A
agentic-ops/legal-mcp
Precedent, statute and contract tools for legal workflows
在 GitHub 查看 ↗链接已于 2026-11-12 核查 · 自动访问被拒（HTTP 429），状态未能确认
安装与配置
客户端配置（取自该仓库的安装命令）
{
"mcpServers": {
"agentic-ops-legal-mcp": {
"command": "npx",
"args": ["@modelcontextprotocol/inspector"]
}
}
}解析自我们于 2026-11-07 抓取的该仓库 README；我们未执行过。
command/args 来自仓库写明的安装命令；不确定时请以该项目 README 为准。
VS Code（.vscode/mcp.json —— 键名是 servers）
{
"servers": {
"agentic-ops-legal-mcp": {
"command": "npx",
"args": ["@modelcontextprotocol/inspector"]
}
}
}VS Code 顶层键是 <code>servers</code>，其余与上面那份相同。
Claude Code（命令行）
claude mcp add --transport stdio agentic-ops-legal-mcp -- npx @modelcontextprotocol/inspector
Claude Code 不收 JSON 文件，用这条命令直接加。
配置项的键名以你的客户端为准：客户端与 CLI
- 来源明细
- 收录自 abordage/awesome-mcp 榜单（我们从中收集的条目之一） · 条目类型：MCP 服务
- 收录与活跃
- 收录于 2026-11-05 · 最近见到 2026-11-14 · 共见到 10 次 · 被 10 个来源列出
- 评分构成
- 综合分 1,003 · 10 个来源 · mcp
- 安装
npx @modelcontextprotocol/inspector
常见问题（答案都来自我们的记录）
怎么安装？
该仓库给出的安装命令是
npx @modelcontextprotocol/inspector。我们的记录里它是仓库自己提供的；不保证在你的客户端上直接可用。它适合谁 / 用来做什么？
我们把它归在这些标签下: MCP 服务。标签来自条目自身，不是我们强加的分类。
谁维护它、还在更新吗？
我们收录于 2026-11-05；最近见到 2026-11-14。这里没有"官方认证"或"质量评级"——我们只记录来源与时间。
# Legal MCP Server — Research, Paralegal & Workflow Automation
以下摘录自该仓库的 README（片段） · 在 GitHub 读完整 README →
A Model Context Protocol (MCP) server for
structured legal workflows. This legal MCP server provides tools, resources,
and prompts for precedent retrieval, statute analysis, citation validation,
contract clause comparison, and guided brief scaffolding. Production mode is
the default: bundled sample legal content is disabled, while real-document
tools and optional opt-in live legal databases remain available.
> This server provides legal‑workflow augmentation, not legal advice. It
> does not replace attorney review and judgment.
Status: V1 — implemented and tested.
Transport: stdio, SSE, and streamable‑HTTP (via FastMCP).
Runtime: Python 3.10+ and the official mcp SDK.
## Contents
Data flow & privacy boundaries
PACER and paid‑database fees (read first)
Quick start
Capabilities
Feature flags (tool categories)
Live integrations (PACER & CourtListener/RECAP)
Docker (optional)
Use as an Agent Skill (Claude, Cursor, Codex, and more)
Built on legal-mcp (showcase)
Forking & building your own
Architecture
Testing, linting & types
Legal & compliance notes
AI agent privacy considerations
Further reading
Integration & development support
License
## Data flow & privacy boundaries
Understanding where data goes is essential before connecting this server to
an AI assistant or enabling live integrations. The diagram below shows the
three separate trust boundaries involved in a typical workflow.
mermaid
flowchart LR
user[User]
aiClient[AI Assistant]
inference[Inference Provider]
mcpServer[Legal MCP Server]
localData[Real local files]
demoData[Opt-in demo content]
courtlistener[CourtListener / RECAP]
pacer[PACER]
user -->|"prompts and documents"| aiClient
aiClient -->|"full conversation context"| inference
aiClient |"MCP tool calls and JSON responses"| mcpServer
mcpServer -->|"local processing"| localData
mcpServer -.->|"explicit demo mode"| demoData
mcpServer -.->|"opt-in, free"| courtlistener
mcpServer -.->|"opt-in, billable"| pacer
| Boundary | What crosses it | Default behavior | Privacy note |
| You → AI assistant | Prompts, uploaded files, tool results pasted into chat | Always active when using an AI client | Your inference provider's ToS governs retention, training, and privilege — not this server |
| AI assistant → MCP server | Tool arguments (file paths, queries, contract IDs) and JSON responses | Local transport (stdio/SSE/HTTP on your machine) | Tool calls are audit-logged locally (utils.audit); responses stay on your network unless you expose the server |
| MCP server → external databases | Search queries to CourtListener or PACER | Disabled by default | Enable only when needed; PACER may incur fees (see below) |
Key takeaway: this MCP server performs local document workflows offline by
default. It does not expose the bundled sample cases, statutes, or contracts
unless LEGAL_MCP_DEMO_MODE=true is explicitly set.
