Brain B70d45d7

MCP运维云端

提供方 Raulvalverdeleal

运维云端 未标注 无需鉴权 社区 / 第三方

Brain是一个为AI编码代理设计的懒加载技能服务,通过MCP服务器实现按需加载技能片段,显著减少上下文令牌使用,提升效率。

一句话选型结论

按资料字段整理

Brain B70d45d7 属于运维云端类 MCP 服务器,传输方式未标注,无需鉴权,没有现成安装命令,需按官方文档接入。接入前先确认权限范围;涉及写入、删除或付款的操作,建议先在测试环境验证。

分类运维云端 传输方式未标注 鉴权无需鉴权 部署方式未标注
GitHub 星标 1 仓库热度,无公开仓库时显示未标注
工具数 7 暴露给模型的工具数量
资源 / 提示词 0 / 0 资源与提示词模板数量
维护方 社区 / 第三方 核验等级 仅资料核对

工具与能力

运维云端
数量来自来源目录的标注,具体工具清单以官方文档为准
工具数量7暴露给模型可调用的工具个数
资源数量0可读取的资源条目
提示词数量0内置提示词模板数量

能力标签

适用场景

懒加载Python本地部署AI编码代理技能管理MCP服务器上下文优化

安装与配置

未标注 无需鉴权
上游未给出传输方式
  1. 1
    准备运行环境

    按官方文档确认运行环境(常见为 Node.js 或 Python),装好后再执行安装命令。

  2. 2
    安装服务

    复制上面的安装命令执行;命令里带占位符的位置,换成自己的密钥或路径。

  3. 3
    写入客户端配置

    在客户端的 MCP 配置里填好启动命令和参数,保存后完全退出客户端再打开,让新配置生效。

  4. 4
    验证是否可用

    连接成功后客户端会列出约 7 个工具,随便调一个只读工具确认能返回结果。

典型使用场景

3 类
按分类与标签整理的常见用法,具体以官方文档为准
云资源查询

查实例、存储、账单等云上资源状态。

部署与发布

把部署、重启、回滚这类操作接进对话。

监控与告警

拉取监控指标,异常时让模型帮你判断。

选择建议

选之前先看这几条
按条目字段给出的判断,不替你决定用不用

值得选的地方

  • 资料标注 7 个工具,职责相对集中,接入后不容易误操作。
  • 资料标注无需鉴权,装好就能连。

先想清楚的地方

  • 没有现成安装命令,需要按官方文档自己填启动命令和参数。
  • 版本更新与行为细节以官方仓库为准。

更适合

  • 需要在运维云端场景里让模型直接调用外部能力的人。
  • 想先快速试一下、能接受在本地或自有环境跑服务的人。

不太适合

  • 需要厂商级 SLA 和技术支持的生产环境。

同类对比

6 个同类
同分类里挑最接近的几条,字段以各自详情页为准
MCP 服务器工具数传输方式部署方式安装命令最后核验
Brain B70d45d7当前 7 未标注 未标注 无 2026-05-17
lobehub 未标注 stdio · 本地进程 本地部署 有 2026-04-11
TrendRadar 未标注 stdio · 本地进程 本地部署 有 2026-04-13
Ui Tars Desktop 8a825770 未标注 stdio · 本地进程 本地部署 有 2026-05-17
ruflo 未标注 stdio · 本地进程 本地部署 有 2026-04-13
FastGPT 未标注 stdio · 本地进程 本地部署 有 2026-04-11

服务器档案

运维云端
字段来自项目仓库与公开索引,中文说明由本站标注
提供方Raulvalverdeleal上游标注的维护方 Raulvalverdeleal
分类运维云端本站按上游分类展示
连接方式未标注上游未给出传输方式
鉴权方式无需鉴权远程服务建议用最小权限凭据
维护方社区 / 第三方核验等级 仅资料核对
包名 / 运行时未标注 · 未标注本地安装时用到的包标识与运行时
部署类型未标注上游给出的部署形态
最近核验2026-05-17上游最后核验时间

详细介绍

9.3 KB
来自项目仓库与上游目录的原文,未做删改

Brain

Lazy loading for AI coding agent skills. A token-efficient MCP server that lets agents fetch only the skill sections they need, when they need them — without loading entire skill libraries into context.

Each skill is a folder with a SKILL.md that tells the agent how to approach a specific task — what tools to use, what patterns to follow, what to watch out for. Skills are loaded progressively via the MCP server, not pulled into context all at once.

One standard format. Any model. Any IDE. Zero context bloat.


