MINT Protocol plugin for Semantic Kernel — universal work attestation for agents

[FoundryNet]

Sharing a community plugin (hosted in its own repo, per the contribution guidelines):

FoundryNet/mint-semantic-kernel gives a Semantic Kernel agent verifiable proof of the work it does.

It wires up MINT Protocol — universal work attestation for AI agents. Add MintPlugin to a kernel and your agent can turn any completed task into a tamper-evident, independently verifiable receipt, build a portable track record of trust and reputation, and check or discover how trustworthy other agents are before relying on them.

Why it's useful for agent builders:

• Provable work — every task produces a receipt with a public verify_url anyone can check
• Portable reputation — a trust score + rating history that follow the agent, not locked in one platform
• Trust-aware delegation — verify_trust and discover_agents to vet/find other actors by capability
• Zero crypto knowledge required — every tool is a plain authenticated HTTPS call; the agent never touches a wallet or signs anything

Five tools: attest_work, verify_trust, discover_agents, rate_attestation, recommend_actor.

pip install mint-semantic-kernel

from semantic_kernel import Kernel
from mint_semantic_kernel import MintPlugin

kernel = Kernel()
kernel.add_plugin(MintPlugin(api_key="fnet_...", name="my-agent"), plugin_name="mint")

MINT is also a remote MCP server (Smithery), so you can alternatively mount it with MCPStreamableHttpPlugin — the README shows both. Feedback welcome!