The highest privacy risk in most setups is the inference provider (OpenAI,
Anthropic, Google, OpenRouter, etc.) receiving your full prompt context —
including excerpts returned by these tools. See
AI agent privacy considerations for
provider-specific guidance.
## ⚠️ PACER and paid‑database fees (read first)
If you connect this MCP (or an AI assistant using it) to PACER or other paid
structured legal workflows. This legal MCP server provides tools, resources,
and prompts for precedent retrieval, statute analysis, citation validation,
contract clause comparison, and guided brief scaffolding. Production mode is
the default: bundled sample legal content is disabled, while real-document
tools and optional opt-in live legal databases remain available.
> This server provides legal‑workflow augmentation, not legal advice. It
> does not replace attorney review and judgment.
Status: V1 — implemented and tested.
Transport: stdio, SSE, and streamable‑HTTP (via FastMCP).
Runtime: Python 3.10+ and the official mcp SDK.
## Contents
Data flow & privacy boundaries
PACER and paid‑database fees (read first)
Quick start
Capabilities
Feature flags (tool categories)
Live integrations (PACER & CourtListener/RECAP)
Docker (optional)
Use as an Agent Skill (Claude, Cursor, Codex, and more)
Built on legal-mcp (showcase)
Forking & building your own
Architecture
Testing, linting & types
Legal & compliance notes
AI agent privacy considerations
Further reading
Integration & development support
License
## Data flow & privacy boundaries
Understanding where data goes is essential before connecting this server to
an AI assistant or enabling live integrations. The diagram below shows the
three separate trust boundaries involved in a typical workflow.
mermaid
flowchart LR
user[User]
aiClient[AI Assistant]
inference[Inference Provider]
mcpServer[Legal MCP Server]
localData[Real local files]
demoData[Opt-in demo content]
courtlistener[CourtListener / RECAP]
pacer[PACER]
user -->|"prompts and documents"| aiClient
aiClient -->|"full conversation context"| inference
aiClient |"MCP tool calls and JSON responses"| mcpServer
mcpServer -->|"local processing"| localData
mcpServer -.->|"explicit demo mode"| demoData
mcpServer -.->|"opt-in, free"| courtlistener
mcpServer -.->|"opt-in, billable"| pacer
| Boundary | What crosses it | Default behavior | Privacy note |
| You → AI assistant | Prompts, uploaded files, tool results pasted into chat | Always active when using an AI client | Your inference provider's ToS governs retention, training, and privilege — not this server |
| AI assistant → MCP server | Tool arguments (file paths, queries, contract IDs) and JSON responses | Local transport (stdio/SSE/HTTP on your machine) | Tool calls are audit-logged locally (utils.audit); responses stay on your network unless you expose the server |
| MCP server → external databases | Search queries to CourtListener or PACER | Disabled by default | Enable only when needed; PACER may incur fees (see below) |
Key takeaway: this MCP server performs local document workflows offline by
default. It does not expose the bundled sample cases, statutes, or contracts
unless LEGAL_MCP_DEMO_MODE=true is explicitly set.
The highest privacy risk in most setups is the inference provider (OpenAI,
Anthropic, Google, OpenRouter, etc.) receiving your full prompt context —
including excerpts returned by these tools. See
AI agent privacy considerations for
provider-specific guidance.
## ⚠️ PACER and paid‑database fees (read first)
If you connect this MCP (or an AI assistant using it) to PACER or other paid
收录徽章（可选）
想把收录标记放进 README 就复制这行，可选，不影响收录。
[](https://anclum.com/zh/s/agentic-ops-legal-mcp/)
- 来源
- awesome · https://github.com/agentic-ops/legal-mcp
- 按领域浏览
- MCP 服务
- 收录来源
- 10 个独立来源
- 收录于
- 今天
同类推荐
所属领域与标签
每个标签都能点进去看同类的全部条目。数字是当前库里的真实条数。