lawstar-dsh-mcp
Run the following command in DeepSeek Harness:
dsh plugin install law-star-cn/lawstar-dsh-mcp
Paste the following prompt into your AI chat to install this plugin:
In a DeepSeek Harness session, send the GitHub URL https://github.com/law-star-cn/lawstar-dsh-mcp to the Agent and say "help me install this plugin" to complete installation and registration automatically.
About this plugin
When drafting with a large language model, citing a statute that does not exist or mixing up a clause number is far more dangerous than a straightforward wrong answer. lawstar-dsh-mcp bridges DeepSeek Harness conversations with the LawStar legal-database MCP. Paste an API Key and you can immediately search statutes, retrieve full text, batch-identify legal citations in any document, and run hallucination checks on AI-generated references - turning guesswork into verifiable citations.
Six MCP tools are available out of the box: semantic statute search, clause text retrieval by law name and article number, keyword-based statute listing, batch citation recognition in text, batch AI hallucination checking, and batch reference retrieval across multiple laws. The API Key is stored securely in a local 0700 directory and shown in masked form in conversation logs; three built-in management tools (connect, status, disconnect) mean no OAuth flow and no manual config files - a simple restart restores the session.
It is built for legal counsel, compliance teams, legal researchers, and anyone who needs precise statutory citations inside AI conversations. If you are tired of manually cross-checking every article number the model produces, this plugin is worth installing.
Use Cases
- Search and retrieve relevant statute text by semantic query in chat
- Verify whether AI-drafted legal documents cite statutes accurately
- Batch-identify all legal references inside contracts or research papers
Best For
- Legal counsel and compliance teams
- Legal researchers and academics
- AI power users who need precise statutory citations
Related Plugins
ModLens is a vision plugin for DeepSeek Harness that gives text-only models sight by reading images pasted directly into chat, with zero-config setup and multiple vision engines.
On-demand vision for text-only DeepSeek Harness agents: built-in free keyless vision chain and 14 vision tools, routing image turns as tool calls to vision models with pixel fidelity, no Python needed, one-command install.
Give text-only models in DeepSeek Harness eyes, enabling image Q&A, long-screenshot OCR, UI restoration, and GUI visual tasks.
An armor-breaking plugin for DeepSeek: rewrites instruction priority, expands refusal-blocked phrases, persists across sessions, and shows a green active indicator.