About Content Provenance
Anchor a content-creation event to the Knox chain; returns a C2PA-aligned, FRE 902-shaped bundle
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://bonissystems.com/api/knox/agents/content-provenance/mcpclaude mcp add --transport http com-bonissystems-content-provenance https://bonissystems.com/api/knox/agents/content-provenance/mcp{"mcpServers":{"com-bonissystems-content-provenance":{"type":"http","url":"https://bonissystems.com/api/knox/agents/content-provenance/mcp"}}}Open in Cursor{"servers":{"com-bonissystems-content-provenance":{"type":"http","url":"https://bonissystems.com/api/knox/agents/content-provenance/mcp"}}}Open in VS Code{"mcpServers":{"com-bonissystems-content-provenance":{"type":"http","url":"https://bonissystems.com/api/knox/agents/content-provenance/mcp"}}}{"mcpServers":{"com-bonissystems-content-provenance":{"serverUrl":"https://bonissystems.com/api/knox/agents/content-provenance/mcp"}}}Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.
Tools
2| Parameter | Type | Required | Description |
|---|---|---|---|
| ai | object | No | AI-generation metadata (required when source = ai_generated). |
| ai.model | string | No | Model identifier (e.g., openai/sora-2, google/veo-3). |
| ai.prompt | string | No | Plain-text prompt (will be hashed in the anchor). |
| ai.provider | string | No | Provider name. |
| ai.parameters | object | No | Model parameters (hashed in the anchor). |
| ai.promptHash | string | No | Pre-hashed prompt (preferred for privacy). |
| ai.generatedAt | string | No | ISO timestamp from the provider. |
| ai.providerReceiptId | string | No | Provider's job/run ID. |
| name | string | Yes | Display name for the work (max 256 chars). |
| human | object | No | Human-original metadata (optional when source = human_original). |
| human.captureAt | string | No | ISO timestamp of capture. |
| human.authorClaim | string | No | Author identity claim (name, DID, etc.). |
| human.captureMethod | string | No | Camera / device / instrument used. |
| human.captureLocation | string | No | Location string; hashed before anchoring. |
| hybrid | object | No | Hybrid-creation metadata (required when source = ai_assisted_hybrid). |
| hybrid.ai | object | No | Optional AI metadata (same shape as 'ai'). |
| hybrid.editChain | array | No | Optional edit-history entries; hashed. |
| hybrid.aiContribution | string | Yes | Description of the AI's role. |
| hybrid.humanContribution | string | Yes | Description of the human creative role. |
| source | enum | Yes | Creation source.human_original | ai_generated | ai_assisted_hybrid |
| sizeBytes | integer | No | Content size in bytes. |
| contentHash | string | Yes | SHA-256 digest of the content as 64 lowercase hex chars. The content itself is not transmitted. |
| contentType | string | No | MIME type (max 128 chars). |
Details
The maintainer has not added details yet. Check the README in the repository.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.