Benchmarks

Same task, same project, same prompt — API documentation with two skills loaded.

Brain (MCP) Raw markdown files
Context tokens 20,000 150,000
Cost $0.03 $0.24
Lines added 876 693
Lines removed 161 90

Brain used 86% fewer tokens while producing 26% more output. The agent fetched only the sections it needed via progressive disclosure — it never loaded the full skill files.


How it works

Skills live in ~/.agents/skills/ but agents must never access this directory directly. Instead, they use the MCP server (brain_mcp.py) to fetch only what they need, when they need it, without loading entire files into context.

Why this matters: Loading all skills into context wastes tokens and degrades performance. Brain's progressive disclosure ensures agents fetch only relevant sections — reducing context usage by 86%.

Security note: You should deny agent access to ~/.agents/skills and disable any direct skill-loading tools. Skills must always be accessed via the MCP server to maintain token efficiency.

The CLI (brain) handles registry management: syncing from remote, searching, and organizing skills.```
~/.brain/
├── brain_mcp.py ← MCP server (agent access layer)
├── brain_cli.py ← CLI tool for registry management
├── index.json ← pre-built frontmatter index
└── scripts/
└── build_index.py ← called by brain sync to regenerate index.json

~/.agents/
└── skills/ ← all available skills (agents must NOT access directly)
├── frontend-design/
│ └── SKILL.md
└── ...


---

## Setup

### 1. Clone the registry```bash
git clone https://github.com/Raulvalverdeleal/brain ~/.brain

2. Install brain

brain is the CLI for registry management. Make it available globally:```bash

Option 1: Create an alias

echo 'alias brain="python3 ~/.brain/brain_cli.py"' >> ~/.zshrc
source ~/.zshrc

Option 2: Create a symlink in your PATH

ln -s ~/.brain/brain_cli.py /usr/local/bin/brain


### 3. Build the index```bash
brain build-index

This parses all skill frontmatters once and writes ~/.brain/index.json. The MCP server loads this file at startup instead of scanning hundreds of files — startup goes from seconds to milliseconds.

> brain requires Python 3. No dependencies beyond the standard library.

4. Register the MCP server

Add to your MCP config (e.g. claude_desktop_config.json, opencode.json, etc.):```json
{
"mcpServers": {
"brain": {
"command": "python3",
"args": ["~/.brain/brain_mcp.py"]
}
}
}


Or for stdio-based transport:```json
{
  "mcp": {
    "brain": {
      "command": "python3",
      "args": ["~/.brain/brain_mcp.py"]
    }
  }
}

The server auto-installs its only dependency (mcp[cli]) on first run.

5. Secure your setup (important)

Never let agents access ~/.agents/skills directly. Doing so defeats lazy loading and wastes tokens by loading all skills into context.

To enforce this:

  1. Deny filesystem access to ~/.agents/skills in your agent configuration
  2. Disable direct skill-loading tools if your platform has them
  3. Add to your global AGENTS.md:- Do not access skills via `/Users/username/.agents/skills` use always brain mcp server instead.
  4. Only expose the Brain MCP server for skill access — it handles progressive disclosure automatically

CLI reference```

brain sync Pull registry and rebuild index if changed
brain search <query> [--page N] Search skills (prefix terms with - to exclude)
brain info <skill> Show metadata and file tree for a skill
brain list List all skills in the registry


**Examples:**```bash
brain sync
brain search &quot;react state management&quot;
brain search frontend -azure --page 2
brain info   react-best-practices
brain list

sync

Runs git pull. If changes are detected — or if index.json is missing — it rebuilds the index automatically. If the registry is already current, it prints index stats and exits.```
● Syncing ~/.brain ...
✓ Already up to date.
──────────────────────────────────────────────────
index 2025-01-05T10:22:11Z 943 skills
no changes — index up to date


### search

Scores skills against your query and returns ranked results (3 per page via MCP, 5 per page via CLI). Name matches score highest, then keywords, then description. Use `-term` to exclude noisy results.```bash
brain search &quot;react state&quot;
brain search postgres -azure -cloud
brain search &quot;api design&quot; --page 2

info

Shows full metadata for a skill: description, keywords, dependencies, file tree.```bash
brain info postgres-best-practices


---

## MCP server tools

The MCP server exposes seven tools for progressive skill access. Agents move through levels only as deep as needed — **a typical session costs ~400 tokens vs 2000+** loading a full skill file cold.```
skill_search    → find candidates (paginated, ranked)
skill_info      → frontmatter + file tree, zero content cost
skill_toc       → heading tree only, up to 5 skills at once
skill_section   → one section by slug
skill_get       → full SKILL.md content
skill_get_file  → any supporting file (references/, scripts/)
skill_index_status → health check, force reload after sync

