register_agent_identityLABSCO SUMMARY
Verification is the half that matters.
Issuing credentials is easy; the reason to reach for DIDs at all is that a third party can check one without asking you. Having register, issue, and verify as three separate calls means both ends of an agent-to-agent handshake can be built from the same server.
What it is
A Python server for agent identity — decentralised identifiers, verifiable credentials, and reputation scoring. The framing in the repository is agent passports for the MCP ecosystem: an agent registers an identity, carries credentials, and another party can verify them.
What you get
register_agent_identity, issue_credential and verify_credential are the register, issue and check sides of the same scheme. get_agent_reputation reads an agent's reputation score, and list_registered_agents lists the identities registered so far.
Requirements
Install with pip install agent_identity_trust_mcp; your client then starts it with the agent_identity_trust_mcp command, over stdio. MIT-licensed.
Setup effort
One command — pip install agent_identity_trust_mcp
USE CASES
01
Giving an agent an identity it can carry
Register the DID once and reuse it across interactions.
02
Attesting something about an agent
Issue a verifiable credential rather than a claim in a config file.
03
Deciding whether to trust an incoming agent
Verify its credential before granting anything.
5 tools
Listed in project docs. Your client may show a different list.
issue_credentialverify_credentialget_agent_reputationlist_registered_agentsBEFORE YOU INSTALL
What to know first
Tools you get
5 tools named in the project's documentation.
Requires
Python 3.10 or later
INSTALLATION
Connect your client
Add the block to your client, or run the command directly.
Server setup
Configuration file
JSON
{
"mcpServers": {
"agent-identity-trust-mcp": {
"command": "agent_identity_trust_mcp"
}
}
}pip
TERMINAL
pip install agent_identity_trust_mcp
