials from both embedded manifests and invisible watermarks.

Features

🔍 Embedded C2PA Detection - Read manifests from file metadata
🌊 TrustMark Watermark Detection - Detect credentials in image pixels (survives social media!)
🌐 URL Support - Check credentials from web URLs
📂 Direct Filesystem Access - Claude can browse your directories
⚡ Smart Detection - Checks embedded first, watermark as fallback
🤖 Automatic Installation - Zero configuration setup
📋 Structured Output - Human-readable parsed data
🛡️ Production Ready - Full error handling and logging
🌐 REST API - HTTP endpoints for ChatGPT and web integration

Related MCP server: c2pa-mcp

Quick Start

# 1. Clone
git clone https://github.com/noga7/mcp-content-credentials.git
cd mcp-content-credentials

# 2. Install (automatic: installs c2patool + TrustMark)
npm install

# 3. Build
npm run build

# 4. Configure Claude Desktop
# Add to ~/Library/Application Support/Claude/claude_desktop_config.json:
{
  "mcpServers": {
    "content-credentials": {
      "command": "node",
      "args": ["/absolute/path/to/mcp-content-credentials/build/index.js"]
    }
  }
}

# 5. Restart Claude Desktop

# Optional: Start REST API for ChatGPT/web access
npm run start:api
# Server runs on http://localhost:3000

REST API (for ChatGPT & Web Apps)

Want to use this with ChatGPT or your own web app? Start the HTTP REST API:

npm run start:api

The server runs on http://localhost:3000. See REST-API.md for full documentation.

For ChatGPT: Use ngrok to expose your local server, or deploy to Render/Railway. See REST-API.md for instructions.

# Quick test
curl "http://localhost:3000/verify-url?url=https://example.com/image.jpg"

Prerequisites

Node.js v18+
Python 3.8.5+ (for TrustMark watermarks)

All other dependencies auto-install during npm install:

✅ c2patool (Homebrew on macOS, binary on Linux)
✅ TrustMark Python package (via pip)

Manual Installation (if auto-install fails)

# c2patool
brew install contentauth/tools/c2patool  # macOS

# TrustMark
pip3 install trustmark Pillow

# Or retry auto-install
npm run install-deps

Usage

Check a Specific File

"Check content credentials in ~/Desktop/photo.jpg"
"Is this image AI-generated?"
"Who created /Users/you/Downloads/image.png?"

Browse Directories

"What images are in my Desktop?"
"Check my Downloads for Content Credentials"
"Find AI-generated images in my Pictures"

Check URLs

"Check credentials at https://example.com/image.jpg"

How It Works

Detection Flow

1. Check Embedded C2PA Manifest (fast: ~150ms)
   ↓
   Found? → Return immediately ✅
   ↓
2. Check TrustMark Watermark (slower: ~600ms)
   ↓
   Found? → Return watermark data ✅
   ↓
3. Neither found → "No Content Credentials found" ❌

Why This Order?

Performance: 80% of credentialed images have embedded manifests
Speed: Skip expensive watermark check when not needed
Completeness: Still catch stripped metadata via watermarks

TrustMark Watermarks

Invisible watermarks embedded in image pixels that:

✅ Survive JPEG compression
✅ Persist through social media uploads (Instagram, Twitter)
✅ Work after print-scan cycles
✅ Remain when metadata is stripped

Supported Formats

Images: JPEG, PNG, WebP, GIF, TIFF, AVIF, HEIC
Video: MP4, MOV

API Response

{
  success: boolean;
  hasCredentials: boolean;
  
  // Embedded C2PA data
  manifestData?: {
    whoThisComesFrom?: {
      linkedInIdentity?: { name, profileUrl, verified }
      otherIdentities?: [{ name, socialAccounts }]
    };
    aboutThisContent?: {
      actions?: [{ action, softwareAgent, when }]
      genAIInfo?: { generative, training, model }
    };
    aboutTheseCredentials?: { claimSigner, timestamp };
    validationInfo?: { certificate, trustInfo };
  };
  
