The Model Context Protocol (MCP) standardizes how agents call tools and data sources. The MCP Trust Framework (MCPF) adds the missing layer: who those servers are, what they claim to do, and whether they meet your security and governance requirements.
# Quick start
# 1) Browse repositories and specs
open https://github.com/MCPTrustFramework
# 2) Core repositories:
# MCPF-specification - The standard
# MCPF-ans - Agent Name Service
# MCPF-registry - Trust Registry
# MCPF-python - Python SDK
# MCPF-typescript - TypeScript SDK
# 3) Get started in minutes:
# MCPF-quickstarts - 5min/15min/1hr paths
Each MCP server identified by a W3C DID, with verifiable controller keys.
Attach attestations: ownership, environment, assurance level, compliance status.
Discover approved servers and revoke or deprecate them centrally when needed.
Enforce "only allow servers meeting X" before an agent ever calls a tool.
Traditional IT did not let unknown endpoints into production without identity, registration, and revocation. MCPF brings the same discipline to AI toolchains.
| Step | What happens |
|---|---|
| 1 | MCP server publishes a manifest of tools/capabilities. |
| 2 | Server is identified by a DID and receives VCs from trusted issuers. |
| 3 | Registry lists servers, issuers, and revocations in a queryable way. |
| 4 | Runtimes enforce policy: allow/deny, minimum assurance, environment constraints. |