# Tability MCP Server
## Using Tability MCP Server
Connect ChatGPT or Claude AI to your Tability account using the Model Context Protocol (MCP). This integration allows Claude, ChatGPT and any MCP-ready services to read your OKRs, check progress, and create check-ins directly through natural conversation.
### What is MCP?
The Model Context Protocol (MCP) is an open standard that allows AI assistants like Claude and ChatGPT to securely connect to external tools and data sources.
With the Tability MCP server, you can access your goals, key results, and initiatives to help you stay on top of your OKRs.
### Examples of usage
With the Tability MCP integration, you can ask your AI assistant to:
* View your workspace, plans, and objectives
* Check progress on key results
* List initiatives and their status
* Create check-ins with progress updates
* Search across your OKRs
* Manage team memberships
**Example prompts:**
* "Show me all my active plans in Tability"
* "What's the progress on our Q1 objectives?"
* "Create a check-in for the revenue key result with a value of 150000"
* "Who owns the customer satisfaction outcome?"
### Prerequisites
* A [Claude](https://claude.ai/), [ChatGPT](https://chatgpt.com/) or Microsoft Teams/Copilot + Copilot Studio account
* A Tability workspace where you have enabled API access for your user account
### How to enable API access for a user
In order to use MCP with a specific workspace, you will need to enable API access for that your user account in that workspace.
{% hint style="info" %}
Contact your admin if you do not have access to the settings of your workspace
{% endhint %}
1. Go to your workspace
2. Go to **Settings > Users**
3. Search for your user account (or the users that need access to MCP)
4. Click on their account
5. Update the settings **API Access Enabled** to **Yes**
### How to configure Tability Remote MCP Server
#### Connector details
We have different MCP server URL based on the cloud that you're using to access Tability.
Cloud
MCP Server URL
US Cloud (default)
https://mcp.tability.app/mcp
EU Cloud
https://mcp-eu.tability.app/mcp
AU Cloud
https://mcp-au.tability.app/mcp
* Connector name: Tability
* Logo: use the logo below if necessary
{% file src="/files/Dz49A89WcLtWjih5Iee5" %}
#### Claude configuration
1. Sign in to your Claude account
2. Go to **Settings > Connectors**
3. Click **Add custom connector**
4. Fill in the connector details
1. **Name**: Tability
2. **Remote MCP server URL**: (or replace with appropriate cloud specific MCP server URL)
5. Save the connector
You can now start mentioning Tability in your prompts.
#### ChatGPT configuration
1. Sigin in to your ChatGPT account
2. Go to **Settings > Apps > Advanced Settings**
3. Turn on **Developer Mode**
4. Click **Create app**
5. Fill in the connector details
1. **Name**: Tability
2. **Remote MCP server URL**: (or replace with appropriate cloud specific MCP server URL)
6. Create the app
To access your Tability data, make sure that the Tability connector is listed in the tools available (click on the + in the prompt box).
#### Microsoft Copilot Studio configuration
**How to create your custom agent**
{% hint style="warning" %}
The Agent in Copilot Studio will use the same identity for all users — we recommend creating a custom user account in Tability to control the visibility of the data.
{% endhint %}
1. Sign into your Copilot Studio account
2. Click on **Create an agent**
3. In the **Tools** section, click on **Add tool**
4. Select **Model Context Protocol**
5. Fill in the details
1. **Server name:** Tability MCP Server
2. **Server Description:** Talk to your OKRs in Tability via the official Remote MCP Server
3. **Server URL:**
4. **Authentication:** OAuth 2.0
5. **Authentication Type:** Dynamic discovery
6. After creating your agent, click on **Create connection**
7. Complete the OAuth process
8. Click on **Add and configure**
You should now be able to test your agent (ex: "Who am I?")
**How to publish to Teams and Copilot**
1. In your agent config page, select the **Channels** tab
2. Click on **Teams and Microsoft 365 Copilot**
3. Click on Add channel
That's it! You will now be able to use your new agent connected to Tability MCP Server
### Verifying the Connection
After connecting the server in Claude, ChatGPT or Copilot:
1. Look for the MCP tools icon in the chat interface (click on the + button), or click on the corresponding Custom Agent in Copilot or Teams
2. Try asking: "Use Tability to show me who I am"
Claude/ChatGPT should respond with your Tability user profile information.
### Available Tools
The Tability MCP Server provides tools grouped by the type of object they work with.
