Vexa
Meeting bot and transcripts for Google Meet, Teams and Zoom. Live or after, speakers labelled.
作者による説明(英語の原文)
Slack MCP server: channels, messages, threads, reactions, users, files, and scheduled messages
この3つを1つのスコアにまとめることはしません。意見、測定、人気はそれぞれ別のものだからです。
このサーバーのやさしい解説はまだ書いていません。以下はレジストリから読み取った事実です。
使っているAIアプリを選んで、設定をコピーしてください。
SLACK_CONFIG_PATH, SLACK_TEAM_ID, SLACK_CLIENT_ID, SLACK_CLIENT_SECRET, SLACK_DISABLE_REFRESH, SLACK_REQUEST_TIMEOUT_MS, SLACK_MAX_RETRIES, MCP_WORKSPACE_PATH「秘密」と表示された値は、あなたのアカウントの鍵です。絶対に人に教えたり、チャットに貼り付けたりしないでください。
必要なもの
どのアプリを使っていますか?
上でアプリを選んでください。選んだアプリを覚えておくので、次からはボタンに「…にインストール」と表示されます。
Claude Desktop → Settings → Developer → Edit Config を開き、claude_desktop_config.json にこれを貼り付けます
{
"mcpServers": {
"slack": {
"command": "npx",
"args": [
"-y",
"@mindstone/mcp-server-slack"
],
"env": {
"SLACK_CONFIG_PATH": "your-value",
"SLACK_TEAM_ID": "your-value",
"SLACK_CLIENT_ID": "your-value",
"SLACK_CLIENT_SECRET": "your-value",
"SLACK_DISABLE_REFRESH": "your-value",
"SLACK_REQUEST_TIMEOUT_MS": "your-value",
"SLACK_MAX_RETRIES": "your-value",
"MCP_WORKSPACE_PATH": "your-value"
}
}
}
}ターミナルでこれを実行します
claude mcp add slack --env SLACK_CONFIG_PATH=your-value --env SLACK_TEAM_ID=your-value --env SLACK_CLIENT_ID=your-value --env SLACK_CLIENT_SECRET=your-value --env SLACK_DISABLE_REFRESH=your-value --env SLACK_REQUEST_TIMEOUT_MS=your-value --env SLACK_MAX_RETRIES=your-value --env MCP_WORKSPACE_PATH=your-value -- npx -y @mindstone/mcp-server-slack動かす前に、空欄の値を入力してください。
プロジェクトの .cursor/mcp.json、または ~/.cursor/mcp.json に貼り付けます
{
"mcpServers": {
"slack": {
"command": "npx",
"args": [
"-y",
"@mindstone/mcp-server-slack"
],
"env": {
"SLACK_CONFIG_PATH": "your-value",
"SLACK_TEAM_ID": "your-value",
"SLACK_CLIENT_ID": "your-value",
"SLACK_CLIENT_SECRET": "your-value",
"SLACK_DISABLE_REFRESH": "your-value",
"SLACK_REQUEST_TIMEOUT_MS": "your-value",
"SLACK_MAX_RETRIES": "your-value",
"MCP_WORKSPACE_PATH": "your-value"
}
}
}
}ブラウザがアプリを開いてよいか確認し、そのあとアプリが設定を表示して確認を求めます。キーの値は空欄のままなので、自分で入力してください。
プロジェクトの .vscode/mcp.json に貼り付けます
{
"servers": {
"slack": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@mindstone/mcp-server-slack"
],
"env": {
"SLACK_CONFIG_PATH": "your-value",
"SLACK_TEAM_ID": "your-value",
"SLACK_CLIENT_ID": "your-value",
"SLACK_CLIENT_SECRET": "your-value",
"SLACK_DISABLE_REFRESH": "your-value",
"SLACK_REQUEST_TIMEOUT_MS": "your-value",
"SLACK_MAX_RETRIES": "your-value",
"MCP_WORKSPACE_PATH": "your-value"
}
}
}
}ブラウザがアプリを開いてよいか確認し、そのあとアプリが設定を表示して確認を求めます。キーの値は空欄のままなので、自分で入力してください。
これはパソコンで動くサーバーですが、ChatGPTがつなげるのはインターネット上のサーバーだけです。ほかのアプリを選んでください。
選んだアプリは、この端末のCookieに保存されます。アカウントは不要です。
SLACK_CLIENT_ID envSLACK_DISABLE_REFRESH envSLACK_REQUEST_TIMEOUT_MS envSLACK_MAX_RETRIES envMCP_WORKSPACE_PATH envこの設定は、作者のレジストリ登録情報から作成しています。READMEと違う場合は、READMEに従ってください。
パソコンで動くサーバーです。インストールすると、ツール一覧がAIアプリに表示されます。
誰でも見られる情報をチェックしており、コードは読んでいません。当てはまらない項目は数に入れていません。 · 2026年11月6日にチェック
レジストリ名は、リポジトリを所有するGitHubアカウント mindstone で確認済みです
このリポジトリはまだGitHubから読み取っていません
このリポジトリはまだGitHubから読み取っていません
これはパソコンで動くため、インターネット上のエンドポイントはありません
パソコンで動き、代わりにローカルの設定を使います
パソコンで動くサーバーです。ツール一覧を読み取れるのは、インターネット上のエンドポイントがある場合だけです
レジストリでこのカテゴリにある有効なすべてのサーバーと比較しています。スターは、公開者がリポジトリの所有者である場合だけ数えます。
当てはまる基本チェック1項目のうち1項目に合格しました。コードは読んでいません。キーやトークンを追加する前に、サーバーがどんなアクセスを求めているかを確認し、必要な権限だけを持つキーを使ってください。
入力が必要なもの:SLACK_CONFIG_PATH, SLACK_TEAM_ID, SLACK_CLIENT_SECRET
