ZS (Zobr Script)

MCP其他

提供方 docxi-org

其他 未标注 无需鉴权 社区 / 第三方

A cognitive scripting language for structured reasoning with LLMs. 12 built-in operations (survey, ground, assert, doubt, contrast, synthesize, etc.) for guiding AI through dialectical analysis, impact assessment, and other thinking patterns.

一句话选型结论

按资料字段整理

ZS (Zobr Script) 属于其他类 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。

分类其他 传输方式未标注 鉴权无需鉴权 部署方式支持远程部署
GitHub 星标 未标注 仓库热度,无公开仓库时显示未标注
工具数 未标注 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

其他
数量来自来源目录的标注,具体工具清单以官方文档为准
工具数量未标注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

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

    确认你的客户端支持远程端点,并拿到服务地址。

  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

    连接成功后随便调一个只读工具,确认能返回结果,再接入正式流程。

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
接入外部数据

把外部系统的数据接进对话。

自动化重复操作

把固定步骤交给模型跑。

补充工具能力

给模型补上它原本没有的能力。

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

  • 资料标注无需鉴权,装好就能连。

先想清楚的地方

  • 远程端点依赖网络与服务方可用性,注意密钥与调用额度。
  • 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。
  • 资料没标注工具数量,实际能力要装好后确认。
  • 版本更新与行为细节以官方仓库为准。

更适合

  • 需要在其他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
ZS (Zobr Script)当前 未标注 未标注 支持远程部署 无 2026-05-17
gemini-cli 未标注 stdio · 本地进程 本地部署 有 2026-04-13
ext-apps 未标注 stdio · 本地进程 本地部署 有 2026-04-19
northcinder 未标注 stdio · 本地进程 本地部署 有 2026-08-23
fastctx 未标注 stdio · 本地进程 本地部署 有 2026-08-23
quickstart-resources 未标注 stdio · 本地进程 本地部署 有 2026-04-12

服务器档案

其他
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docxi-org上游标注的维护方 docxi-org
分类其他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
部署类型支持远程部署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

6.4 KB
来自项目仓库与上游目录的原文,未做删改

ZS (Zobr Script)

A cognitive scripting language for structured reasoning with LLMs


ZS provides formal constructs for describing reasoning processes — not as rigid instructions, but as composable cognitive operations with variables, control flow, and result formatting.

Think of it as SQL for thinking: you define what cognitive steps to take, the LLM decides how to execute them.

Scripts are executed by an LLM as interpreter: the model reads a .zobr file, executes operations step by step, tracks variables, follows control flow, and produces structured output.

Quick Example```

task: "Evaluate risks of AI in education"

risks = survey("main risks of AI in education", count: 4)
evidence = for r in risks {
concrete = ground(r, extract: [examples, studies])
yield { risk: r, evidence: concrete }
}
overview = synthesize(evidence, method: "rank by severity")

result = conclude {
top_risks: list
most_critical: string
recommendation: string
confidence: low | medium | high
}


## 12 Built-in Cognitive Operations

Operations are organized into five categories:

**Discovery** — explore and extract

| Operation | Description |
|-----------|-------------|
| `survey(topic, count?)` | Explore a topic and identify key elements — positions, factors, perspectives |
| `ground(claim, extract?)` | Connect a claim to concrete evidence, facts, or experience |

**Argument** — reason and challenge

| Operation | Description |
|-----------|-------------|
| `assert(thesis, based_on?)` | State a position with reasoning |
| `doubt(target)` | Problematize a claim — find weaknesses, hidden assumptions, edge cases |
| `contrast(target, with?)` | Find or construct the strongest opposing position or counterexample |
| `analogy(target, from?)` | Transfer understanding from another domain to reveal hidden structure |

**Synthesis** — combine and transform

| Operation | Description |
|-----------|-------------|
| `synthesize(sources, method?)` | Combine multiple findings into emergent insight (not just a summary) |
| `reframe(target, lens?)` | Reformulate a problem in different terms, change the analytical lens |

**Meta** — reflect and steer

Operation · Description
`assess(scale?)` · Reflective pause — evaluate the current state of reasoning (open/converging/stuck)
`pivot(reason)` · Explicitly change reasoning strategy when the current approach is insufficient
`scope(narrow\ · wide)` · Control analytical zoom — from specific mechanisms to systemic connections

**Output**

| Operation | Description |
|-----------|-------------|
| `conclude { ... }` | Define the structure and format of the final result |

Plus: variables, `for`/`if`/`loop` control flow, user-defined functions (`define`), `yield`, `import`, `@last`/`@N` references.

