Skip to main content
Glama
moltline-mcp

moltline-mcp

moltline-mcp

一个轻量、零依赖的 stdio 桥接器,用于连接 Moltline Studio 的 14 台托管 MCP 服务器。

大多数现代 MCP 客户端都可以直接通过 Streamable HTTP 连接到该服务器群——无需安装(见下文直接连接)。此桥接器专为仅支持 stdio 传输的客户端而存在:它在你的客户端与托管服务器之间原样代理换行分隔的 JSON-RPC,不收集任何遥测数据,除 Python 3.9+ 标准库外无任何依赖。

  • 免费层:无需注册、无需账户、无需凭证——立即连接并调用工具。

  • 付费工具需使用 Moltline 许可证解锁,且仅作为工具参数传递(绝不会出现在 URL 或请求头中)。参见 auth.md。

  • 服务器群已通过独立审计:直接端点上获得 MCPize Verified A 认证。

服务器群

服务器

工具

功能

catalog

10

搜索和浏览 Moltline 目录:138 个技能包和全部 14 台服务器。

codereview

7

代码审查辅助工具:差异检查清单、代码异味检查、审查摘要。

timeops

5

时间操作:工作日、会议重叠、重复事件、截止日期、SLA 到期日。

data

7

数据转换:解析、转换、清理和格式化工具。

business

8

小企业运营:发票、跟进、日常流程。

creator

8

内容创作:钩子、大纲、字幕、再利用。

educator

7

教育:课程规划、测验和学习辅助。

govern

7

治理检查:策略、合规和审查门禁。

humanizer

5

文本人性化:语气、清晰度、自然重写。

merchant

6

商务:产品文案、列表、店面辅助。

outbound

8

外联:序列、个性化、回复草拟。

personal

9

个人效率:规划、日常安排、生活管理。

research

8

研究:引用、摘要、资料来源整理。

skillmd-lint

6

SKILL.md 检查:验证并改进 agent 技能文件。

机器可读的发现方式:api-catalog · 每台服务器的卡片位于 https://mcp.moltlinestudio.com/<server>/.well-known/mcp/server-card.json · 服务器健康状态。

Related MCP server: Developer Toolbox MCP

直接连接(首选)

如果你的 MCP 客户端支持 Streamable HTTP(Claude Desktop、Claude Code、Cursor 以及大多数当前客户端都支持),请直接指向托管端点——无需安装任何东西:

{
  "mcpServers": {
    "moltline-timeops": {
      "type": "http",
      "url": "https://mcp.moltlinestudio.com/timeops"
    }
  }
}

将 timeops 换成上方表格中的任意 slug。

stdio 桥接器(适用于仅支持 stdio 的客户端)

安装

pip install moltline-mcp        # from PyPI, or:
pipx install moltline-mcp       # isolated install

或者直接从仓库检出目录运行——它只是一个仅依赖标准库的单一文件:

python3 moltline_mcp.py timeops

客户端配置

{
  "mcpServers": {
    "moltline-timeops": {
      "command": "moltline-mcp",
      "args": ["timeops"]
    }
  }
}

命令行

moltline-mcp [server] [--timeout SECONDS] [--list] [--version]
  • server — 14 个 slug 之一(默认为 catalog);传入其他值会快速失败并列出有效列表。

  • --timeout — 每个请求的超时时间(秒,默认 300,或环境变量 MOLTLINE_TIMEOUT)。

  • --list — 打印服务器 slug 并退出。

  • 环境变量 MOLTLINE_BASE_URL — 覆盖服务器群的基础 URL(用于测试)。

  • 环境变量 MOLTLINE_DEBUG=1 — 在 stderr 上输出诊断日志(stdout 保持协议纯净)。

Docker

该桥接器也可以容器化运行(stdio 输入,需要可访问服务器群的网络出口):

docker build -t moltline-mcp .
docker run -i --rm moltline-mcp timeops   # any of the 14 slugs; default: catalog

将你的 MCP 客户端的 command 指向 docker,args 设为 ["run", "-i", "--rm", "moltline-mcp", "timeops"]。

工作原理

每个服务器连接对应一个进程。从 stdin 读取的每条 JSON-RPC 消息都会 POST 到 https://mcp.moltlinestudio.com/<server>;JSON 和 SSE 帧格式的响应会以换行分隔的 JSON 形式中继回 stdout。该桥接器会跟踪服务器分配的 Mcp-Session-Id,并回显协商好的 MCP-Protocol-Version,遵循 Streamable HTTP 传输规范。它绝不会检查、存储或上报你的流量。

访问与许可

  • 免费层 — 匿名使用。无需注册或凭证;所有免费工具立即可用。

  • 高级版 — 通过 moltlinestudio.com 购买(人工介入)的 Moltline 许可证解锁。当某个高级工具要求时,许可证会作为工具参数传入——绝不会作为 bearer 请求头,也绝不会出现在 URL 中。详情:auth.md。

链接

许可证

MIT © 2026 Moltline Studio

Available Tools

10 tools
get_free_skillGet Free SkillA
Read-onlyIdempotent
Inspect

Load a product's free gateway skill with its complete instructions. FREE.

