[Beta] Rally MCP
Last updated: July 22, 2026
Beta - Updated Regularly: This feature is actively evolving, and so is this article. We'll continue updating it throughout Beta as new functionality is added and things change. Check back often for the latest.
Rally MCP lets you connect AI assistants like Claude, Claude Code, Cursor, and other MCP-compatible tools to your Rally workspace.
Rally hosts an MCP service that your assistant connects to over the web; through that connection, your assistant discovers and runs tools like searching your participant pool, reviewing participants and responses, looking up interview details, and more.
Everything your assistant can see or do through MCP stays inside your workspace and follows the same access your Rally account already has.
Connecting to the Rally MCP
Rally MCP uses Sign in with Rally, your AI client opens a Rally login page in your browser, you sign in, and you're connected. No keys to copy or manage.
Endpoint
Use this MCP URL when your client asks for a server address:
https://mcp.rallyuxr.com/mcpClaude (Desktop and claude.ai)
Go to Customize > Connectors > Click + > Add custom connector.
Enter the Rally MCP URL:
https://mcp.rallyuxr.com/mcpClick Add. Claude will open your browser to sign in to Rally.
After you approve access, the connection is active.
On Team and Enterprise plans, an Owner must first add the connector in Organization settings > Connectors before members can connect to it.
For more details on adding custom connectors in Claude, see Get started with custom connectors using remote MCP.
Cursor
Open your MCP configuration file (
.cursor/mcp.jsonin your project, or your user-level MCP settings).Add the following entry:
{
"mcpServers": {
"rally": {
"url": "https://mcp.rallyuxr.com/mcp"
}
}
}Restart Cursor. It will prompt you to sign in to Rally in your browser.
Claude Code
Add Rally as an MCP server using the CLI:
claude mcp add rally --transport http https://mcp.rallyuxr.com/mcpClaude Code handles the OAuth flow automatically. It opens your browser to sign in to Rally when you first use a Rally tool. You can check the connection status anytime by typing /mcp in Claude Code.
For more on connecting Claude Code to MCP servers, see Connect Claude Code to tools via MCP.
Other MCP clients
If your client supports remote MCP servers (sometimes called "HTTP" or "Streamable HTTP" transport), point it at https://mcp.rallyuxr.com/mcp. The client will handle the OAuth sign-in flow automatically.
If your client only supports local (stdio) servers, you can use mcp-remote as a bridge:
{
"mcpServers": {
"rally": {
"command": "npx",
"args": [
"mcp-remote",
"https://mcp.rallyuxr.com/mcp"
]
}
}
}When the client starts, mcp-remote will open your browser so you can sign in to Rally.
What can be done with the MCP
Ask questions about your research
Using the MCP, you can ask your AI assistant plain-language questions about any study or participant in your workspace you have access to.
With the MCP connected, you can:
Ask who's booked, confirmed, or completed within a study
Ask who's enrolled in a study
Get a summary of where a study stands and whether it's on track to hit quota
Track recruitment progress against quota — who's consented and how close you are to target
Look up people in your workspace using criteria, driven by your property data
Pull what a participant said in their screener or observer room transcript
Get the full detail on a single interview
List studies by keyword or status (Ex: "Which studies are still in draft?")
See what people answered on a screener or survey
Check for decisions across your studies that are waiting on your input
What you want to do | Example prompt | Tool |
|---|---|---|
See upcoming interviews | "Who's booked this week?" |
|
Check past interviews | "Which interviews happened last week?" |
|
See who's enrolled in a study | "Who's enrolled in the onboarding study?" |
|
Check study progress | "Are we on track to hit quota?" |
|
Track quota and consent progress | "How's recruitment tracking for the Onboarding study? Who's consented, and how close are we to target?" |
|
Review a transcript | "What did Jim say about pricing?" |
|
Get interview details | "Give me the details of Friday's 2pm." |
|
Find a study | "Which studies are still in draft?" |
|
Get a study summary | "Tell me about the onboarding study." |
|
Find people in your workspace | "Find designers in SF who shop online weekly." |
|
Look up a participant | "Tell me about Jim Cooper." |
|
Look up a person | "Tell me about Jane Smith." |
|
Review screener/survey answers | "What did people answer on the screener?" |
|
See what needs your input | "What needs my input across my studies?" |
|
Note: Quota tracking shows who's consented and counted toward your target — it doesn't include creating a study with a quota.
