原型 · 预览版:收录官方注册中心里的全部服务器,每 30 分钟同步一次。使用 Google 登录即可撰写评价。原型 · 每 30 分钟更新
PopNx MCP为使用 AI 的人准备的 MCP 服务器 · 用大白话讲清楚 登录

Senrelay (ContextCore)

作者:qingsongcui版本 1.0.0-beta.2i★ 101i在你的电脑上运行官方网站 ↗
注册名称io.github.qingsongcui/contextcore

安装方法

能做什么

Local macOS multi-agent session relay (/contextcore), source-linked memory, and 15-host MCP sync.

作者提供的原文

  • 连接方式 在你的电脑上运行
  • 账号或密钥 无需密钥
  • 分类 搜索与 AI 记忆

可搭配使用

教 AI 做这类工作的 Skill,可与本项一起使用

timesfm

TimesFM (Time Series Foundation Model) is a pretrained time-series foundation model developed by Google Research for time-series forecasting.

作者:google-research★ 35,6381 个 skill

Skill · 操作手册

Shadowbroker

Open-source intelligence for the global theater. Track everything from the corporate/private jets of the wealthy, and spy satellites, to seismic events in one unified interface. Hook an AI agent up to have it parse through data and find previously unseen correlations. The knowledge is available to…

作者:BigBodyCobain★ 11,6051 个 skill

Skill · 操作手册

google-maps-scraper

scrape data from Google Maps. Extracts data such as the name, address, phone number, website URL, rating, reviews number, latitude and longitude, reviews,email and more for each place

作者:gosom★ 8,2361 个 skill

Skill · 操作手册

为什么排在这里

列表按使用分(满分 100)排序,由以下部分组成

热度24/80GitHub 星标或每周下载量:较大的计 60,较小的计 20
新鲜度12/1230 天内有发布或代码更新得满分
仍在响应0/8上次检查时云端端点有响应
使用分36/100

质量: 基础检查通过 3/3 项(仅展示,不用于排序) · 上升势头: 暂无数据 (只用于“上升中”标签)

安装

选择你使用的 AI 应用,然后复制设置。

通过 3/3 项检查 · 在你的电脑上运行

第一步:你用哪个 AI?

选择你用的应用,步骤会显示在下方。

可连接 Claude,但需要先准备

不需要密钥,不用安装程序 · 仅限电脑上的 Claude 应用(Windows 或 Mac),网页和手机不可用

  1. 下载开发者的安装文件

    下载作者的 .mcpb 文件

    .mcpb 文件直接来自开发者,我们没有修改

  2. 双击文件,然后在电脑版 Claude 应用中点击 Install

  3. 试一试

    用 Senrelay (ContextCore) 告诉我你能帮我做什么,然后做一件给我看

    ✓ 如果 Claude 说正在使用 Senrelay (ContextCore),或回答中出现 Senrelay (ContextCore) 的工具名称,就表示连接成功

菜单名称已于 2026年11月11日 对照 Anthropic 帮助页面核实 · 你的界面可能因版本略有不同

ChatGPT 暂时无法连接 Senrelay (ContextCore)

Senrelay (ContextCore) 需要安装在你的电脑上,而 ChatGPT 只能连接在网上运行的服务器

你可以改用这些方式

A · 使用能连接 Senrelay (ContextCore) 的应用

  • 不需要密钥,不用安装程序 · 仅限电脑上的 Claude 应用(Windows 或 Mac),网页和手机不可用

B · 搜索与 AI 记忆 类中能连接 ChatGPT 的其他服务器

从同类中使用较多的里挑选,仅限用地址即可连接、无需密钥的

Claude Code 暂时无法连接 Senrelay (ContextCore)

开发者只提供了电脑版 Claude 应用的安装文件

你可以改用这些方式

A · 使用能连接 Senrelay (ContextCore) 的应用

  • 不需要密钥,不用安装程序 · 仅限电脑上的 Claude 应用(Windows 或 Mac),网页和手机不可用

Cursor 暂时无法连接 Senrelay (ContextCore)

