Spec Driven Development
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Beschreibung vom Entwickler (englisches Original)
Secure MCP server for WorkBoard OKR and strategy execution platform
Diese drei werden nie zu einer Punktzahl zusammengefasst: Meinungen, Messungen und Beliebtheit sind verschiedene Dinge.
Für diesen Server haben wir noch keine Zusammenfassung in einfacher Sprache geschrieben. Unten stehen die Fakten, die wir aus der Registry gelesen haben.
Wähle die KI-App, die du nutzt, und kopiere die Einstellungen.
Du brauchst
Welche App nutzt du?
Wähle oben deine App. Wir merken sie uns, damit der Button beim nächsten Mal „In … installieren“ anzeigt.
Öffne Claude Desktop → Settings → Developer → Edit Config und füge dies in claude_desktop_config.json ein
{
"mcpServers": {
"workboard": {
"command": "uvx",
"args": [
"mcp-workboard-crunchtools"
]
}
}
}Führe das in deinem Terminal aus
claude mcp add workboard -- uvx mcp-workboard-crunchtoolsIn .cursor/mcp.json in deinem Projekt oder in ~/.cursor/mcp.json einfügen
{
"mcpServers": {
"workboard": {
"command": "uvx",
"args": [
"mcp-workboard-crunchtools"
]
}
}
}Dein Browser fragt, ob er die App öffnen darf, dann zeigt die App die Einstellungen und bittet dich um Bestätigung. Schlüsselwerte bleiben leer, damit du sie selbst einträgst.
In .vscode/mcp.json in deinem Projekt einfügen
{
"servers": {
"workboard": {
"type": "stdio",
"command": "uvx",
"args": [
"mcp-workboard-crunchtools"
]
}
}
}Dein Browser fragt, ob er die App öffnen darf, dann zeigt die App die Einstellungen und bittet dich um Bestätigung. Schlüsselwerte bleiben leer, damit du sie selbst einträgst.
Dieser Server läuft auf deinem Computer, und ChatGPT kann sich nur mit Servern im Internet verbinden. Wähle eine andere App.
Deine Auswahl bleibt in einem Cookie auf diesem Gerät; kein Konto nötig.
Diese Einstellungen werden aus dem Registry-Eintrag des Entwicklers erzeugt. Wenn in der README etwas anderes steht, folge der README.
Läuft auf deinem Computer; die Tool-Liste erscheint nach der Installation in deiner KI-App.
Wir prüfen Informationen, die jeder sehen kann; den Code haben wir nicht gelesen. Checks, die nicht zutreffen, werden nicht mitgezählt. · Geprüft am 6. Nov. 2026
Der Registry-Name wurde mit dem GitHub-Konto crunchtools bestätigt, dem das Repo gehört
Dieses Repo haben wir noch nicht von GitHub gelesen
Dieses Repo haben wir noch nicht von GitHub gelesen
Dieser Server läuft auf deinem Computer; es gibt keinen Endpunkt im Internet
Läuft auf deinem Computer und nutzt stattdessen lokale Einstellungen
Läuft auf deinem Computer; Tool-Listen können wir nur von Endpunkten im Internet lesen
Verglichen mit allen aktiven Servern dieser Kategorie in der Registry. Sterne zählen nur, wenn dem Herausgeber das Repo gehört.
Er hat 1 von 1 zutreffenden Basischecks bestanden. Den Code haben wir nicht gelesen. Bevor du einen Schlüssel oder Token hinzufügst, sieh nach, welche Zugriffe der Server verlangt, und nutze einen Schlüssel, der nur die Berechtigungen hat, die du brauchst.
Die Registry nennt keinen erforderlichen Schlüssel, manche Server bitten dich aber bei der ersten Nutzung, dich anzumelden.
Er läuft auf deinem Computer. Deine KI-App startet ihn bei Bedarf, und die Daten laufen nicht über die Server des Entwicklers (außer der Server ruft selbst einen Onlinedienst auf).
Das GitHub-Repo wurde zuletzt – geändert, und die neueste Version (0.6.1) kam vor 8 Monaten in die Registry.
Apps, die MCP unterstützen, etwa Claude Desktop, Claude Code, Cursor und VS Code. Außerdem brauchst du Python (uv) auf deinem Computer.
In derselben Kategorie: Spec Driven Development, Remote Desktop Commander, Symantec Cloud DLP AIops
Server derselben Kategorie von anderen Entwicklern, sortiert nach Sternen.
So liest du eine Karte:★ GitHub-SterneiDrei Säulen: Bewertungen · Checks · NutzungiAktualisiert = neueste Version in der Registry veröffentlichti
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Remote Desktop Commander: use files, terminal and processes on your own computers from any AI app.
Governed Symantec Cloud DLP — 14 MCP tools, read-only with audit.
Unverändert aus dem Repo des Entwicklers übernommen. PopNx MCP hat den Inhalt weder geprüft noch empfiehlt es ihn. HTML, Bilder und Skripte wurden entfernt. Links führen von dieser Website weg.
A secure MCP (Model Context Protocol) server for WorkBoard OKR and strategy execution platform.
