PostHog MCP Server
Official PostHog MCP Server for product analytics, feature flags, experiments, and more.
Official remote MCP server for Archivist AI TTRPG campaign memory: characters, sessions, and more.
选择你使用的 AI 应用,然后复制设置。
通过 5/5 项检查 · 你的提问会经过开发者的服务器(mcp.myarchivist.ai) · ✓ 命令已检查 2026年11月13日
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 · 约 2 分钟
不需要密钥,不用安装程序 · 在 claude.ai 或桌面应用设置一次,即可在聊天中使用 · 免费账户可添加 1 个 · Team/Enterprise 方案由所有者(Owner)添加
CustomizeConnectors
把这里的内容复制到 Claude 中同名的输入框,然后点击 Continue
Archivist AIhttps://mcp.myarchivist.ai/mcp在 Claude 检测到的登录设置页点击 Continue · Authentication 按作者说明选择(Sign in now、Sign in when needed 或 No sign in),然后点击 Add
+ConnectorsArchivist AI
用 Archivist AI 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 Archivist AI,或回答中出现 Archivist AI 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
能否连接 ChatGPT 取决于方案
完整 MCP:网页版 ChatGPT Business、Enterprise 或 Edu · Pro:以读取/获取权限连接,修改数据的工具可能用不了 · Plus:官方文档尚未确认,如果在插件页看到添加自定义 MCP 的选项可以试试 · 仅限网页
Plugins+Add custom MCP server
输入名称,在 Connection 下粘贴地址,勾选风险提示,然后点击 Create as a plugin
Archivist AIhttps://mcp.myarchivist.ai/mcp开启新聊天,输入前先从插件列表中选择 Archivist AI
用 Archivist AI 告诉我你能帮我做什么,然后做一件给我看✓ 如果 ChatGPT 说正在使用 Archivist AI,或回答中出现 Archivist AI 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 OpenAI 帮助页面核实 · 你的界面可能因版本略有不同
可连接 Claude Code · 约 2 分钟
不需要密钥,不用安装程序
Mac:按 Command+空格,输入 Terminal · Windows:打开 PowerShell
claude mcp add --transport http --scope user archivist-ai https://mcp.myarchivist.ai/mcp应能看到 Archivist AI 在列表中并显示已连接
用 Archivist AI 告诉我你能帮我做什么,然后做一件给我看✓ 如果 Claude Code 说正在使用 Archivist AI,或回答中出现 Archivist AI 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
可连接 Cursor · 约 2 分钟
不需要密钥,不用安装程序
用 Archivist AI 告诉我你能帮我做什么,然后做一件给我看✓ 如果 Cursor 说正在使用 Archivist AI,或回答中出现 Archivist AI 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 Cursor 帮助页面核实 · 你的界面可能因版本略有不同
可连接 VS Code · 约 2 分钟
不需要密钥,不用安装程序
用 Archivist AI 告诉我你能帮我做什么,然后做一件给我看✓ 如果 VS Code 说正在使用 Archivist AI,或回答中出现 Archivist AI 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 VS Code 帮助页面核实 · 你的界面可能因版本略有不同
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
通过网页连接的应用使用的地址
https://mcp.myarchivist.ai/mcpJSON 设置在下方“开发者专用”中
Claude Code
claude mcp add --transport http --scope user archivist-ai https://mcp.myarchivist.ai/mcpCursor (~/.cursor/mcp.json)
{
"mcpServers": {
"archivist-ai": {
"url": "https://mcp.myarchivist.ai/mcp"
}
}
}VS Code (mcp.json)
{
"servers": {
"archivist-ai": {
"type": "http",
"url": "https://mcp.myarchivist.ai/mcp"
}
}
}这些设置是根据作者在注册中心的条目生成的。如果 README 的写法不同,请以 README 为准。
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。
通过互联网连接,适用于
ClaudeChatGPTGooseLM StudioMsty StudioCherry StudioCursorVS Code + GitHub CopilotVisual StudioWindsurf (Devin Desktop)ZedKiroClineContinueJetBrains AI AssistantClaude CodeCodex CLIGemini CLIOpenCodenodecodeWarpLibreChatOpen WebUIRaycast
服务器要求先登录,才会列出它的工具。
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14日
注册名称已通过 GitHub 账户 Astrotomic 验证,该账户拥有此仓库
代码最后更新于前天
使用 MIT
在 284 毫秒内响应(HTTP 401)
声明支持 OAuth 登录,你的 AI 应用可以带你去登录
尚未检查;我们会在检查端点时读取工具列表
提问、分享技巧或报告无法使用。按“有帮助”数量排序。
还没有评价
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。
它在 5 项适用的基础检查中通过了 5 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。
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。
它在作者的云端运行。通过互联网连接,无需安装,但你发送的内容会经过作者的服务器。
GitHub 仓库最后更新于前天,最新版本(3.0.1)于21天前进入注册中心。
支持 MCP 的应用,例如 Claude Desktop、Claude Code、Cursor 和 VS Code。它通过 URL 连接,因此也能用于接受远程 MCP 的应用,例如网页版 ChatGPT(Business 及以上为完整 MCP;Pro 为只读)。
同一分类中有:PostHog MCP Server, Openshorts, Google Ads + Meta Ads + SEO/GEO MCP
同一分类中其他作者的服务器,按星标数排序。
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
Official PostHog MCP Server for product analytics, feature flags, experiments, and more.
