What is the Empwr.ai MCP?
MCP (Model Context Protocol) is an open standard that lets AI assistants securely access data from external apps. The Empwr.ai MCP gives the assistant of your choice direct access to your Empwr.ai workspace, so you can ask questions in plain language and get answers grounded in your actual meetings and projects, no copy-pasting required.
Before you begin
You'll need:
A paid Empwr.ai account. If you don't have one yet, contact us at [email protected] to get set up.
An account with the AI assistant you want to connect. Custom connector support varies by product and plan, so check your assistant's documentation if you aren't sure whether your plan supports custom MCP servers.
The Empwr.ai MCP URL
You'll be asked to paste this URL during setup in any of the assistants below:
Keep it handy. Every setup flow on this page uses the same URL.
Step 1: Connect to Your AI Assistant
Pick the assistant you use and follow the steps below. After authorization, the connection is live and ready for queries.
Claude
Sign in at claude.ai and open Settings → Connectors.
Scroll to the bottom of the page and click Add Custom Connector.
Paste
https://app.empwr.ai/api/mcpinto the URL field.Follow the prompts to authorize Empwr.ai.
Once connected, Empwr.ai shows up as a connector you can use in any Claude conversation.
ChatGPT
ChatGPT supports custom MCP connectors on eligible paid plans.
Sign in at chatgpt.com and open Settings → Connectors.
Click Create (or Add a connector, depending on your plan).
Paste
https://app.empwr.ai/api/mcpas the MCP server URL.Authorize the connection when prompted.
Open AI Codex
Codex supports custom MCP connectors on eligible paid plans.
Sign into Codex and open Settings → MCP Servers
Click Add Server
Name the server
Empwr.aiand then pastehttps://app.empwr.ai/api/mcpas the MCP server URL.Click Save and authorize the connection when prompted.
If you don't see the Connectors option, your plan may not include custom MCP support. Email [email protected] and we'll point you to the right next step.
Microsoft Copilot
Microsoft Copilot supports MCP connectors through Copilot Studio agents.
Sign in at copilotstudio.microsoft.com.
Open or create the agent you'd like to add Empwr.ai to.
Go to Tools → Add a tool → Custom connector (look for the MCP server option).
Paste
https://app.empwr.ai/api/mcpand complete the authorization.
If you're using the consumer version of Microsoft Copilot, custom connector support may be limited. Reach out to [email protected] for guidance.
Step 2: Try a Query
Once the connection is live, your AI assistant can pull context directly from your Empwr.ai workspace. A few examples to get you started:
"What decisions and open questions came out of this week's meetings?"
"What did I commit to this week that I haven't finished yet?"
"Give me the current status of the {project} rollout: blockers, risks, and open Jira issues."
You can ask follow-up questions in the same conversation, and the assistant will pull fresh context from Empwr.ai each time.
Empwr.ai MCP Tools
The following documents the tools exposed by the Empwr.ai MCP server. These tools let an AI assistant (like Claude) read project, meeting, and task data from your Empwr.ai workspace so it can answer questions, summarize work, and help you stay on top of what's happening.
All tools are read-only — they fetch information from Empwr.ai but don't modify anything.
Projects
list_projects — List Projects
Returns the projects you have access to in your workspace.
Use this when you want a quick overview of what's in flight, or as a starting point before drilling into a specific project.
get_project — Get Project Details
Fetches the full details of a single project, including its description, status, owner, and metadata.
Use this when you already know which project you care about and want the deeper context behind it.
get_project_risks — Get Project Risks
Returns the risks tracked against a project — things the team has flagged as potential blockers or threats to delivery.
Use this when you're trying to understand what could go wrong, or to brief a stakeholder on the state of a project.
Project Documents
get_project_documents — Get Project Documents
Lists the documents attached to a project (specs, briefs, status reports, etc.).
Use this to discover what written context exists for a project before diving in.
get_project_document_details — Get Project Document Details
Returns the full content and metadata for a specific document.
Use this after get_project_documents when you want to actually read a document, not just see its title.
Tasks
list_tasks — List Tasks
Returns tasks across your workspace, regardless of which project they belong to.
Use this for a personal, cross-project view — e.g. "what am I working on this week?"
list_project_tasks — List Project Tasks
Returns the tasks scoped to a single project.
Use this when you want to understand the work breakdown for one specific project.
Meetings
list_meetings — List Meetings
Returns the meetings Empwr.ai has captured (via integrations like Recall.ai, Google Calendar, etc.).
Use this to find a recent or upcoming meeting before pulling its details.
get_meeting_outcome — Get Meeting Outcome
Returns the AI-generated outcome of a specific meeting — the summary, key decisions, and what was discussed.
Use this when you missed a meeting, want a recap, or are trying to remember what was decided.
Action Items
list_action_items — List Action Items
Returns action items extracted from meetings — the "who owes what" follow-ups Empwr.ai pulled out of conversations.
Use this to track commitments coming out of meetings without having to re-read every transcript.
Integrations
list_project_integration_issues — List Project Integration Issues
Returns issues from connected tools (Jira, Linear, Monday.com, etc.) that are linked to a project in Empwr.ai.
Use this when you want a unified view of work tracked outside Empwr.ai but tied to a specific project.
How they fit together
A typical flow looks like this:
Start broad with list_projects, list_meetings, or list_tasks.
Narrow down with get_project, get_meeting_outcome, or list_project_tasks.
Dig into details with get_project_documents → get_project_document_details, or get_project_risks and list_project_integration_issues for the full project picture.
The assistant will usually chain these together on its own — you just describe what you want to know, and it picks the right tools.
Need Help?
Custom MCP setup can look different depending on your AI assistant and your plan. If you hit a snag at any step, send us a note at [email protected] and we'll get you connected.