あなたのパソコンで動きます。必要なときにAIアプリが起動し、データは作者のサーバーを通りません(サーバー自体がオンラインサービスを呼び出す場合を除きます)。
GitHubリポジトリの最終更新は–、最新バージョン(0.3.7)がレジストリに届いたのは今日です。
Claude Desktop、Claude Code、Cursor、VS CodeなどのMCP対応アプリで使えます。パソコンにNode.jsも必要です。
同じカテゴリには:Vexa, emailmd, MCP WhatsApp Cloud
同じカテゴリで、ほかの作者が作ったサーバー。スターの多い順。
カードの見方:★ GitHubスターi3つの柱:レビュー · チェック · 利用状況i更新=最新バージョンをレジストリに公開した日i
Meeting bot and transcripts for Google Meet, Teams and Zoom. Live or after, speakers labelled.
Render markdown into email-safe HTML, lint drafts for deliverability problems, and preview emails.
MCP server for WhatsApp Cloud API (Meta) — messages, media, and templates via Graph API
作者のリポジトリから書かれたとおりにコピーしたものです。PopNx MCPは内容を確認・推奨していません。HTML、画像、スクリプトは取り除いています。リンクはこのサイトの外へ移動します。
Slack workspace MCP server — channels, messages, threads, reactions, users, files, bookmarks, and scheduled messages via the Slack Web API.
*Multi-workspace Slack MCP. Host-driven OAuth, per-workspace credentials files on disk, and a security review on every release.*
SLACK_CLIENT_SECRET)STATUS.jsonWhen we started building this connector, Slack had not yet released an official MCP server — that came later (announced February 2026, generally available April 2026). The community Slack MCPs available at the time each got parts of the job right, but none of them combined fast user-name lookups for small and medium workspaces, the correct mention format for modern Slack (most still used the deprecated link_names=true), support for more than one Slack workspace from the same user account, and tokens that stay on the user's own machine. Slack's official server now exists and is a fine choice for many use cases. We continue to maintain this one because the host application handles the login flow, each workspace has its own credentials file on disk under the user's control, and the connector goes through our own security review before each release.
"Find the most recent message from Alice in #q3-planning and react with :eyes:."
Tools the host calls:
lookup_user_by_email — resolves Alice's email to her Slack user ID.search_slack_messages — searches #q3-planning for her most recent message, returning the channel + timestamp.add_slack_reaction — adds the eyes reaction to that message.Response (trimmed):
{
"match": { "channel": "C08X...", "ts": "1715953812.004200", "user": "U07Z...", "text": "Pushed the updated forecast to the doc, ready for review." }, "reaction": { "ok": true, "name": "eyes" } }
${SLACK_CONFIG_PATH}/workspaces/{teamId}.json. This server reads those files; it does not initiate OAuth itself.After clicking the button, your host will prompt you to fill: SLACK_CONFIG_PATH, SLACK_TEAM_ID, SLACK_CLIENT_SECRET, SLACK_REQUEST_TIMEOUT_MS, SLACK_MAX_RETRIES.
Manual config for Claude Desktop / Claude Code / Goose / Continue.dev (Slack)
{
"mcpServers": { "Slack": { "command": "npx", "args": [ "-y", "@mindstone/mcp-server-slack" ], "env": { "SLACK_CONFIG_PATH": "", "SLACK_TEAM_ID": "", "SLACK_CLIENT_SECRET": "", "SLACK_REQUEST_TIMEOUT_MS": "60000", "SLACK_MAX_RETRIES": "10" } } } }
cd <path-to-repo>/connectors/slack
npm install npm run build
npx -y @mindstone/mcp-server-slack
node dist/index.js
This server is designed to run alongside a host application that performs the Slack OAuth flow on its own. The host writes credentials to disk; this server reads them.
