A
licenseNot graded
qualityD
maintenanceMCP Server for AI agent identity and authorization. Create, verify, and manage agent identities with trust scores and scoped authorization tokens.
48 PyPI
MIT
aip-identity
Enables AI agents to link and register their AIP identities using GitHub accounts to facilitate identity verification and trust scoring within the AIP protocol.
AIP MCP Server
MCP server that gives AI agents (Claude, Cursor, etc.) access to AIP identity tools — verify agents, check trust scores, sign content, and exchange encrypted messages.
Install
pip install aip-mcp-serverRelated MCP server: @citizenofthecloud/mcp-server
Setup
First, register an AIP identity (if you don't have one):
pip install aip-identity
aip register --platform github --username your-usernameClaude Desktop
Add to ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows):
{
"mcpServers": {
"aip": {
"command": "aip-mcp-server"
}
}
}Cursor
Add to .cursor/mcp.json in your project:
{
"mcpServers": {
"aip": {
"command": "aip-mcp-server"
}
}
}Environment Variables
Variable | Default | Description |
|
| Path to credentials file |
|
| AIP service endpoint |
Tools
Tool | Description |
| Show your current AIP identity (DID, public key) |
| Verify another agent's identity via challenge-response |
| Get trust score and vouch chain for an agent |
| Cryptographically sign content to prove authorship |
| Verify a signature against a DID's public key |
| Send an encrypted message to another agent |
| Check for incoming messages |
| Register a new AIP identity |
Resources
URI | Description |
| Current agent's full identity info |
| Trust graph data for a specific DID |
Links
aip-identity on PyPI — Full CLI and Python SDK
AIP Protocol — Source code and docs
AIP Service — Production service
Available Tools
8 toolsaip_check_messagesB
Check for messages sent to your agent.
Args: unread_only: If True, only return unread messages (default: True)
Inputs: unread_only.
aip_registerC
Register a new AIP identity for your agent.
Args: platform: Platform name (e.g. 'github', 'moltbook', 'discord') username: Your username on that platform
Inputs: platform (required), username (required).
aip_send_messageC
Send an encrypted message to another agent.
Args: recipient_did: The DID of the recipient agent message: The message text to send
Inputs: recipient_did (required), message (required).
aip_signB
Cryptographically sign content with your AIP identity to prove authorship.
Args: content: The text content to sign
Inputs: content (required).
aip_trust_scoreC
Get the trust score and vouch chain for an agent.
Args: did: The DID of the agent to check scope: Optional trust scope filter (e.g. GENERAL, CODE_SIGNING)
Inputs: did (required), scope.
aip_verifyA
Verify another agent's identity via cryptographic challenge-response.
Args: did: The DID of the agent to verify (e.g. did:aip:abc123...)
Inputs: did (required).
aip_verify_signatureA
Verify a cryptographic signature against a DID's public key.
Args: content: The original content that was signed signature: The base64-encoded signature to verify did: The DID of the agent who allegedly signed it
Inputs: content (required), signature (required), did (required).
aip_whoamiA
Show your current AIP identity — DID, platform, and public key.
Inputs: no named parameters.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
A3.6/5.0
Scored across 8 tools
Disambiguation5/5
Each tool has a clearly distinct purpose with no overlap: message checking, identity registration, message sending, content signing, trust score retrieval, identity verification, signature verification, and identity display. The descriptions reinforce these distinct functions, making misselection unlikely.
Naming Consistency5/5
All tools follow a perfect 'aip_' prefix + verb pattern (e.g., aip_check_messages, aip_register, aip_send_message). The naming is completely consistent with snake_case throughout, making the tool set predictable and easy to understand.
Tool Count5/5
With 8 tools, this is well-scoped for an identity management server. Each tool serves a specific function in the AIP identity lifecycle (registration, verification, messaging, signing), and none appear redundant or unnecessary for the domain.
Completeness4/5
The tool set covers core identity operations well: registration, verification, signing, and trust management. A minor gap exists in message management—there's no tool to delete or manage sent messages—but agents can still perform essential workflows without significant hindrance.
Maintenance
ActivityInactive
ResponsivenessNo recent community issues
Related MCP Connectors
MCP server for the Z1N Protocol - on-chain identity for AI agents on Polygon
MCP server for verifying EUDI/Talao wallet data via OIDC4VP (pull) for AI agents.
MCP server for OnceAsk, the AI-native current-address layer for people and agents.
Free trust records for AI agents and MCP servers: trust checks, sybil signals, signed attestations.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceMCP server for Citizen of the Cloud — agent identity verification, trust scoring, and registry access for any AI runtime that speaks the Model Context Protocol.22 npmMIT
- AlicenseAqualityDmaintenanceMCP server for AI agent trust verification, enabling agents to verify identities, check trust scores, and build reputation across multiple blockchain and web platforms.1220 npm1MIT
- AlicenseNot gradedqualityDmaintenanceMCP server for AInternet — DNS, identity and messaging for AI agents, enabling .aint domain resolution, Ed25519-based identity verification, and inter-agent messaging.MIT