## `zobr-check` — Static Validator

The package includes a CLI tool for static validation of `.zobr` scripts:```bash
# Install from source
git clone https://github.com/docxi-org/zobr-script.git
cd zobr-script
npm install && npm run build

# Validate a script
node dist/cli.js script.zobr

The validator checks:
- Syntax correctness (PEG grammar)
- Undefined variable references
- Correct operation signatures (positional/named argument counts)
- Unused variables (warnings)
- Reserved word misuse

How It Works

In the current version, a ZS script is executed by an LLM as interpreter:

  1. Provide the language spec and system prompt as context — together they define the full operation semantics, control flow rules, and output format
  2. Pass a .zobr script as the task
  3. The LLM executes operations step by step, tracking variables and following control flow
  4. Output is structured according to the conclude block

MCP Server

Connect ZS to Claude, Claude Desktop, or any MCP client — no installation needed.

MCP endpoint: https://zobr-script-mcp.docxi-next.workers.dev/mcp

In claude.ai: Settings → Connectors → Add custom connector → paste the URL above.

Tools provided:
- zs_execute — feed a script, get full spec + interpreter context injected automatically
- zs_validate — full PEG parser + semantic validation (same as zobr-check)
- zs_operations — quick reference for all 12 operations

Also available on Smithery.

Benchmark Results

Tested with three Claude models across 5 tasks of increasing complexity:

Model Composite Score Structural Compliance Content Quality Generation Quality
Claude Opus 4.6 9.4 / 10 9.8 9.4 9.0
Claude Sonnet 4.6 9.3 / 10 9.7 9.3 9.0
Claude Haiku 4.5 7.9 / 10 9.3 7.0 7.5

Key findings:
- Structure compresses the capability gap: Sonnet achieves near-parity with Opus (9.3 vs 9.4) — when reasoning structure is provided by the script, the model's job shifts from organizing thought to filling containers with content
- Even the smallest model follows scripts with 93% structural fidelity: ZS is a reasoning amplifier, not a capability test
- All models generate valid scripts: Task 05 (script generation) produced 0 syntax errors across all models

Full results: benchmark report ・ infographic ・ на русском ・ инфографика

Use Cases

  • Repeatable analysis patterns — encode your best analytical workflow once as a .zobr script, apply it to any new input
  • Quality assurance for AI reasoning — auditable operations with visible variable flow, not black-box responses
  • Cost optimization via model routing — use smaller models for structural tasks, larger models only where depth matters
  • Knowledge capture — distill exceptional AI reasoning into reusable .zobr artifacts
  • Education & critical thinking — externalize the structure of rigorous thinking: survey before asserting, doubt your own claims, contrast with the strongest counter
  • Multi-agent cognitive workflows — scripts as shared protocols between agents

What ZS Is Not

  • Not a prompt template engine (see POML)
  • Not an LLM orchestration framework (see DSPy, LangChain)
  • Not chain-of-thought prompting

ZS operates at a different level: it formalizes cognitive operations themselves as first-class language constructs.

Documentation

  • Language Specification v0.1
  • System Prompt for LLM Interpreter
  • Test Tasks
  • Benchmark Report ・ на русском

Status

Spec v0.1. Benchmark complete (3 models × 5 tasks). Static validator shipped.

License

Apache License 2.0 — see LICENSE


Part of the Black Zobr ecosystem.

常见问题

7 问
答案由本站依据条目字段整理,不引用上游原文
ZS (Zobr Script) 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。

ZS (Zobr Script) 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。

ZS (Zobr Script) 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。

ZS (Zobr Script) 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。

ZS (Zobr Script) 能提供哪些能力?

资料显示能力标签包括 开发工具、自动化、API集成。具体工具清单以官方文档为准。

ZS (Zobr Script) 需要什么运行环境?

属于远程端点,不需要在本地装运行时。

ZS (Zobr Script) 是本地还是远程?

它是远程端点,连服务地址即可。

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。