开发者只提供了电脑版 Claude 应用的安装文件

你可以改用这些方式

A · 使用能连接 Senrelay (ContextCore) 的应用

  • 不需要密钥,不用安装程序 · 仅限电脑上的 Claude 应用(Windows 或 Mac),网页和手机不可用

VS Code 暂时无法连接 Senrelay (ContextCore)

开发者只提供了电脑版 Claude 应用的安装文件

你可以改用这些方式

A · 使用能连接 Senrelay (ContextCore) 的应用

  • 不需要密钥,不用安装程序 · 仅限电脑上的 Claude 应用(Windows 或 Mac),网页和手机不可用

其他支持 MCP 的应用(如 Windsurf、Zed、Gemini CLI)添加方式各不相同,请在应用列表中查看

查看所有支持 MCP 的应用 →

JSON 设置在下方“开发者专用”中

卡住了?问问正在用 Senrelay (ContextCore) 的人💬 讨论 →

一览

每周下载量i
不在 npm/PyPI 上
连接方式
在你的电脑上运行
最新版本i
1.0.0-beta.2
发布到注册中心i
2026年11月16日
代码最后更新i
2026年11月17日
作者
qingsongcui
软件包
mcpb: …/senrelay-contextcore-mcp.mcpb
注册状态
活跃

哪些应用可以使用它

依据这个服务器的连接方式和各应用自己的文档,检查于 2026年11月10日。

在你的电脑上运行,适用于

ClaudeGooseLM StudioMsty StudioCherry StudioVisual StudioWindsurf (Devin Desktop)ZedKiroClineContinueJetBrains AI AssistantCodex CLIGemini CLIOpenCodenodecodeWarpLibreChatRaycast

全部应用及其优缺点 →

它能做什么

它在你的电脑上运行;安装后,工具列表会显示在你的 AI 应用中。

基础检查i

我们检查的是任何人都能看到的信息;我们没有阅读代码。不适用的检查项不计入总数。 · 检查于 2026年11月20日

  • ✓ 通过

    作者与仓库一致

    注册名称已通过 GitHub 账户 qingsongcui 验证,该账户拥有此仓库

  • ✓ 通过

    仍在维护

    代码最后更新于3天前

  • ✓ 通过

    有许可证

    使用 MIT

  • – 不适用

    端点有响应

    它在你的电脑上运行,没有互联网端点

  • – 不适用

    使用 OAuth 登录

    在你的电脑上运行,改用本地设置

  • … 尚未检查

    工具描述中没有隐藏指令

    它在你的电脑上运行;我们只能读取互联网端点的工具列表

已公开的漏洞(OSV.dev)

未检查:只能检查标明版本的 npm 和 PyPI 包

我们检查什么 → · JSON

作者:申请重新检查或报告信息错误
给作者:在 README 中加徽章

如果你是作者,可把这段代码贴到 README。徽章会链接回本页。

[![Featured on PopNx MCP](https://mcp.popnx.com/badge/qingsongcui-contextcore.svg)](https://mcp.popnx.com/en/servers/qingsongcui-contextcore)

讨论

提问、分享技巧或报告无法使用。按“有帮助”数量排序。

还没有帖子,欢迎第一个提问或分享。

此处内容由用户撰写,不代表 PopNx 团队。

登录后发帖

用户评价

还没有评价

登录后写评价

与“搜索与 AI 记忆”中的其他服务器比较i

  • 星标数多于此分类中其他 6470 个服务器的 97%
  • 发布到注册中心的时间比此分类中其他 6470 个服务器的 90% 更新
  • 基础检查结果等于或优于此分类中其他 6470 个服务器的 99%

与注册中心里这个分类中所有活跃的服务器比较。只有当发布者拥有该仓库时,星标数才计入。

常见问题

Senrelay (ContextCore) 安全吗?

它在 3 项适用的基础检查中通过了 3 项。我们没有阅读代码。在添加密钥或令牌之前,请先看看这个服务器要求哪些权限,并使用只具备所需权限的密钥。

它需要哪些密钥或代码?

注册中心没有列出必需的密钥,不过有些服务器会在首次使用时要求你登录。

它在我的电脑上运行还是在云端?

它在你的电脑上运行。你的 AI 应用会在需要时启动它,数据不会经过作者的服务器(除非它自己调用在线服务)。

它还在维护吗?