#### User and workspace
| Tool | Description |
| ------------------------ | ---------------------- |
| `tability_whoami` | Get your user profile |
| `tability_get_workspace` | View workspace details |
#### Agents
| Tool | Description |
| ----------------------- | ------------------------------------------------ |
| `tability_list_agents` | List workspace agents |
| `tability_get_agent` | Get a specific agent profile and its active work |
| `tability_create_agent` | Create a new agent profile |
#### Memberships
| Tool | Description |
| ---------------------------------------- | ----------------------------- |
| `tability_list_memberships` | List workspace members |
| `tability_get_membership` | Get member details |
| `tability_get_membership_manager` | Get a member's manager |
| `tability_get_membership_direct_reports` | Get a member's direct reports |
#### Plans
| Tool | Description |
| --------------------------- | -------------------------------------------------------------------- |
| `tability_list_plans` | List plans |
| `tability_get_plan` | Get plan details |
| `tability_get_plan_content` | Get a plan's objectives, outcomes, initiatives, and latest check-ins |
#### Objectives
| Tool | Description |
| ----------------------------------- | ------------------------- |
| `tability_list_objectives_for_plan` | List objectives in a plan |
| `tability_get_objective` | Get objective details |
| `tability_search_objectives` | Search objectives |
#### Outcomes
| Tool | Description |
| -------------------------------------- | ------------------------------------ |
| `tability_list_outcomes_for_plan` | List outcomes in a plan |
| `tability_list_outcomes_for_objective` | List outcomes for an objective |
| `tability_create_outcome` | Create an outcome under an objective |
| `tability_get_outcome` | Get outcome details |
| `tability_search_outcomes` | Search outcomes |
#### Initiatives
| Tool | Description |
| --------------------------------------- | -------------------------------------------- |
| `tability_list_initiatives_for_plan` | List initiatives in a plan |
| `tability_list_initiatives_for_outcome` | List initiatives for an outcome |
| `tability_get_initiative` | Get initiative details |
| `tability_create_initiative` | Create an initiative for an outcome |
| `tability_update_initiative` | Update initiative fields except `work_state` |
| `tability_search_initiatives` | Search initiatives |
#### Initiative comments and replies
| Tool | Description |
| ------------------------------------ | ----------------------------------------------------------- |
| `tability_list_initiative_comments` | List status comments for an initiative |
| `tability_get_initiative_comment` | Get initiative comment details |
| `tability_create_initiative_comment` | Create an initiative status comment and update `work_state` |
| `tability_list_initiative_replies` | List replies on an initiative comment |
#### Check-ins
| Tool | Description |
| ------------------------------------ | ----------------------------- |
| `tability_list_checkins_for_outcome` | List check-ins for an outcome |
| `tability_get_checkin` | Get check-in details |
| `tability_create_checkin` | Create a progress check-in |
| `tability_list_checkin_comments` | List comments on a check-in |
#### Agent relationships
| Tool | Description |
| --------------------------------------------------- | ----------------------------------- |
| `tability_list_agent_relationships_for_outcome` | List agents linked to an outcome |
| `tability_create_agent_relationship_for_outcome` | Link an agent to an outcome |
| `tability_list_agent_relationships_for_initiative` | List agents linked to an initiative |
| `tability_create_agent_relationship_for_initiative` | Link an agent to an initiative |
| `tability_get_agent_relationship` | Get agent relationship details |
| `tability_delete_agent_relationship` | Remove an agent relationship |
#### Search
| Tool | Description |
| ----------------------- | ------------ |
| `tability_search_plans` | Search plans |
### Example Conversations
#### Checking OKR Progress
> **You:** What's the status of our Q1 2024 plan?
>
> **Claude:** I'll look up your Q1 2024 plan. \[Uses tability\_search\_plans and tability\_list\_outcomes\_for\_plan]
>
> Your Q1 2024 plan has 3 objectives with 12 key results. Overall progress is 67%. Here's a summary...
#### Creating a Check-in
> **You:** Update the MRR key result to $52,000 with a note that we closed the Acme deal
>
> **Claude:** I'll create that check-in for you. \[Uses tability\_create\_checkin]
>
> Done! I've recorded a check-in for the MRR key result with a value of $52,000 and your note about the Acme deal.
#### Finding Ownership
> **You:** Who is responsible for our customer satisfaction outcomes?
>
> **Claude:** Let me search for customer satisfaction outcomes. \[Uses tability\_search\_outcomes]
>
> I found 2 outcomes related to customer satisfaction. The NPS score outcome is owned by Sarah, and the CSAT outcome is owned by Mike.
### Troubleshooting
#### Support
If you encounter issues with the MCP integration:
* Contact Tability support at
---
# Agent Instructions: Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.
Perform an HTTP GET request on the current page URL with the `ask` query parameter:
```
GET https://guides.tability.io/docs/become-a-tability-power-user/integrations/tability-mcp-server.md?ask=
```
The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.
Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.