
MCP Workboard
io.github.crunchtoolsPublished by GitHub account crunchtoolsv0.6.1Updated Oct 24, 2026
Secure MCP server for WorkBoard OKR and strategy execution platform
Overview
Local MCP server for the WorkBoard OKR and strategy execution platform, letting an assistant read and update users, objectives, key results and workstreams.
- What you can do
- Look up users: get the current user or a user by ID, list all users, create and update users
- Read objectives: owned objectives, team objectives over a date window, objective details with key results, and the current user's objectives by ID
- Create objectives with key results, and list or update key result progress for weekly check-ins
- Work with workstreams: list accessible or team workstreams, read details and action items, list Kanban columns, create and update workstream properties
- Check authorization status and, in OAuth mode, start browser approval and report the result of the last redirect
- When to use it
- Useful when a team runs its OKRs and strategy execution in WorkBoard and wants an assistant to answer questions about objectives, key results and workstreams, or to record progress updates and create objectives without switching apps.
- Requirements
- Runs locally over stdio from the PyPI package mcp-workboard-crunchtools (uvx or pip) or as a container image. Needs a WorkBoard API token supplied through the WORKBOARD_API_TOKEN environment variable, or OAuth mode with WORKBOARD_CLIENT_ID and WORKBOARD_CLIENT_SECRET; the OAuth redirect setup also uses WORKBOARD_OAUTH_REDIRECT_URI and WORKBOARD_TOKEN_STORE_PATH. Network access to the WorkBoard API is required.
Installation
In SourceWeft
- Open MCP Workboard in the dashboard and add it to a workspace.
- Enable the server for the chats that should use its tools.
Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.
Other MCP clients
Follow the launch instructions in the repository.
README
MCP WorkBoard CrunchTools
A secure MCP (Model Context Protocol) server for WorkBoard OKR and strategy execution platform.
Overview
This MCP server is designed to be:
- Secure by default - Threat modeling, input validation, and token protection
- No third-party services - Runs locally via stdio, your API token never leaves your machine
- Cross-platform - Works on Linux, macOS, and Windows
- Automatically updated - GitHub Actions monitor for CVEs and update dependencies
- Containerized - Available at
quay.io/crunchtools/mcp-workboardbuilt on Hummingbird Python base image
Naming Convention
Why Hummingbird?
The container image is built on the Hummingbird Python base image from Project Hummingbird, which provides:
- Minimal CVE exposure - Built with a minimal package set, dramatically reducing attack surface
- Regular updates - Security patches applied promptly
- Optimized for Python - Pre-configured with uv package manager
- Production-ready - Proper signal handling and non-root user defaults
Features
User Management (4 tools)
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 user
Objective Management (5 tools)
workboard_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)
Key Result Management (2 tools)
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-ins
Workstream Management (6 tools)
workboard_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)
Authorization (3 tools)
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 redirect
Installation
With uvx (Recommended)
With pip
With Container
Configuration
Getting a WorkBoard API Token
- Log in to your WorkBoard instance
- Navigate to Admin Settings > API Configuration
- Generate a JWT API token
- Copy the token immediately - store it securely
Add to Claude Code
Or for the container version:
OAuth on a Server (Container Behind a Reverse Proxy)
In OAuth mode (WORKBOARD_CLIENT_ID + WORKBOARD_CLIENT_SECRET), a server
reachable over HTTPS can be re-authorized without a shell:
- Register the public callback URL, e.g.
https://workboard.example.com/callback, as the redirect URI of the WorkBoard app. - Run the server with an HTTP transport and set
WORKBOARD_OAUTH_REDIRECT_URIto that same URL. The proxy must route/callbackto the server. - Call
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. - Call
workboard_auth_status_toolto confirm (orworkboard_auth_result_toolto see why it failed).
Usage Examples
Get Current User
List All Users
Get User Objectives
Get Objective Details
Get My Objectives
List My Key Results
Update Key Result Progress
Create an Objective
List Workstreams
Get Workstream Action Items
Security
This server was designed with security as a primary concern. See SECURITY.md for:
- Threat model and attack vectors
- Defense in depth architecture
- Token handling best practices
- Input validation rules
Key Security Features
-
Token Protection
- Stored as SecretStr (never accidentally logged)
- Environment variable only (never in files or args)
- Sanitized from all error messages
-
Input Validation
- Pydantic models for all inputs
- Positive integer validation for IDs
- Email validation for user creation
-
API Hardening
- Hardcoded API base URL (prevents SSRF)
- TLS certificate validation
- Request timeouts
- Response size limits
-
Automated CVE Scanning
- GitHub Actions scan dependencies weekly
- Automatic issues for security updates
- Dependabot alerts enabled
Development
Setup
Run Tests
Lint and Type Check
Build Container
License
AGPL-3.0-or-later
Contributing
Contributions welcome! Please read SECURITY.md before submitting security-related changes.
Links
Source: README.md at commit ea07dcf
Tools
0Version history
1- v0.6.1LatestSep 16, 2026
Score
50% of the applicable checks met
How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.
- Reached in the last 30 days25 pts
Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.
- Auth declared10 pts
Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.
- Tools listed15 pts
Answer tools/list without a credential, or ship a package that starts in a sandbox without one.
- DescriptionRequired15 pts
- Logo10 pts
- Documentation15 pts
- License10 pts