GitHub 仓库最后更新于3天前,最新版本(1.0.0-beta.2)于4天前进入注册中心。

哪些应用可以使用它?

支持 MCP 的应用,例如 Claude Desktop、Claude Code、Cursor 和 VS Code。你的电脑上还需要有 MCPB。

有什么可以替代它?

同一分类中有:OpenSEO, Exa, Microsoft Learn MCP, Docs, COTAL actions (cotal.ai)

功能相近的其他选择

同一分类、其他作者、命令已通过检查。官方的排在前面,再按星标排序。

如何看卡片:↓ 每周下载量i★ GitHub 星标i三大支柱:评价 · 检查 · 使用情况i更新 = 最新版本发布到注册中心的时间i

OpenSEO

Keyword research, site audits, rank tracking and AI visibility for your AI agent.

作者:every-app广泛使用★ 2.8万6天前更新

在云端运行✓ everyapp.com

Exa

Official Exa MCP for web search, content fetching, and multi-step research.

作者:exa-labs广泛使用★ 5245今天更新

在云端运行✓ 服务方 · exa.aiPopNx 团队已实际试用

Microsoft Learn MCP

Official Microsoft Learn MCP Server – real-time, trusted docs & code samples for AI and LLMs.

作者:MicrosoftDocs广泛使用★ 200012个月前更新

在云端运行✓ 服务方 · microsoft.comPopNx 团队已实际试用

Docs

Search and read Empryo's documentation. Read-only, no auth, no local access.

作者:proxysoul正在增长★ 16282个月前更新

在云端运行✓ empryo.com
与相似项目对比
本项
Senrelay (ContextCore)
OpenSEOExaMicrosoft Learn MCPDocsCOTAL actions (cotal.ai)
运行位置需要安装在电脑上在云端运行,无需安装在云端运行,无需安装在云端运行,无需安装在云端运行,无需安装在云端运行,无需安装
需要密钥否否否否否否
可在 Claude 中按 + 添加否是是是否否
基础检查3/35/52/44/44/44/4
许可证MITMITMITCC-BY-4.0NOASSERTIONApache-2.0
价格登记中未列出费用登记中未列出费用登记中未列出费用登记中未列出费用登记中未列出费用登记中未列出费用

作者的 README

打开 README

按原文从作者的仓库复制。PopNx MCP 没有审查或背书其内容。HTML、图片和脚本已被移除。链接会离开本站。

Senrelay · 续境 (ContextCore)

A native macOS app, browser workbench, and local background service that lets multiple AI coding assistants accumulate source-linked project memories, relay conversations across agents in a single command, and manage providers, MCP tools, Skills, and instructions in one place.

English · 中文 · Official Website · Setup Guide · 15-Host Config Paths · Cross-Agent Relay Workflow · 5-Way Comparison · Public Beta Release (v1.0.0-beta.3)

100% Free & Open Source (`$0`, [MIT License](LICENSE)) · No Account Required · Apple Silicon `macOS 14.0+` (`arm64`) Local-First

Disambiguation: Senrelay(续境) (qingsongcui/ContextCore) is a local Apple Silicon macOS developer workbench. It is unrelated to third-party services at context-core.dev, public PyPI pip install contextcore, or hardware automotive relays. Install via brew install --cask qingsongcui/tap/senrelay.

42-Second Launch Film ("Turn 85")

https://github.com/user-attachments/assets/836bb4e6-1238-4c9f-9120-e2781e5de06e

Watch on senrelay.com · Download 1080p MP4 · English Captions (.srt)

Product and scope

The active product lives in app/. The public specification summarizes confirmed product requirements and boundaries.