SLACK_CONFIG_PATH — Path to the Slack config directory (host-managed). Contains config.json (workspace metadata) and workspaces/{teamId}.json (per-workspace tokens, mode 0600).SLACK_TEAM_ID — Workspace team ID (per-workspace instance).SLACK_CLIENT_ID — OAuth Connected App client ID. Only needed to refresh a *rotating* token. Saved non-rotating tokens authorize the Slack API directly without it. When a refresh is required but this is absent, the server fails loud with REFRESH_NO_CLIENT_CREDENTIALS and directs the host to re-authenticate.SLACK_CLIENT_SECRET — OAuth Connected App client secret. Same conditions as SLACK_CLIENT_ID.SLACK_DISABLE_REFRESH — Set to 1 to disable token refresh on this surface. The server will fail-closed with a structured auth_required response on token expiry instead of attempting an oauth.v2.access refresh. Use this on the cloud surface so desktop remains the sole refresh authority and avoids racing for single-use refresh tokens.SLACK_REQUEST_TIMEOUT_MS — Override the default 60s upstream timeout. Must be a positive integer ≤ 300000 (5 minutes).MCP_WORKSPACE_PATH — Directory that upload_slack_file reads are constrained to. Paths outside it (including symlinks pointing outside) are refused. Defaults to the system temp dir when unset.The host calls the authenticate_slack_workspace tool. The OSS server returns a structured auth_required response of the form:
{
"status": "auth_required", "user_action": { "id": "slack.connect_workspace", "label": "Connect Slack", "instruction": "Click \"Connect Slack\" in the side panel to authorise the workspace." }, "agent_action": { "instruction": "Tell the user to click the Connect Slack button in the connector settings to authorise. Then call list_slack_workspaces to verify." }, "setupToolName": "authenticate_slack_workspace" }
The host's MCP service recognises this shape and dispatches to its registered Slack OAuth orchestrator (the desktop browser flow). Once the user signs in, the host writes tokens to ${SLACK_CONFIG_PATH}/workspaces/{teamId}.json and the server picks them up on the next call.
The OSS server never initiates OAuth itself.
This server is designed for host-orchestrated OAuth: the host writes per-workspace token files to disk and the server reads them. The examples below show the env shape — your host application is responsible for populating ${SLACK_CONFIG_PATH}/workspaces/{teamId}.json before tool calls succeed.
{
"mcpServers": { "Slack": { "command": "npx", "args": ["-y", "@mindstone/mcp-server-slack"], "env": { "SLACK_CONFIG_PATH": "/absolute/path/to/slack-config", "SLACK_TEAM_ID": "T0123ABCD", "SLACK_CLIENT_ID": "your-slack-app-client-id", "SLACK_CLIENT_SECRET": "your-slack-app-client-secret" } } } }
Until the host has written ${SLACK_CONFIG_PATH}/workspaces/T0123ABCD.json for that team, every tool call returns a structured auth_required response (see the Authentication flow above).
{
"mcpServers": { "Slack": { "command": "node", "args": [" /connectors/slack/dist/index.js"], "env": { "SLACK_CONFIG_PATH": "/absolute/path/to/slack-config", "SLACK_TEAM_ID": "T0123ABCD", "SLACK_CLIENT_ID": "your-slack-app-client-id", "SLACK_CLIENT_SECRET": "your-slack-app-client-secret" } } } }
list_slack_users, get_slack_user_profile, lookup_user_by_email, message name enrichment and the profile shown by open_slack_dm use user authorization first. If it is absent or refused for authorization, scope or token-type reasons, the read may try bot authorization once. A retry starts the read again, including pagination and username resolution. Neither authorization can supply permissions it was not granted; email lookup still needs users:read.email.
If obtaining user credentials reports TOKEN_PERSIST_FAILED, these reads try once more to obtain credentials for user authorization before starting the Slack API read. If the retry fails or finds no user credentials, the read ends without trying bot authorization. Other operational errors do not trigger authorization fallback. Writes keep their identity: opening a DM uses user authorization once, and send_myself_a_note uses only bot authorization. If Slack refuses the app's authorization, the app cannot send you a notification even while other Slack actions still work. Reconnecting may restore it.
list_slack_workspaces tests bot and user authorization independently with auth.test. connected means at least one passed; tokenHealth.botToken and tokenHealth.userToken report each result separately (valid, refused, unavailable, or missing / not_configured). Having a saved token does not establish that Slack accepts it. When no probe passes and at least one is unavailable, follow the retry/status guidance rather than reconnecting immediately. Confirmed expiry with refresh disabled still requires authentication.
The Slack API error classifier preserves the four canonical refusal strings invalid_auth, token_expired, token_revoked and account_inactive byte-for-byte as code, alongside recovery guidance and next_step. Existing API error normalizations include ratelimited → rate_limited, not_allowed_token_type → missing_scope, and users_not_found → user_not_found. Other Slack API error strings pass through unchanged as code. Refresh refusals use the provider's REFRESH_AUTH_REJECTED code with the upstream string in extra data (slack_error_code). The final tool response shape depends on the tool, including existing auth_required responses.
For the people tools and enrichment helpers named above, DM opening and send_myself_a_note, errors include token_role (user or bot) when the attempted role is known, including operational credential-acquisition errors. Structured acquisition failures keep their existing recovery shape.
Each token request reads the token file. If a permission or disk error prevents that read, bot and user token requests can use the requested role's cached credentials already held in memory, including unsaved refresh results, only when that token exists and does not need ref
冒頭だけを表示しています。続きはリポジトリで読めます