Progressive disclosure flow```

agent: skill_search("figma design implementation")
→ 3 results, page 1 of 2

agent: skill_info("figma-implement-design")
→ frontmatter + file tree (no content loaded)

agent: skill_toc("figma-implement-design")
→ heading tree with slugs, dependency TOCs appended

agent: skill_section("figma-implement-design", "phase-3-design-tokens")
→ only that section


### skill_search

Paginated search across all skills. Returns 3 results per page via MCP server (5 per page via CLI). Supports negative filtering.```
query: &quot;figma design&quot;  matches:4  page:1/2

→ call skill_search(query=&#x27;figma design&#x27;, page=2) for more

■ figma-implement-design  (score:14)
  Full workflow to go from a Figma file to production-ready code...

skill_toc

Returns the heading tree of one or more skills as addressable slugs. Pass up to 5 IDs in one call to plan your section fetches upfront.```
■ figma-implement-design

phase-1-orient Phase 1 — Orient

phase-2-visual-reference Phase 2 — Visual reference

#phase-3-design-tokens Phase 3 — Design tokens
...

supporting files:
references/advanced-patterns.md


Dependency TOCs are listed but not expanded automatically — the agent requests them explicitly if needed.

### skill_section

Fetches content from one heading to the next heading of equal or higher level. The primary efficiency tool — use it instead of `skill_get` whenever possible.```bash
skill_section(&quot;figma-implement-design&quot;, &quot;phase-3-design-tokens&quot;)

skill_info

Returns frontmatter metadata and file tree with zero content cost. If a skills.json exists in the project with notes for this skill, they are appended automatically.


How skills work

When the agent receives a task, it uses skill_search to find relevant skills, then progressively loads content via skill_toc and skill_section. The agent fetches skill_get only when it needs the full document.

Skills are intentionally independent — you only load what your task needs.

Skill structure```

~/.agents/skills/
└── your-skill-name/
├── SKILL.md ← required
├── references/ ← optional: supplementary docs
└── scripts/ ← optional: helper scripts


### Required frontmatter

Every `SKILL.md` must start with a YAML frontmatter block:```yaml
---
name: your-skill-name
description: One or two sentences. When should an agent use this skill?
keywords: react ui components typescript
---

name and description are required.
keywords is optional but improve search ranking and dependency resolution.

index.json

index.json is generated by build_index.py and is the MCP server's data source. It contains parsed frontmatter for every skill — never full content. Rebuild it after any brain sync that pulls changes.json { &quot;_meta&quot;: { &quot;built_at&quot;: &quot;2025-01-05T10:22:11Z&quot;, &quot;skill_count&quot;: 943 }, &quot;skills&quot;: { &quot;frontend-design&quot;: { &quot;name&quot;: &quot;frontend-design&quot;, &quot;description&quot;: &quot;...&quot;, &quot;keywords&quot;: [&quot;react&quot;, &quot;ui&quot;, &quot;css&quot;], &quot;file_tree&quot;: [&quot;SKILL.md&quot;], &quot;has_references&quot;: false, &quot;has_scripts&quot;: false } } }

TODOS

  • [ ] Build index when a skill is added / re-build index on mcp launch.

常见问题

5 问
答案由本站依据条目字段整理,不引用上游原文
Brain B70d45d7 怎么安装?

资料没有给出安装命令,请到官方仓库或文档按说明接入;这类条目多数是生态应用,或尚未发布可安装包。

Brain B70d45d7 怎么在客户端里配置?

它的传输方式未标注,在客户端 MCP 配置里按官方文档填写启动命令和参数,保存后重启客户端生效。

Brain B70d45d7 收费吗?

本站不代收费用,也没有标注具体价格。是否收费取决于服务本身和背后的接口额度,正式使用前按官方说明确认。

Brain B70d45d7 需要 API Key 吗?

资料标注为无需认证,装好就能连;如果实际调用时报鉴权错误,按官方文档补上凭据。

Brain B70d45d7 能提供哪些能力?

资料显示约 7 个工具;能力标签包括 技能管理、Python、云端部署。具体工具清单以官方文档为准。

热门专题

按标签挑服务器
全部专题 →

服务器信息以作者仓库与官方文档为准;分类、传输方式与鉴权方式的中文说明为中文整理,最近核验 2026-05-17。