  • Native macOS App + Browser Workbench + Local Daemon: Built with a native AppKit/WKWebView macOS shell, a React/Vite workbench, and an independent FastAPI + SQLite loopback service. Closing the window or browser tab does not stop background capture.
  • Six Core Context Hosts: Codex (Desktop and CLI), Oh My Pi (OMP), Cursor, Antigravity, Claude Code, and OpenCode. Capabilities are tracked independently per host and surface (Codex Desktop ≠ Codex CLI, Cursor IDE ≠ Cursor CLI, Antigravity Desktop ≠ agy, OMP ≠ Pi / OpenCode); see docs/support-matrix.md. Writing a configuration file does not prove a running host process has reloaded it, and local endpoint checks are distinct from live model inference.
  • In-Agent Conversation Relay: Open any new Agent and type /contextcore (or say "接着做" / "接力" / "continue" / "relay") to list recent cross-host conversation candidates as short, recognizable briefs (title, brief_summary, source Agent, project or explicit unassigned label, native session ID, directory, and Git branch—keeping sibling Git worktrees and distinct same-title sessions separate without calling a background model). Replying with only a candidate number (or native/internal session ID) loads bounded context and transcript_paging (must_not_execute=true) without generating a summary card; when turns are omitted, the receiving Agent sequentially pages read_conversation_messages (offset=0, limit=30, or GET /api/conversations/ /messages), compacts the entire transcript in its own context, reports where the previous session left off, and waits for your next instruction. Attaching a concrete task alongside your selection authorizes continuing directly (unless a matching working_tasks entry is marked discussion_only). Lifecycle hooks report events silently and never inject unrequested context into chat.
  • Dual-Tier Companion Auto-Memory & Version Governance: Combines durable, source-quoted project/global memories (contents: six classes with 📌 core-rule pinning, AGENTS.md handbook preview, explicit supersession, outdated archival, Pending Conflicts, and honest saved/provided/cited receipts, leaving a brief 💡 notice) with short-term working_tasks state (active task goal, completed steps, failed attempts, one-off constraints, and fail-closed discussion_only gates via bootstrap_working_memory, upsert_working_task, and source-backed promote_task_lesson). Supports version rollback and independent permanent deletion of chats versus memories.
  • Unified Multi-Host Management: Switch target hosts from the permanent top bar, run One-Click Connect, fill read-only provider presets and test endpoint latency, bind models and Keychain secrets, and manage MCP servers, Skills, system prompts, project bundles, per-host routing modes, and local configuration import/export. Changes save automatic rollback snapshots and open a Diff confirmation dialog whenever external manual file edits conflict.
  • Instant Lexical Search & Optional Local Semantics: Search across all projects or the current project from the workbench header with local FTS5 indexing. Optional local vector semantic search and source-backed relationship graphs live under Settings → Advanced (disabled by default; searching never triggers automatic downloads or dependency installation).
  • Backups & Scope Boundaries: Whole-database SQLite online snapshots (0600 permissions under /backups/) are supported from Settings and contextcore backup. Automated cloud sync, Skill generation foundries, and unsolicited proactive insights are out of scope.

Desktop app, pricing, and when NOT to use

The native macOS bundle ships a self-contained Python runtime (1.0.0b3), backend service, and frontend workbench; see desktop build and verification. Current public Beta candidates (v1.0.0-beta.3) target Apple Silicon (`arm64`) on macOS 14.0+ and use ad-hoc signing (Senrelay-macOS.zip contains Senrelay.app only).

  • Pricing & License: Free (`$0`, [MIT License](LICENSE)), with no paid tiers, cloud account, or telemetry. You supply your own API keys stored locally in macOS Keychain.
  • When NOT to use Senrelay:
  1. You use Windows, Linux, or an Intel (`x86_64`) Mac — current builds support macOS 14.0+ Apple Silicon (`arm64`) only.
  2. You need multi-device cloud sync, hosted team memory, or remote web access — Senrelay runs strictly on local loopback (127.0.0.1:8420, dev 18420) on a single Mac.
  3. You expect cross-host session capture or `/contextcore` relay for the 9 extended config hosts (Claude Desktop, Gemini CLI, Grok Build, Kimi Code, MiniMax Code, Pi, Hermes, OpenClaw, agy) — those 9 hosts only support previewed configuration management.
  4. You require a zero-prompt Apple-notarized installer — Public Beta builds are ad-hoc signed, so first launch requires running xattr -cr /Applications/Senrelay.app once.
Quick install via Homebrew Tap (macOS 14.0+ arm64)
brew install --cask qingsongcui/tap/senrelay

xattr -cr /Applications/Senrelay.app

Manual ZIP install
  1. Download Senrelay-macOS.zip from v1.0.0-beta.3, extract it, and move Senrelay.app to /Applications;
  2. Run xattr -cr /Applications/Senrelay.app in Terminal (or allow it under System Settings → Privacy & Security → Open Anyway; source checkouts also include app/macos/install-macos.sh).