  // Watermark data (if no embedded found)
  trustMarkData?: {
    identifier: string;    // Watermark payload
    schema: string;        // BCH_SUPER, BCH_5, etc.
    manifestUrl?: string;  // URL to full manifest
  };
  
  error?: string;
}

Filesystem Access

Claude can browse these directories automatically:

~/Desktop
~/Downloads
~/Documents
~/Pictures

No need to provide exact paths! Just ask:

"What images are in my Desktop?"
"Check recent downloads"

Development

npm run build        # Compile TypeScript
npm run dev          # Development mode
npm run lint         # Check code quality
npm run test         # Run tests
npm run precommit    # Full quality check

Architecture

mcp-content-credentials/
├── src/
│   ├── index.ts              # MCP server + filesystem access
│   ├── c2pa-service.ts       # Detection orchestration
│   ├── trustmark-service.ts  # Watermark detection (Python)
│   ├── parsers/              # Data formatters
│   └── types/                # TypeScript definitions
├── scripts/
│   ├── install-trustmark.cjs # Auto-installer
│   └── trustmark-decode.py   # Python watermark decoder
└── build/                    # Compiled output

Troubleshooting

"Unable to access that file"

Restart Claude Desktop (most common fix!)
Use absolute paths: /Users/you/... not ~/...
Verify MCP is connected: Ask "What tools do you have?"

"c2patool: command not found"

brew install contentauth/tools/c2patool  # macOS
# or
npm run install-deps

"Python or TrustMark not found"

pip3 install trustmark Pillow
# or
npm run install-deps

No Content Credentials Found

This is normal! The file either:

Wasn't created with content authentication
Had credentials removed
Is a screenshot/copy without provenance

Performance

Embedded check: ~150ms (fast path, 80% of cases)
+ Watermark check: ~600ms (fallback, 20% of cases)
First watermark: ~30s (downloads ONNX model, one-time)

Security

✅ Read-only filesystem access
✅ Limited to user directories (Desktop, Downloads, etc.)
✅ Input validation on all paths and URLs
✅ Temporary files auto-deleted
✅ No access to hidden/system files

Contributing

See CONTRIBUTING.md

Resources

License

MIT

Available Tools

2 tools

read_credentials_fileA

Read Content Credentials from a local file. USE THIS TOOL when the user drops a file or provides a file path AND asks questions like: "who made this", "how was this made", "where does this come from", "is this AI", "is this real", "does this have Content Credentials", "what are the c2pa details", or mentions "c2pa" or "Content Credentials". If the user asks a SPECIFIC question (e.g., "Is this AI?"), answer their question directly using the relevant data, then offer to share more details from the Content Credentials. If the user asks GENERALLY about the file or its credentials, present the information in this order (SKIP sections that have no data): 1) Who this comes from (use BULLET POINTS, prioritize LinkedIn verified identities at the top - OMIT THIS ENTIRE SECTION if no CAWG or personal identity is found), 2) About this content (actions taken - EXCLUDE "c2pa.opened" actions unless specifically requested), 3) About these Content Credentials (signer and timestamp), 4) Validation info (certificate details).

ParametersJSON Schema

Name	Required	Description	Default
`filePath`	Yes	Absolute or relative path to the file to check for Content Credentials. Supports all filesystem characters including periods, numbers, dashes, underscores, and spaces. Examples: /path/to/file-name.jpg, /mnt/data/image 2.png, ./my-file.2024-01.jpg

