Dock Labs launches AI agent MCP server for digital identity

Last year, the arrival of AI agents was greeted with excitement in the tech space. This year, however, the security risks of agentic AI have become more visible, with companies now developing tools to control them, especially in the sensitive space of digital identity.

Dock Labs has released a Model Context Protocol (MCP) server that allows organizations to issue and verify credentials, manage DIDs, and generate presentation requests directly through LLM-powered agents, all while maintaining tight control over what those agents are allowed to do.

The integration addresses a practical security concern in agentic software. Giving an AI agent broad API access to sensitive infrastructure creates a difficult-to-manage attack surface. The MCP layer acts as a structured intermediary between autonomous systems and Dock Labs’ digital ID infrastructure, allowing organizations to expose only specific identity functions to agents while keeping other operations off-limits.

“Rather than granting agents broad API access, the MCP layer allows enterprises to expose tightly scoped identity functions, supporting least-privilege access and safer automation,” the firm notes, adding that the product is focused on the emerging agentic commerce ecosystem.

Dock Labs explains that Model Context Protocol is an emerging standard that provides a uniform way for AI agents and LLMs to call external tools and services. Rather than hard-wiring credential logic into an agent or handing over API keys, MCP lets developers define exactly which capabilities an agent can access.

The company has applied this model to its digital identity infrastructure, making it callable directly by agents and LLMs using natural language workflows. This means an agent could create new Decentralized Identifiers (DIDs), configure DID profiles, issue digital ID credentials, create proof requests and verify credentials.

A second MCP server is already in development, focused on wallet functionality, including credential storage, credential presentation, and more specialized agent flows. Dock Labs says the broader goal is not a single all-purpose tool, but a collection of composable, purpose-built identity capabilities that can be mixed and matched depending on the use case.

Other identity companies are also developing Model Context Protocol products. Earlier this month, Vouched said it has formally donated its Model Context Protocol – Identity (MCP-I) framework to the Decentralized Identity Foundation (DIF).

The Model Context Protocol (MCP) was originally developed by Anthropic and open-sourced under the Agentic AI Foundation (Linux Foundation). MCP-I extends this framework by introducing a complete identity and delegation layer for AI agents, leveraging Decentralized Identifiers (DIDs) and Verifiable Credentials (VCs) to enable the cryptographic verification of agents and human principals without prior coordination, the Seattle-based company says.

Article Topics

AI agents  |  cybersecurity  |  digital identity  |  Dock  |  identity access management (IAM)  |  identity security