Typical input {"slug": "inbox-zero-assistant"} returns {"slug": ..., "skill": "", "instructions": ""}.

Returns exactly one skill - the product's free gateway skill - chosen automatically from the slug, with no plan required. Use when the caller wants usable instructions immediately. Not for the product's other skills: those are named and need get_full_skill with a skill_name, which requires a paid plan. Errors: on invalid, missing, or malformed input this tool never raises a protocol error — it returns {"error": ""} (for example {"error": "unknown slug ''"}). Every call is read-only and idempotent, so after correcting the input it is always safe to retry.

Inputs: slug (required). Returns: object

get_full_kitGet Full KitA
Read-onlyIdempotent
Inspect

Load a themed kit and every member product in full. PREMIUM (paid plan).

Typical input {"slug": "founder-kit"} returns {"slug": ..., "name": ..., "products": [{"slug": ..., "name": ..., "persona": ..., "skills": [...]}, ...]}.

Returns every member product of one bundle in full, so the payload is large. Use only after list_kits has confirmed the kit slug. Not for a single product (get_full_product). Errors: on invalid, missing, or malformed input this tool never raises a protocol error — it returns {"error": ""} (for example {"error": "unknown kit ''"}). Every call is read-only and idempotent, so after correcting the input it is always safe to retry.

Inputs: slug (required). Returns: object

get_full_personaGet Full PersonaA
Read-onlyIdempotent
Inspect

Load a product's complete persona definition. PREMIUM (paid plan).

Typical input {"slug": "inbox-zero-assistant"} returns {"slug": ..., "persona": ""}.

Returns the persona text alone, with no skill bodies. Use when the caller needs the product's voice and operating rules only. Not when skills are also wanted - get_full_product returns persona and every skill in one call. Errors: on invalid, missing, or malformed input this tool never raises a protocol error — it returns {"error": ""} (for example {"error": "unknown slug ''"}). Every call is read-only and idempotent, so after correcting the input it is always safe to retry.

Inputs: slug (required). Returns: object

get_full_productGet Full ProductA
Read-onlyIdempotent
Inspect

Load one product in full: persona plus every skill's instructions. PREMIUM (paid plan).

Typical input {"slug": "inbox-zero-assistant"} returns {"slug": ..., "name": ..., "persona": ..., "skills": [{"name": ..., "instructions": ...}], "free_skill": {...}}.

Returns persona plus every skill for one product. Use when the caller wants the whole product. Not for a single skill (get_full_skill) and not for a bundle of products (get_full_kit). Errors: on invalid, missing, or malformed input this tool never raises a protocol error — it returns {"error": ""} (for example {"error": "unknown slug ''"}). Every call is read-only and idempotent, so after correcting the input it is always safe to retry.

Inputs: slug (required). Returns: object

get_full_skillGet Full SkillA
Read-onlyIdempotent
Inspect

Load one paid skill's complete instructions from a product. PREMIUM (paid plan).

Typical input {"slug": "inbox-zero-assistant", "skill_name": "Deep Triage"} returns {"slug": ..., "skill": ..., "instructions": ""}.

Returns one named skill, selected by skill_name. Use after preview_product has shown the skill list and the caller wants one specific paid skill. Not for the free gateway skill, which get_free_skill returns with no plan, and not for every skill at once (get_full_product). Errors: on invalid, missing, or malformed input this tool never raises a protocol error — it returns {"error": ""} (for example {"error": "unknown slug ''"}). Every call is read-only and idempotent, so after correcting the input it is always safe to retry.

Inputs: slug (required), skill_name (required). Returns: object

list_kitsList KitsA
Read-onlyIdempotent
Inspect

List the 12 themed kits with pricing and member products. FREE.

Takes no arguments. Returns a list of kit objects, each {"slug": ..., "name": ..., "price_usd": N, "tagline": ..., "members": ["product-slug", ...]}. Use a kit's slug with get_full_kit (premium).

Use when the caller asks about bundles or bundle pricing. Not for individual products (search_catalog) and not for a kit's full contents (get_full_kit). Errors: on invalid, missing, or malformed input this tool never raises a protocol error — it returns {"error": ""}. Every call is read-only and idempotent, so after correcting the input it is always safe to retry.