TDQS

A4.2/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of behavioral disclosure. It effectively describes the tool's behavior, including how to process user questions (specific vs. general), the order of information presentation, and rules for skipping sections or omitting data. However, it lacks details on error handling, file format limitations, or performance aspects like rate limits.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is front-loaded with the purpose and usage guidelines, but it becomes verbose with detailed response instructions that might be better suited for an output schema or separate documentation. While informative, some sentences could be streamlined to improve conciseness without losing essential guidance.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (involving file reading and credential parsing) and lack of annotations or output schema, the description does a good job of covering usage scenarios and behavioral expectations. However, it could be more complete by addressing potential errors, file size limits, or authentication needs, which are relevant for such operations.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has 100% description coverage, providing a clear parameter 'filePath' with examples. The description does not add significant meaning beyond the schema, as it doesn't elaborate on parameter usage or constraints. Given the high schema coverage, a baseline score of 3 is appropriate, as the description doesn't compensate but also doesn't detract.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose as 'Read Content Credentials from a local file,' specifying both the verb ('Read') and resource ('Content Credentials from a local file'). It distinguishes from the sibling tool 'read_credentials_url' by explicitly focusing on local files rather than URLs, making the distinction clear.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides explicit guidance on when to use this tool: 'when the user drops a file or provides a file path AND asks questions like...' and lists specific question types. It also distinguishes usage from alternatives by implying this is for local files, contrasting with the sibling tool for URLs, and offers detailed instructions on how to respond based on user queries.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

read_credentials_urlA

Read Content Credentials from a file at a URL. USE THIS TOOL when the user provides a URL AND asks questions like: "who made this", "how was this made", "where does this come from", "is this AI", "is this real", "does this have Content Credentials", "what are the c2pa details", or mentions "c2pa" or "Content Credentials". Downloads the file temporarily, checks for embedded C2PA manifests, then cleans up. If the user asks a SPECIFIC question (e.g., "Is this AI?"), answer their question directly using the relevant data, then offer to share more details from the Content Credentials. If the user asks GENERALLY about the file or its credentials, present the information in this order (SKIP sections that have no data): 1) Who this comes from (use BULLET POINTS, prioritize LinkedIn verified identities at the top - OMIT THIS ENTIRE SECTION if no CAWG or personal identity is found), 2) About this content (actions taken - EXCLUDE "c2pa.opened" actions unless specifically requested), 3) About these Content Credentials (signer and timestamp), 4) Validation info (certificate details).

ParametersJSON Schema

Name	Required	Description	Default
`url`	Yes	HTTP or HTTPS URL of the file to check for Content Credentials

TDQS

A4.3/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of behavioral disclosure. It effectively describes the tool's behavior: it downloads files temporarily, checks for C2PA manifests, cleans up afterward, and outlines the structured response format. However, it doesn't mention potential errors (e.g., invalid URLs, network issues) or performance characteristics like rate limits, leaving some gaps.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is appropriately sized and front-loaded with the core purpose and usage guidelines. However, it includes extensive formatting instructions (e.g., bullet points, section ordering) that might be better suited for an output schema or separate documentation, slightly reducing efficiency. Most sentences are necessary for clarity.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (involving file download, C2PA parsing, and structured responses) and lack of annotations/output schema, the description does a good job covering behavior and usage. It explains the processing steps and response format in detail. However, without an output schema, the description must fully define return values, which it does partially but could be more explicit about data types or error cases.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has 100% description coverage, so the baseline is 3. The description doesn't add any parameter-specific information beyond what's in the schema (which already defines 'url' as an HTTP/HTTPS URL). No additional syntax, format, or constraints are provided in the description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the specific action ('Read Content Credentials from a file at a URL'), identifies the resource (file at URL), and distinguishes it from its sibling 'read_credentials_file' by specifying URL-based input rather than file-based input. The verb 'read' is precise and the scope is well-defined.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides explicit guidance on when to use this tool ('when the user provides a URL AND asks questions like...'), includes specific example questions (e.g., 'who made this', 'is this AI'), and mentions the sibling tool context. It also gives detailed instructions on how to respond based on user intent (specific vs. general questions), making it highly actionable.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

A4.1/5.0

Disambiguation5/5

The two tools have clearly distinct purposes based on input source: read_credentials_file handles local files while read_credentials_url handles URLs. Their descriptions explicitly specify when to use each tool, eliminating any potential confusion about which to select for a given scenario.

Naming Consistency5/5

Both tools follow an identical verb_noun pattern (read_credentials_file and read_credentials_url) with perfect consistency. The naming clearly indicates the action (read) and distinguishes the input type (file vs URL) in a predictable manner.

Tool Count3/5

With only 2 tools, the server feels somewhat thin for a Content Credentials domain that could benefit from additional operations like validation, manifest listing, or credential creation. While the two tools cover the core reading functionality from different sources, the scope seems limited compared to what a comprehensive C2PA/credentials server might offer.

