About

About MCPF

The MCP Trust Framework is an open source, community-driven standard for adding identity and trust to MCP servers.

Background

The Model Context Protocol (MCP) from Anthropic provides a standardized way for AI agents to interact with tools and data sources. However, MCP intentionally does not define trust, identity, or governance mechanisms.

MCPF addresses this gap by providing:

Identity Layer

Based on W3C DIDs and Verifiable Credentials, enabling servers to prove their identity and attestations.

Trust Registry

Queryable services that list approved servers, issuers, and revocation status.

Governance Framework

Policy enforcement mechanisms that ensure agents only use approved, verified tools.

Origin: MCPF was originally incubated with support from the VeriTrust trust ecosystem, applying W3C standards and blockchain-based trust patterns to the MCP protocol.

Status

Specification: Draft

Reference Implementation: Alpha

SDKs: Alpha

License: CC BY-NC 4.0

Copyright

Copyright © 2025 VeriTrust

Licensed under Creative Commons Attribution-NonCommercial 4.0. Free for research, education, and personal use. Commercial licensing available.