CodeNeuro
Enables Hermes coding agents to use CodeNeuro's MCP tools for scoped context retrieval, recording runtime findings, patching or revoking stale rules, proposing architecture contract changes, and listing active rules.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@CodeNeuroget the architecture contracts and P0 rules for src/services/pay/calc.ts before I edit it"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
CodeNeuro
面向 Coding Agent 的任务、需求和规则上下文 Hub,提供 Web 工作台与 MCP 接口。
按 Project → Requirement → Task 管理整体业务目标和可独立开发、验证的子任务。
按业务主题或文件范围检索规则,显式选择 P0–P3 优先级。
管理规则审阅、测试证据、下发记录与反馈。
安装与启动
需要 Python 3.11+。在仓库目录执行:
uv venv
uv pip install --python .venv/bin/python -r requirements.txt
# 初始化新数据库
.venv/bin/python -m codeneuro init-db --db /absolute/path/codeneuro.db
# 启动 Hub
.venv/bin/python -m codeneuro serve --db /absolute/path/codeneuro.dbWindows 将 .venv/bin/python 替换为 .venv/Scripts/python.exe。
打开 http://127.0.0.1:8801/app/,注册项目后即可使用工作台。所有子任务验证完成后,需求等待用户整体验收。Agent 直接传项目和任务,无需创建或关闭 Session。
代码只维护当前模型和接口。已有本地数据用一次性迁移脚本转入新库,原库保留;操作说明见需求与任务设计。
Related MCP server: uacos
MCP 接入
支持 stdio MCP 的客户端可配置:
{
"mcpServers": {
"codeneuro": {
"command": "/absolute/path/to/python",
"args": ["-m", "codeneuro", "mcp", "--db", "/absolute/path/codeneuro.db"]
}
}
}Hub 的 Streamable HTTP MCP 地址为 http://127.0.0.1:8801/mcp/。详细使用见 客户端接入与使用。
使用边界
Web API 和 MCP 无鉴权,默认仅监听本机,不应直接暴露公网。
Agent 主动查询上下文;Hub 不拦截文件操作,也不替 Agent 执行编码或测试。
规则以 Hub 数据库为准,不向工作区生成规则文件副本。
文档
This server cannot be deployed
Maintenance
Related MCP Connectors
Give your AI agent persistent, governed memory for every project. At task start it recalls the approved decisions, conventions, risks and architecture (semantic search, ranked by importance); at close it proposes what was learned as typed memories that you review and approve — governance, not a notes dump. Agents propose, humans govern: edits go back to pending and deletion is human-only by design. Connect Claude Code, Cursor, Claude Desktop or any MCP client in two minutes with just your API key — hosted (nothing to install) or locally via `uvx solucortex-mcp`. Built by SoluAI and dogfooded daily: SoluCortex is developed using its own living memory.
Path-scoped project memories, rules and skills for coding agents, on your machine or Pathrule Cloud.
System-of-record notebook for AI coding agents: pages, datastores, tasks, skills over MCP.
Project management shared by people and AI agents, with persistent project state through MCP.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceProvides AI agents with queryable, version-controlled project rules and coding standards. Enables validation, rule-based guidance, and task summaries to keep AI work aligned with your project's conventions without repeating context.2MIT
- AlicenseNot gradedqualityBmaintenanceLocal-first code intelligence and safety layer for AI coding agents. MCP server exposes dependency graph, impact analysis, and AST-compressed repo context, backed by typed local memory, patch-scope safety gates, and git-independent transaction rollback.1MIT
- AlicenseNot gradedqualityBmaintenanceGives coding agents a local, SQLite-backed memory of a codebase, enabling them to query symbol impact, change history, and task scope through MCP while recording what actually changed after edits.MIT
- AlicenseCqualityBmaintenanceLocal-first MCP runtime for coding agents with bounded workspace access, content-preconditioned writes, AST search, LSP navigation and diagnostics, and Git status/diff. Designed to give coding agents useful repository access without treating unrestricted shell access as the default integration boundary.133MIT