Turning Strategy Into Shared Operational Context

Dotwork MCP provides secure, live access to your ontology, objects, properties, relationships, and history, so AI is grounded in the operating model and the organization can update context seamlessly.

CursorClaude CodeCodexChatGPTCowork

Sign in to connect to the
Dotwork MCP

.cursor/mcp.json
{
  "mcpServers": {
    "dotwork": {
      "url": "https://<your-dotwork-host>/mcp"
    }
  }
}

Dotwork resolves identity and workspace scope after the client connects to the MCP endpoint.

Dotwork MCP turns the graph behind your operating model into a governed context layer for assistants, agents, and AI-native workflows.

A live model of how your organization operates

Give AI the same operating structure your teams use: value streams, products, teams, goals, work, metrics, workflows, relationships, and ownership, all in a connected operational graph.

Grounded intelligence from real operating context

Help agents generate plans, summaries, recommendations, and decisions using current strategy, portfolio activity, dependencies, discussions, and execution data, not isolated prompts or stale documentation.

Operational actions with built-in guardrails

Let agents safely prepare updates, create relationships, move workflows forward, coordinate handoffs, and draft changes inside governed operational boundaries with human approval where needed.

Context that always links back to the source

Every answer connects back to the relevant Dotwork artifact, workflow, inbox, or operational record so knowledge stays connected to the system of work, not trapped in chat threads.

What teams use it for

Powering skills for visibility, exploration, and action

Connect your preferred MCP-compatible client, complete Dotwork sign-in, and give your assistant the context it needs to find, explain, update, and route work.

---
name: dotwork-prioritization
description: Show where capacity is flowing, what outcomes it's producing, and where the real tradeoff decisions are. Use this skill whenever someone asks about "portfolio mix", "investment allocation", "where is our capacity going", "show me the tradeoffs", "effort to outcomes", "what are we getting for our investment", "who's contributing to this goal", "why isn't this moving", or "capacity planning". Pulls live Initiatives, traverses the Priority/OKR graph, uses field history to detect progress stalls and allocation drift, and surfaces investment-to-outcome mismatches. Always run this skill — do not attempt portfolio prioritization analysis without it.
---
# Prioritization: Understanding Portfolio Mix Without the Theater
Most organizations can't answer "where is our capacity going and what is it producing?" in under an hour. They either have no allocation data (so they guess) or they have it tracked at such granularity that it's stale by the time anyone reads it. This skill takes the middle path: connect work to outcomes using the relationship graph, then surface where the math doesn't add up.
## What this skill covers
1. Work-to-Outcome Map — Initiatives traced up through OKRs to Priorities, showing how execution connects to strategy
2. Investment Distribution — Where work is clustered, by Priority and team
3. Progress vs. Status Check — Cross-referencing field history (has the KR actually moved?) against self-reported status
4. Stall Detection — Initiatives that have been "In Progress" for a long time with no field movement
5. Tradeoff Surface — Where the portfolio is over-concentrated or under-served relative to stated priorities
Enterprise governed

Headless Strategic Context, Built for the Enterprise.

Dotwork MCP inherits your authentication, permissions, site policy, and approval model. Agents can be helpful without becoming another unmanaged integration surface.

Uses the normal Dotwork sign-in flow, including SAML SSO, OAuth, or basic auth when enabled.
Scopes access to the authenticated user, active site, workspace policy, and customer deployment.
Optionally keeps humans in the loop for approvals before higher-risk reads, writes, workflow starts, or messages take action in Dotwork.
Shows granular token spend across agent actions and workflows so teams can understand AI usage inside Dotwork.

FAQ

Dotwork MCP, in plain language.

A quick orientation for business, platform, and AI teams evaluating how assistants should work with Dotwork.

What is MCP?+

Model Context Protocol is a standard way for AI clients to connect to external systems. Dotwork uses it to expose the ontology adn operational graph in a structured, permissioned way.

Who is Dotwork MCP for?+

It is for teams that want both people and agents to understand strategy, portfolios, operating structures, dependencies, and work history instead of only reading disconnected app data.

Can it make changes in Dotwork?+

Yes, when the client, site policy, and user approval allow it. The page is designed around governed access, so write-oriented actions can remain confirm-first.

Which clients can connect?+

Any MCP-compatible client that can reach the Dotwork endpoint and complete the supported authentication flow. Common examples include Cursor, Claude Code, Codex, ChatGPT, and Cowork.

Bring Dotwork context to your AI agents.

Get a DemoContact Sales
SSO-ready. Enterprise security built in. Designed for humans and agents working from the same context.
Dotwork

Your company's operating system for the AI era

Twitter•LinkedIn•YouTube
AICPA
SOC 2

Platform

Solutions

Resources

Company

Connect

© 2025-2026 Dotwork, Inc. All rights reserved.