Inputs: no named parameters. Returns: result

preview_productPreview ProductA
Read-onlyIdempotent
Inspect

Preview one product: metadata, persona teaser, and paid-skill teasers. FREE.

Typical input {"slug": "inbox-zero-assistant"} returns {"slug": ..., "name": ..., "tagline": ..., "persona_preview": ..., "skills": [{"name": ..., "preview": ...}], "free_skill": ..., "note": ...}.

Returns teasers only, never full text. Use to judge a product before committing. Not for the complete persona or skill bodies (get_full_persona, get_full_product), and not when the caller wants instructions they can act on now (get_free_skill). Errors: on invalid, missing, or malformed input this tool never raises a protocol error — it returns {"error": ""} (for example {"error": "unknown slug ''"}). Every call is read-only and idempotent, so after correcting the input it is always safe to retry.

Inputs: slug (required). Returns: object

recommend_productsRecommend ProductsA
Read-onlyIdempotent
Inspect

Recommend catalog products for a need described in plain language. FREE.

Typical input {"need": "help answering customer support emails"} returns {"need": ..., "recommendations": [{"slug": ..., "name": ..., "why": ..., "area": ..., "try_free": ""}], "next": "..."}.

Use when the caller describes a problem instead of naming a product; ranking is by fit to the described need. Not for exact keyword or slug lookups (search_catalog). Errors: on invalid, missing, or malformed input this tool never raises a protocol error — it returns {"error": ""}. Every call is read-only and idempotent, so after correcting the input it is always safe to retry.

Inputs: need (required), limit. Returns: object

search_catalogSearch CatalogA
Read-onlyIdempotent
Inspect

Search all 138 catalog products by keyword and/or focus area. FREE.

Typical input {"query": "email inbox", "limit": 5} returns a ranked list of product objects [{"slug": ..., "name": ..., "area": ..., "segment": ..., "tagline": ...}]. An empty query with an area set browses that area.

Use when the caller names a keyword, product, or focus area to look up. Not for bundles (list_kits) and not for plain-language problem statements, which recommend_products ranks by fit rather than keyword match. Errors: on invalid, missing, or malformed input this tool never raises a protocol error — it returns {"error": ""}. Every call is read-only and idempotent, so after correcting the input it is always safe to retry.

Inputs: area, limit, query. Returns: result

upgrade_infoUpgrade InfoA
Read-onlyIdempotent
Inspect

Explain how to unlock full personas, paid skills, and kits. FREE.

Takes no arguments. Returns {"message": ..., "how": ..., "free_tier": ...} describing the upgrade path and what stays free.

Use when a premium tool has been refused or the caller asks what a plan covers. Not for per-bundle or per-product pricing (list_kits, preview_product). Errors: on invalid, missing, or malformed input this tool never raises a protocol error — it returns {"error": ""}. Every call is read-only and idempotent, so after correcting the input it is always safe to retry.

Inputs: no named parameters. Returns: object

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A4.7/5.0

    Scored across 10 tools

    Disambiguation5/5

    Each tool targets a distinct access level or content type: keyword search vs. plain-language recommendation, product preview vs. free skill instructions, and individual premium content vs. full product/kit bundles. The descriptions explicitly cross-reference related tools with 'not for' guidance, eliminating ambiguity.

    Naming Consistency5/5

    All tool names follow a consistent imperative verb_noun snake_case pattern. The get_full_* prefix clearly groups premium full-content loaders, while search_catalog, preview_product, list_kits, and recommend_products use predictable action-object names.

    Tool Count5/5

    Ten tools is well-scoped for a catalog and content-access server: it covers discovery, preview, free access, premium access, bundles, and upgrade information without redundant functions. Every tool earns its place in the workflow.

    Completeness5/5

    The tool surface covers the full read-only lifecycle: discover products and kits, preview them, obtain free content, unlock premium personas/skills/products/kits, and learn about upgrading. No obvious dead ends exist for an agent navigating the catalog.

    Maintenance

    ActivityActive
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • F
      license
      A
      quality
      D
      maintenance
      Universal MCP proxy server that discovers, searches, and executes tools across all configured MCP servers from a single entry point.
      7
      -
    • A
      license
      Not graded
      quality
      D
      maintenance
      MCP stdio server that exposes 95 headless it-tools utilities (crypto, encoding, converters, generators, text, math, and more) through three routing tools (categories, list, execute), with flat JSON schemas, worked examples, and deterministic seeded execution designed for small router models.
      GPL 3.0
    • A
      license
      A
      quality
      C
      maintenance
      Remote MCP server for 2ools—build, version, review, and export websites, web apps, and games from the AI chat you already use. This repository includes a credential-free stdio proxy and Dockerfile that forward introspection to the verified remote endpoint without mocking tools.
      43
      1
      MIT