This MCP server is designed to be:
quay.io/crunchtools/mcp-workboard built on Hummingbird Python base image| Component | Name |
|---|---|
| GitHub repo | crunchtools/mcp-workboard |
| Container | quay.io/crunchtools/mcp-workboard |
| Python package (PyPI) | mcp-workboard-crunchtools |
| CLI command | mcp-workboard-crunchtools |
| Module import | mcp_workboard_crunchtools |
The container image is built on the Hummingbird Python base image from Project Hummingbird, which provides:
workboard_get_user_tool - Get a user by ID or the current authenticated userworkboard_list_users_tool - List all users (Data-Admin role required)workboard_create_user_tool - Create a new user (Data-Admin role required)workboard_update_user_tool - Update an existing userworkboard_get_objectives_tool - Get all objectives a user ownsworkboard_get_team_objectives_tool - Get a team's objectives overlapping a date window, past quarters included (slow: reads every visible objective)workboard_get_objective_details_tool - Get details for a specific objective with key resultsworkboard_get_my_objectives_tool - Get the current user's owned objectives by ID (recommended)workboard_create_objective_tool - Create a new objective with key results (Data-Admin required)workboard_get_my_key_results_tool - List current user's key results with metric IDs and progressworkboard_update_key_result_tool - Update key result progress for weekly OKR check-insworkboard_get_workstreams_tool - Get team workstreams accessible to the authenticated userworkboard_get_workstream_activities_tool - Get workstream details with all action itemsworkboard_get_workstream_columns_tool - List the Kanban columns in use on a workstreamworkboard_get_team_workstreams_tool - Get all workstreams belonging to a specific teamworkboard_create_workstream_tool - Create a new workstream for a teamworkboard_update_workstream_tool - Update workstream properties (name, dates, pace, health, priority)workboard_auth_status_tool - Report auth mode, token store, and whether the credential works (GET /user)workboard_auth_start_tool - Return the WorkBoard authorize URL for browser approval (OAuth mode)workboard_auth_result_tool - Report the outcome of the most recent authorization redirectuvx mcp-workboard-crunchtools
pip install mcp-workboard-crunchtools
podman run -e WORKBOARD_API_TOKEN=your_token \
quay.io/crunchtools/mcp-workboard
claude mcp add mcp-workboard \
--env WORKBOARD_API_TOKEN=your_token_here \ -- uvx mcp-workboard-crunchtools
Or for the container version:
claude mcp add mcp-workboard \
--env WORKBOARD_API_TOKEN=your_token_here \ -- podman run -i --rm -e WORKBOARD_API_TOKEN quay.io/crunchtools/mcp-workboard
In OAuth mode (WORKBOARD_CLIENT_ID + WORKBOARD_CLIENT_SECRET), a server reachable over HTTPS can be re-authorized without a shell:
https://workboard.example.com/callback, as the redirect URI of the WorkBoard app.WORKBOARD_OAUTH_REDIRECT_URI to that same URL. The proxy must route /callback to the server.workboard_auth_start_tool, open the URL it returns and approve. WorkBoard redirects to /callback; the server exchanges the code and saves the tokens to the token store. The authorization expires after 10 minutes.workboard_auth_status_tool to confirm (or workboard_auth_result_tool to see why it failed).podman run -p 8000:8000 \
-e WORKBOARD_CLIENT_ID -e WORKBOARD_CLIENT_SECRET \ -e WORKBOARD_OAUTH_REDIRECT_URI=https://workboard.example.com/callback \ -e WORKBOARD_TOKEN_STORE_PATH=/data/tokens.json -v workboard-tokens:/data:Z \ quay.io/crunchtools/mcp-workboard --transport streamable-http --host 0.0.0.0
| Variable | Default | Description |
|---|---|---|
WORKBOARD_OAUTH_REDIRECT_URI | unset | Public URL of this server's /callback route. Required for workboard_auth_start_tool; the CLI login ignores it and uses http://localhost:8963/callback. |
WORKBOARD_TOKEN_STORE_PATH | ~/.config/mcp-workboard/tokens.json | Where OAuth tokens are stored |
User: Who am I in WorkBoard?
Assistant: [calls workboard_get_user with no args]
User: List all WorkBoard users
Assistant: [calls workboard_list_users]
User: Show me objectives for user 12345
Assistant: [calls workboard_get_objectives with user_id=12345]
User: Get details on objective 67890 for user 12345
Assistant: [calls workboard_get_objective_details with user_id=12345, objective_id=67890]
User: Show me my objectives (IDs: 2900058, 2900075, 2901770)
Assistant: [calls workboard_get_my_objectives with objective_ids=[2900058, 2900075, 2901770]]
User: Show me my key results
Assistant: [calls workboard_get_my_key_results]
User: Update key result 12345 to 75
Assistant: [calls workboard_update_key_result with metric_id=12345, value="75"]
User: Create an objective called "Increase retention" owned by user@example.com
Assistant: [calls workboard_create_objective with name, owner, dates, and optional key_results]
User: Show me my workstreams
Assistant: [calls workboard_get_workstreams]
User: Show me the agenda for workstream 4130463
Assistant: [calls workboard_get_workstream_activities with ws_id=4130463]
This server was designed with security as a primary concern. See SECURITY.md for:
git clone https://github.com/crunchtools/mcp-workboard.git
cd mcp-workboard uv sync
uv run pytest
uv run ruff check src tests
uv run mypy src
podman build -t mcp-workboard .
AGPL-3.0-or-later
Contributions welcome! Please read SECURITY.md before submitting security-related changes.