About Mark
proof, called Mark in the README, creates publicly verifiable provenance records for creators, agents, and content workflows. It hashes content locally and supports offline verification; a record captures a signer's claim and time, not proof that authorship is true.
Key features
- 01Hash content with SHA-256
- 02Record signer, time, and Ed25519 signature
- 03Anchor records through a Merkle tree and chains
- 04View public verification pages
- 05Verify anchored proofs offline
Use cases
- 01Add provenance markers to AI-generated content
- 02Create verifiable records for files or text
- 03Check content against an existing signed proof
- 04Verify anchored content proofs without a network
MCP support
The MCP server provides create_proof and verify_proof tools for agents to create and check content proofs.
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://makemark.io/mcpclaude mcp add --transport http dev-tatastu-proof https://makemark.io/mcp{"mcpServers":{"dev-tatastu-proof":{"type":"http","url":"https://makemark.io/mcp"}}}Open in Cursor{"servers":{"dev-tatastu-proof":{"type":"http","url":"https://makemark.io/mcp"}}}Open in VS Code{"mcpServers":{"dev-tatastu-proof":{"type":"http","url":"https://makemark.io/mcp"}}}{"mcpServers":{"dev-tatastu-proof":{"serverUrl":"https://makemark.io/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
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.