Completeness2/5

The server only provides read operations from two input sources, missing essential capabilities for a Content Credentials domain. There are no tools for creating, updating, validating, or managing credentials, nor tools to list available manifests or check credential status. This creates significant gaps that would limit agent workflows beyond basic information retrieval.

Maintenance

ActivityInactive

ResponsivenessSyncing

Resources

GitHub Repository

Need Help?

Related Servers

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

Lumethic Photo Verification A
com.lumethic
Verify photos are genuine camera captures, not AI-generated: C2PA checks and RAW+JPEG forensics.
Image & Video Processing Security
142
H/M Content Credentials Evidence Verifier
net.hogarmas
Free C2PA 2.4 triage and reproducible official trust snapshot. No media, keys, or payment.
Security Legal & Compliance
1
c2paintake-mcp
com.clauxel.c2paintake
Remote MCP for C2PA intake verifier MCP, structured receipts, audit logs, and reviewer-ready evidenc
Security Legal & Compliance
2
ProofX - Content Protection for Creators A
io.github.razashariff
Protect and verify digital content with cryptographic signing and proof of ownership.
Security Multimedia Processing
62

Related MCP Servers

mtl-c2pa-mcp
AI & Machine Learning Security
musictechlab
A
license
Not graded
quality
D
maintenance
MCP server for reading C2PA content provenance manifests from media files, enabling natural language queries about AI-generated content, signatures, and provenance.
Updated 3 months ago (2026-05-29 16:35 UTC)
2
MIT
c2pa-mcp
Security
harelrech
A
license
A
quality
A
maintenance
Verifies C2PA Content Credentials for local files or URLs and returns an LLM-ready verdict on trust, AI generation, and provenance.
Updated a month ago (2026-07-24 07:44 UTC)
4
26
1
Apache 2.0
chronoverify-mcp
Image & Video Processing Security
beeswaxpat
A
license
A
quality
B
maintenance
Provides MCP-compatible AI agents with a verify_image tool to check a photo's capture time and provenance using C2PA, EXIF, XMP metadata, and pixel forensics, returning a verdict and confidence score.
Updated 3 days ago (2026-08-31 15:08 UTC)
1
86
2
MIT
Watermarking Authenticity MCP
AI & Machine Learning Security Legal & Compliance
CSOAI-ORG
A
license
Not graded
quality
B
maintenance
Provides AI content watermarking and C2PA compliance for EU AI Act Article 50, enabling detection, verification, and batch processing of authenticated content.
Updated a month ago (2026-07-26 01:22 UTC)
4
MIT

Latest Blog Posts

Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)
By Om-Shree-0709 on July 25, 2026.
mcp
Agent Identity
OAuth 2.1
Your AI Chatbot Just Exposed Your CEO's Salary to an Intern
By Om-Shree-0709 on July 2, 2026.
Agent Identity
MCP Security
OAuth Delegation
Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)
By Om-Shree-0709 on June 30, 2026.
Agentic Ai
Prompt Injection
WebAssembly

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/noga7/mcp-content-credentials'

If you have feedback or need assistance with the MCP directory API, please join our Discord server

MCP Content Credentials Server

Features

Quick Start

REST API (for ChatGPT & Web Apps)

Prerequisites

Manual Installation (if auto-install fails)

Usage

Check a Specific File

Browse Directories

Check URLs

How It Works

Detection Flow

Why This Order?

TrustMark Watermarks

Supported Formats

API Response

Filesystem Access

Development

Architecture

Troubleshooting

"Unable to access that file"

"c2patool: command not found"

"Python or TrustMark not found"

No Content Credentials Found

Performance

Security

Contributing

Resources

License

Available Tools

TDQS

TDQS

TDQS

Maintenance

Resources

Looking for Admin?

Related MCP Connectors

Related MCP Servers

mtl-c2pa-mcp

c2pa-mcp

chronoverify-mcp

Watermarking Authenticity MCP

Latest Blog Posts

MCP directory API