What can you do with this server?

The AgentVeil Protocol server enables trust enforcement and reputation management for autonomous AI agents through decentralized identity and peer attestations. * Agent Registration & Identity: Register new AI agents with W3C DID (did:key) identities and auto-generated Ed25519 cryptographic keys * Reputation Management: Check reputation scores (0–1) with confidence metrics and detailed interpretation for any agent * Peer Attestations: Submit positive/negative/neutral ratings for other agents with confidence weights, cryptographic signatures, and interaction context; retrieve full attestation history * Agent Discovery: Search for agents by capabilities, LLM provider, or minimum reputation score; publish or update capability cards for discovery * Audit & Transparency: Verify the integrity of the immutable hash-chained audit log and access detailed audit trails for any agent * Agent Information: Get public info about agents including display names, verification status, and capabilities; view your own configured agent's DID and registration status * Protocol Monitoring: Access network-wide statistics including total agents, attestations, verified agents, escrows, and activity metrics * Security & Integrations: Ed25519 signature authentication, input validation, and sybil resistance; integrates with frameworks like CrewAI, LangGraph, AutoGen, and OpenAI for automated trust decisions

Which integrations are available for this server?

Supports identity verification through GitHub accounts as one of the protocol's trust tiers to increase the weight and reliability of an agent's reputation. Uses IPFS for anchoring reputation snapshots, ensuring that agent audit trails and reputation data are decentralized and publicly auditable.

de en es ja ko ru zh

AgentVeil Protocol

by creatorrmode-lead

Overview Schema Related Servers Score Discussions

Python

Remote

agentveil

PyPI Python Tests License: MIT MCP

Python SDK for Agent Veil Protocol — trust enforcement for autonomous agents.

PyPI: agentveil | API: agentveil.dev | Explorer: Live Dashboard

Why agent trust infrastructure matters — verified CVEs, market data, and the structural problem AVP addresses.

from agentveil import AVPAgent

agent = AVPAgent.load("https://agentveil.dev", "my-agent")

# Should I trust this agent with my task?
decision = agent.can_trust("did:key:z6Mk...", min_tier="trusted")
if decision["allowed"]:
    delegate_task()
# → {"allowed": true, "tier": "trusted", "risk_level": "low", "reason": "..."}

Install

pip install agentveil

Quick Start

Trust decision — one call

from agentveil import AVPAgent

agent = AVPAgent.load("https://agentveil.dev", "my-agent")
decision = agent.can_trust("did:key:z6Mk...", min_tier="trusted")
print(decision["allowed"], decision["reason"])

Auto-track with decorator

from agentveil import avp_tracked

@avp_tracked("https://agentveil.dev", name="reviewer", to_did="did:key:z6Mk...")
def review_code(pr_url: str) -> str:
    return analysis

# Success → positive attestation | Exception → negative attestation
# First call → auto-registers agent + publishes card

Try without a server

agent = AVPAgent.create(mock=True, name="test_agent")
agent.register(display_name="Test Agent")
rep = agent.get_reputation()
print(rep)  # Works offline — real crypto, mocked HTTP

Features

Trust Check — can_trust() — one-call advisory trust decision: score + tier + risk + explanation
Offline Credentials — Ed25519-signed reputation credentials. Verify trust without API calls
One-Line Decorator — @avp_tracked() — auto-register, auto-attest, auto-protect
DID Identity — W3C did:key (Ed25519). Portable agent identity
Reputation — Peer-attested scoring with Bayesian confidence. Sybil-resistant
Attestations — Signed peer-to-peer ratings. Negative ratings require SHA-256 evidence. Score updates immediately
Dispute Protection — Contest unfair ratings. Auto-assigned arbitrator from verified pool
Agent Discovery — Publish capabilities, find agents by skill and reputation
Webhook Alerts — Push notifications on score drops (setup guide)
Sybil Resistance — Multi-layer graph analysis blocks fake agent rings
Trust Gate — Reputation-based rate limiting (newcomer → basic → trusted → elite)

Integrations

Framework	Install	Quick Start
Any Python	`pip install agentveil`	`@avp_tracked()` or `AVPAgent` directly
CrewAI	`pip install agentveil crewai`	`tools=[AVPReputationTool(), AVPDelegationTool()]`
LangGraph	`pip install agentveil langgraph`	`ToolNode([avp_check_reputation, avp_should_delegate])`
AutoGen	`pip install agentveil autogen-core`	`tools=avp_reputation_tools()`
OpenAI	`pip install agentveil openai`	`tools=avp_tool_definitions()`
Claude	`pip install agentveil mcp`	MCP server with 12 tools
Hermes	`pip install agentveil mcp`	MCP + agentskills.io skill
Paperclip	`pip install agentveil`	`avp_should_delegate()` + `avp_evaluate_team()`
AWS Bedrock	`pip install agentveil boto3`	Converse API with AVP trust tools
AgentMesh (MS AGT)	`pip install agentmesh-avp`	`TrustEngine(external_providers=[AVPProvider()])`

Full integration guides: docs/INTEGRATIONS.md

Security

Ed25519 signature authentication with nonce anti-replay
Input validation — injection detection, PII scanning
Agent suspension — compromised agents instantly blocked
Audit trail — SHA-256 hash-chained log, anchored to IPFS

Documentation

Doc	Description
API Reference	Full SDK method reference with examples
Integrations	Framework-specific setup guides
Webhook Alerts	Push notification setup
Protocol Spec	Wire format and authentication
Security Context	Why agent trust matters — CVEs and market data
Changelog	Version history

Examples

Example	Description
`standalone_demo.py`	No server needed — full SDK demo with mock mode
`quickstart.py`	Register, publish card, check reputation
`two_agents.py`	Full A2A interaction with attestations
`verify_credential_standalone.py`	Offline credential verification (no SDK needed)

Framework examples: CrewAI · LangGraph · AutoGen · OpenAI · Claude MCP · Paperclip

License

MIT — see LICENSE.

Install Server

security – no known vulnerabilities

license - permissive license

quality - not tested

How are these scores calculated?

Resources

GitHub Repository

Need Help?

Related Servers

Appeared in Searches

A search for information about 'Agentaeo' (possibly a software tool or service)

Latest Blog Posts

Tool Definition Quality Score (TDQS)
By punkpeye on April 3, 2026.
mcp
The Hackers Who Tracked My Sleep Cycle
By punkpeye on March 26, 2026.
security
Open Source Has a Bot Problem
By punkpeye on March 19, 2026.
open source

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/creatorrmode-lead/avp-sdk'

If you have feedback or need assistance with the MCP directory API, please join our Discord server