Turn long videos into viral vertical shorts and publish them to TikTok, Instagram and YouTube.
Google Ads, Meta Ads, Google Analytics (GA4) & Search Console MCP server by Ryze AI
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。
The official Model Context Protocol (MCP) server for Archivist AI -- a TTRPG campaign memory platform for game masters and players.
Registry metadata lives in server.json. Publishing to the official MCP Registry is automated on version tags via .github/workflows/publish-mcp.yml (git tag v3.0.1 && git push origin v3.0.1).
Connect AI assistants like Claude, ChatGPT, Cursor, Notion, and Windsurf directly to your campaign data: characters, sessions, locations, factions, items, quests, journals, key moments, hero awards, quotes, spotlights, and more.
MCP Server URL: https://mcp.myarchivist.ai/mcp
Discord tools live on a sibling host: https://discord.myarchivist.ai/mcp. That is a separate MCP resource (OAuth + your recording bot) and does not replace campaign tools here.
Claude Desktop
Claude Desktop requires the mcp-remote proxy (Node.js must be installed).
Add to your claude_desktop_config.json (~/Library/Application Support/Claude/claude_desktop_config.json on macOS, %APPDATA%\Claude\claude_desktop_config.json on Windows):
{
"mcpServers": { "archivist-ai": { "command": "npx", "args": [ "-y", "mcp-remote", "https://mcp.myarchivist.ai/mcp", "--header", "X-API-Key:${ARCHIVIST_API_KEY}" ], "env": { "ARCHIVIST_API_KEY": "YOUR_API_KEY" } } } }
Replace YOUR_API_KEY with your Archivist AI API key from app.myarchivist.ai. Restart Claude Desktop after saving.
API keys must be sent in the X-API-Key header. Do not put an API key in an Authorization: Bearer header; Bearer credentials are reserved for OAuth access tokens.
OpenCode
OAuth (recommended):
{
"$schema": "https://opencode.ai/config.json", "mcp": { "archivist-ai": { "type": "remote", "url": "https://mcp.myarchivist.ai/mcp" } } }
To use an API key instead, disable OAuth auto-detection and send the key in X-API-Key:
{
"$schema": "https://opencode.ai/config.json", "mcp": { "archivist-ai": { "type": "remote", "url": "https://mcp.myarchivist.ai/mcp", "oauth": false, "headers": { "X-API-Key": "{env:ARCHIVIST_API_KEY}" } } } }
</details>
Cursor
Add to .cursor/mcp.json in your project:
{
"mcpServers": { "archivist-ai": { "url": "https://mcp.myarchivist.ai/mcp" } } }
</details>
Windsurf
Add to your MCP configuration:
{
"mcpServers": { "archivist-ai": { "serverUrl": "https://mcp.myarchivist.ai/mcp" } } }
</details>
ChatGPT
Archivist AI is available as a ChatGPT plugin. Search for "Archivist AI" in the ChatGPT plugin store.
Read tools are non-destructive and idempotent. Write tools follow standard REST semantics — deletes are destructive and idempotent; PATCH is non-idempotent; PUT is idempotent. Every read tool that returns text-carrying descriptions (Character, Faction, Location, Item, Moment, Beat, Session, Journal) accepts an optional with_links parameter — see Wikilinks below for why you almost always want to pass with_links: true before editing.
Campaign delete, session delete, product-view-only endpoints (beat reorder/batch-edit, campaign settings, cast/member management), multipart recording uploads, and AI image generation are intentionally not exposed.
