Anthropic Scales Claude Cowork Legal Automation With 20+ MCP Connectors And 12 Plugins

Anthropic said in a Tuesday (May 12) blog post that it is scaling legal automation for Claude Cowork with more than 20 Model Context Protocol (MCP) connectors and 12 plugins for specific legal work and practice areas.

“We have been building toward this moment, and now it’s finally arrived”

Artificial Lawyer

The company said the new MCP connectors enable Claude to connect with legal industry systems for contract lifecycle and drafting, deal rooms and transaction documents, document management, eDiscovery and review, legal research and case law, and public service.

Artificial Lawyer

Anthropic also said the 12 practice-area plugins are each built around a specific legal role and can be tailored to each team, with each agent template installed in Cowork or Claude Code.

In the same announcement, Anthropic tied the update to Claude Opus 4.7, describing it as “our most capable publicly available model for legal reasoning and long-document work.”

Quartz said Anthropic launched 12 new plugins and MCP connectors linking Claude to Thomson Reuters, Harvey, DocuSign, and other legal platforms, with users able to draw on those external platforms from within Claude itself.

Thomson Reuters also said its next generation of CoCounsel Legal is being rebuilt on Anthropic's Claude Agent SDK, with general availability expected this summer, while Mark Pike, Anthropic's associate general counsel, discussed the effort.

Fortune

Fortune reported that Anthropic’s underlying model, Claude Opus 4.7, scored 90.9% on Harvey’s BigLaw Bench, and said Anthropic released “more than 20 new integrations with the tools law firms already rely on.”

Fortune added that Freshfields, Quinn Emanuel Urquhart & Sullivan, Holland & Knight, and Crosby Legal are using Claude on live matters, and quoted Gerrit Beckhaus saying Claude has become an “essential part” of Freshfields’ proprietary AI-powered solutions.

Fortune described a legal backlash in courtrooms and filings, saying lawyers were caught submitting briefs containing citations to cases that never existed—ghost precedents conjured by AI tools.

“Anthropic announced Tuesday that it built 12 plug-ins for various legal practice areas for its Claude large language model (LLM) and AI chatbot”

Law

To address that risk, Fortune said Anthropic’s answer is “grounding,” with connector architecture designed so that Claude can only draw from live, verified sources rather than generating answers from memory.

The same Fortune report said Anthropic is also making an access-to-justice argument, noting that “Roughly 80% of civil litigants appear in court without a lawyer,” and quoting Sonja Ebron, CEO and co-founder of Courtroom5, saying “Claude can now meet them where they are—in the moment they’re scared and searching for answers.”

In parallel, Law.com quoted Mark Pike saying Anthropic built the legal practice plug-ins because legal work requires “in-depth document comprehension,” and said the company is keeping a human in the loop on decision making.