Package naming note: The contextcore CLI ships inside Senrelay.app and this source repository (qingsongcui/ContextCore). Do not run pip install contextcore — the contextcore package on PyPI is an unrelated third-party project.

Developer ID signing, Apple notarization, clean-Mac physical Gatekeeper acceptance, and live upgrade acceptance remain open boundaries documented in release readiness.

Daily-use workflow

Navigation and layout
  • Primary Left Navigation (3 fixed entries + conditional conflict badge):
  • Projects (projects): Top global search bar across projects, plus four focused project tabs: Overview, Chats, Memory (including tasks/todos and 📌 pinned rules), and Materials.
  • Agent Management (agents): Permanent top host switcher bar for One-Click Connect, providers & models, MCP tools, Skills, system prompts, and routing modes.
  • Usage & Performance (usage): Recorded requests, token consumption, latency, and cost estimates, with unobserved metrics marked unknown rather than 0.
  • Needs Decision (conflicts, shown on demand): Appears in primary navigation with a count badge only when memory conflicts are pending.
  • Compact Sidebar Footer: Live local service indicator, Settings (settings, containing appearance, language, LaunchAgent autostart, SQLite online backup, optional semantic search settings, and the embedded Change Log viewer), bilingual toggle (中 / EN), and theme switcher.
1. Create and organize projects

Projects organize work topics. Create a project associated with one or more local repository directories, or with no directory at all (directory-free topic projects). Rename, merge, split, or archive projects (archived projects remain searchable), or reconstruct projects from historical chat sessions.

2. Accumulate memories, materials, and sources
  • Companion Auto-Memory + Dual-Tier Working Memory: Companion MCP tools and Skills capture source-quoted durable memories (contents with a brief 💡 receipt) and short-term active task state (working_tasks with completed steps, failed attempts, one-off restrictions, and discussion_only edit guards via bootstrap_working_memory, upsert_working_task, and source-backed promote_task_lesson), while the workbench supports manual notes and document imports (MD, TXT, JSON, PDF, DOCX, DOC).
  • Six Categories & Tiered Governance: Organize memories across Preferences, Background, Constraints, Tasks, Lessons, and References, pin 📌 core rules to the protected prompt tier, archive obsolete rules as outdated, consolidate duplicates, and preview AGENTS.md handbooks.
  • Independent Permanent Deletion: Trace any memory back to its exact dialogue turns or document source and roll back retained versions. Deleting a conversation never deletes extracted memories, and deleting a memory never deletes original conversations.
3. Cross-Agent conversation relay

When switching tools (for example after hitting quota or context limits), continue directly inside your receiving Agent without filling out forms in the web UI:

  1. Open your target Agent (Claude Code, Codex, Cursor, Antigravity, OMP, or OpenCode) and type /contextcore (or say "continue" / "relay" / "接着做" / "接力").
  2. Senrelay syncs authorized histories and lists recent cross-host conversation candidates as short, recognizable briefs (title, brief_summary, source Agent, project or unassigned marker, native session ID, directory, and Git branch/head—keeping distinct same-title sessions and sibling Git worktrees separate without calling a background model).
  3. Choose how to proceed:
  • Reply with just a number (or provide an exact native/internal session ID): Loads bounded context and transcript_paging (must_not_execute=true) without a handoff card; if any turns were omitted, the receiving Agent sequentially calls read_conversation_messages (offset=0, limit=30, or GET /api/conversations/ /messages), compacts the full transcript in context, summarizes progress, constraints, and next steps, and waits before modifying code.
  • Reply with a number plus a concrete task (e.g. 1, finish the remaining edge-case unit tests): Loads the relay context and continues working right away (unless a matched working_tasks entry is discussion_only).
4. Agent Management
  • Top Host Switcher & One-Click Connect: Select any core or extended host from the top bar; click One-Click Connect to configure authorized his

只显示了开头部分;其余内容请在仓库中阅读