Server data from the Official MCP Registry
MCP server for verifying EUDI/Talao wallet data via OIDC4VP (pull) for AI agents.
MCP server for verifying EUDI/Talao wallet data via OIDC4VP (pull) for AI agents.
Remote endpoints: streamable-http: https://wallet-connectors.com/mcp
This MCP server for managing AI Agent wallets and digital identities has appropriate authentication mechanisms (PAT, OAuth2, private_key_jwt) and uses cloud KMS for key management, which is good. However, there are notable security concerns: secrets (PAT tokens, OAuth client secrets) are generated and returned in structured responses without explicit warnings about secure storage, sensitive configuration data is returned in API responses, there is no evidence of input validation on critical parameters like URLs and JWK payloads, and error handling could expose implementation details. The permissions (network_http, env_vars) are appropriate for a financial/identity service but the code quality issues around credential handling and data exposure lower the score to the moderate range. Supply chain analysis found 25 known vulnerabilities in dependencies (1 critical, 8 high severity).
3 files analyzed · 33 issues found
Security scores are indicators to help you make informed decisions, not guarantees. Always review permissions before connecting any MCP server.
This plugin requests these system permissions. Most are normal for its category.
Available as Local & Remote
This plugin can run on your machine or connect to a hosted endpoint. during install.
From the project's GitHub README.
Wallet4Agent provides the trust layer that AI Agents need to operate safely in the real world.
This document explains the technical components, standards, and identity mechanisms behind the platform.
AI Agents increasingly take actions, access data, and collaborate.
To do this safely, they must be able to:
Wallet4Agent provides AI Agents with:
Everything is standards‑based and interoperable.
Wallet4Agent is built with three coordinated layers:
POST https://wallet4agent.com/mcpManages:
Supports:
All complex cryptographic and identity logic stays in Wallet4Agent.
Your agent simply calls MCP tools.
Each AI Agent receives a Decentralized Identifier (DID) compliant with the W3C DID Core specification.
Wallet4Agent supports two DID methods:
A DID anchored on a domain.
did:web:wallet4agent.com:<agent-id>
⭐ Characteristics:
https://wallet4agent.com/did/<agent-id>🔗 DID:web specification:
https://www.w3.org/TR/did-spec-registries/#did-method-web
A DID anchored on the Cheqd decentralized ledger.
did:cheqd:<network>:<identifier>
⭐ Characteristics:
🔗 DID:cheqd specification:
https://docs.cheqd.io/identity/
Regardless of DID method, the DID Document exposes:
DID Documents are automatically updated when:
External agents and services use the DID Document to verify signatures, credentials, and linked proofs.
Linked VP allows Wallet4Agent to publish verifiable credentials inside the DID Document as references.
Why this matters:
Supported formats:
Specification:
https://identity.foundation/linked-vp/spec/v1.0.0/
Each agent has a dedicated cloud KMS key.
Used for:
Benefits:
Developers may register additional public JWKs:
private_key_jwtWallet4Agent stores the public keys; developers retain the private keys.
Wallet4Agent supports three agent authentication flows:
Authorization: Bearer <agent_pat>
Simple and effective for development or local agents.
Agent receives:
client_id = Agent DIDclient_secretThen exchanges using:
grant_type=client_credentials
Ideal for most production requests.
Strongest method:
Useful for hardware-backed keys and enterprise infrastructures.
Wallet4Agent handles complete credential issuance flows:
Supported formats:
Agents only call MCP tools — Wallet4Agent does all protocol-level work.
Wallet4Agent supports verification of:
Agents can:
The agent never sees sensitive tokens; only derived, safe claims are returned.
Wallet4Agent stores credentials as attestations, including:
Agents can:
Published under:
/.well-known/oauth-protected-resource/mcp
Includes:
Enables automatic configuration by OAuth2 clients and gateways.
Wallet4Agent supports human-in-the-loop requirements:
{
"always_human_in_the_loop": true
}
Used for:
If you are an Agent developer, Wallet4Agent gives you:
| Feature | What you get |
|---|---|
| 🆔 Agent identity | DID + DID Document |
| 🔑 Authentication | Dev PAT, Agent PAT, OAuth2 Client Credentials, private_key_jwt |
| 🔐 Cryptographic keys | Cloud KMS signatures, non‑exportable |
| 📜 Credential issuance | Full OIDC4VCI support (SD‑JWT VC & VC JSON‑LD) |
| ✅ Credential verification | OIDC4VP with simple MCP tools and safe derived claims |
| 👤 Human interaction | QR code → wallet → verified attributes |
| 🤝 Inter‑agent trust | Ability to inspect credentials of other agents (when authorized) |
| ⚙️ Configuration | Auth mode, keys, policies all manageable via MCP |
| 🛡️ Security | KMS, OAuth2, DID rotation & key updates, role‑separated tokens |
Your AI Agent becomes a verifiable digital entity, capable of participating in decentralized and regulated digital identity ecosystems while preserving security and accountability.
Maintainer: Wallet4Agent (Web3 Digital Wallet / Talao )
For feedback or additional documentation, use the contact channels on the Wallet4Agent website.
| Standard | Purpose | Link |
|---|---|---|
| DID Core | Core DID specification | https://www.w3.org/TR/did-core/ |
| Linked Verifiable Presentations | Public VCs in DID Documents | https://identity.foundation/linked-vp/spec/v1.0.0/ |
| OIDC4VCI | Credential issuance | https://openid.net/specs/openid-4-verifiable-credential-issuance-1_0.html |
| OIDC4VP | Credential presentation | https://openid.net/specs/openid-4-verifiable-presentations-1_0.html |
| W3C Verifiable Credentials | VC Data Model | https://www.w3.org/TR/vc-data-model-2.0/ |
| SD-JWT VC (IETF) | Selective disclosure credential format | https://www.ietf.org/archive/id/draft-ietf-oauth-sd-jwt-vc-12.html |
Be the first to review this server!
by Toleno · Developer Tools
Toleno Network MCP Server — Manage your Toleno mining account with Claude AI using natural language.
by mcp-marketplace · Developer Tools
Create, build, and publish Python MCP servers to PyPI — conversationally.
by Microsoft · Content & Media
Convert files (PDF, Word, Excel, images, audio) to Markdown for LLM consumption