OAuth clients that connect via https://app.myarchivist.ai request scopes at authorization time. Every write tool (create/update/delete + image upload) additionally requires the agent_write scope on the caller's token.
The MCP mirrors the API's enforcement in tools/list: agent clients without agent_write see only the read tools, and receive a "tool not found" JSON-RPC error if they attempt to call a write tool anyway. API-key credentials and non-agent OAuth clients bypass this filter — the API is the authoritative gate for them and all tools remain visible.
Existing OAuth clients that connected before agent_write was advertised need to re-authorize to receive a token with the new scope.
| Tool | Description |
|---|---|
list_campaigns | List your campaigns. Returns a paginated list. |
get_campaign | Get a specific campaign by ID. |
get_campaign_stats | Get statistics for a campaign: character count, session count, and more. |
create_campaign | Create a new campaign. Subject to the account's subscription-tier campaign limit. |
update_campaign | Partially update campaign metadata (title, description, tones, public/mature flags). |
| Tool | Description |
|---|---|
list_sessions | List game sessions. Filter by session type or public-only. |
get_session | Get a session by ID. Optionally include related beats and moments. |
get_session_cast_analysis | Get cast analysis: talk-share breakdown and core session metrics. |
get_session_transcript | Get the cleaned transcript for a game session, including utterances, full text, and aggregate stats. |
get_session_handout | Get the generated session handout for a game session, including summary, outlines, spotlights, and notable moments. |
patch_session | Partial update (title, session_date, summary, notes, type, public, image). Explicit-link contract for wikilinks. |
| Tool | Description |
|---|---|
list_beats | List beats ordered by index. Beats represent story moments (major, minor, step). |
get_beat | Get a specific beat by ID. |
create_beat | Create a beat. Explicit-link contract for wikilinks. |
update_beat | Partially update a beat. |
delete_beat | Delete a beat (child beats have parent_id cleared). |
list_moments | List Key Moments (Moments) in a campaign or session. Filter by label, categories (typically key-moment), or kind. Includes image and presentation metadata. |
get_moment | Get a Key Moment by ID, including image URL, categories, kind, and metadata. |
create_moment | Create a Key Moment attached to a session. Set categories=["key-moment"] for a Key Moment card. Explicit-link contract for wikilinks. |
update_moment | Partially update a Key Moment, including image and merged presentation metadata. |
delete_moment | Delete a Key Moment. |
| Tool | Description |
|---|---|
list_hero_awards | List hero awards in a campaign or session. |
get_hero_award | Get a hero award by ID. |
create_hero_award | Create a hero award attached to a session. |
update_hero_award | Partially update a hero award. |
delete_hero_award | Delete a hero award. |
list_quotes | List memorable session quotes in a campaign or session. |
get_quote | Get a quote by ID. |
create_quote | Create a quote attached to a session (creates a recap pipeline if needed). |
update_quote | Partially update a quote. |
delete_quote | Delete a quote. |
list_spotlights | List recap spotlights (GEMS cards, not session-handout spotlights). |
get_spotlight | Get a recap spotlight by ID. |
create_spotlight | Create a recap spotlight attached to a session. |
update_spotlight | Partially update a recap spotlight. |
delete_spotlight | Delete a recap spotlight. |
| Tool | Description |
|---|---|
list_characters | List characters in a campaign. Filter by name, type (PC/NPC), or approval status. |
get_character | Get a character by ID including aliases, backstory, and speaker linkage. |
create_character | Create a character. Description/backstory wikilinks auto-resolve. |
update_character | Partially update a character. Read with with_links: true before editing description/backstory. |
delete_character | Delete a character. API unbrackets all inbound [[alias]] references automatically. |
list_factions | List factions. Factions represent guilds, organisations, or other groups. |
get_faction | Get a specific faction by ID. |
create_faction | Create a faction. Description wikilinks auto-resolve. |
update_faction | Partially update a faction. Read with with_links: true before editing. |
delete_faction | Delete a faction. |
list_locations | List locations. Locations can be nested (cities, taverns, dungeons, etc.). |
get_location | Get a specific location by ID. |
create_location | Create a location. Description wikilinks auto-resolve. |
update_location | Partially update a location. Read with with_links: true before editing. |
delete_location | Delete a location (child locations have parent_id cleared). |
list_items | List items. Items include weapons, armour, artefacts, and other notable objects. |
get_item | Get a specific item by ID. |
create_item | Create an item. Description wikilinks auto-resolve. |
update_item | Partially update an item. Read with with_links: true before editing. |
delete_item | Delete an item. |
| Tool | Descript