Manage interviews
Using the MCP, you can book, move, staff, and prep interviews directly from your AI assistant, no need to open the scheduler yourself.
With the MCP connected, you can:
Schedule, reschedule, or cancel an interview
Move an interview to a different host
Add a guest or observer to an upcoming session
Mark attendance or a no-show after the fact
Block off or adjust your personal interviewer availability
Put together a prep brief ahead of a session
What you want to do | Example prompt | Tool |
|---|---|---|
Schedule an interview | "Schedule an interview with Jim Cooper next Tuesday at 2PM." |
|
Reschedule an interview | "Reschedule Jim Cooper's interview to Thursday at 2PM." |
|
Cancel an interview | "Cancel tomorrow's interview with Jim Cooper." |
|
Change who's hosting | "Move tomorrow's 2pm interview to Sarah." |
|
Add a guest to a session | "Add Jamie as a guest to Friday's session." |
|
Mark attendance or a no-show | "P5 didn't show, mark it." |
|
Update your availability | "Block my Fridays from the scheduler." |
|
Get a prep brief before an interview | "Prep me for my 3pm with P4." |
|
Set up and publish an interview study from a template
Using the MCP, you can build a study using one of your organization's approved templates, screener included. The MCP can only create studies from existing templates, it cannot create a study from scratch.
Just tell your assistant who you'd like to talk to and walk through the steps until the study is published.
Specifically, you can:
Find people in Rally who match your criteria and create a study from one of your organization's approved templates with that audience
Import a list of people from a file and create a study using them as the audience
Update fields on a draft study (incentive, duration, participant target, etc.)
Add, refine, or remove screener questions
Attach a consent form
See what email templates a study has configured
Publish the study once it's ready
Studies stay in draft state until you explicitly publish them, nothing goes live until you do.
What you want to do | Example prompt | Tool |
|---|---|---|
Start a study using your populations | "Find dog owners who shop online weekly and start a study." |
|
Start a study from an imported list | "Import this CSV and start a study with them." |
|
Start a study from a template | "Set up an onboarding interview study." |
|
Update study details | "Bump the incentive to $75 and change duration to 45 minutes." |
|
Add a screener question | "Add a screener question about company size." |
|
Remove a screener question | "Drop the age question." |
|
Attach a consent form | "Attach our standard consent form." |
|
See a study's message templates | "What emails does the Onboarding study send?" |
|
Publish the study | "Publish the onboarding study." |
|
Manage populations
The MCP also gives you a way to work with your populations and the properties tracked on people, outside of any single study.
With the MCP connected, you can:
Create a new population or panel
Look up the custom person properties tracked in your workspace
What you want to do | Example prompt | Tool |
|---|---|---|
Add people to a live study | "Create a new panel for enterprise users." |
|
Import people into a panel | "What custom properties do we track on people, like company size or role?" |
|
Manage participants
Once a study is running, the MCP lets you manage who's in it. This means adding people, changing their status, and keeping notes on them.
With the MCP connected, you can:
Add more people to a study that's already in draft or live
Import a list of people into a population, without necessarily starting a study
Qualify or disqualify a participant
Add a note to a participant's record
What you want to do | Example prompt | Tool |
|---|---|---|
Add people to a live study | "Add 20 more people to the onboarding study." |
|
Import people into a panel | "Import these 40 contacts into the panel." |
|
Qualify or disqualify someone | "Disqualify Mo from my study." |
|
Add a note to a participant | "Note that P1 prefers mornings." |
|
Message participants
Using the MCP, you can reach out to participants directly, whether it's a saved study message or a quick one-off note.
With the MCP connected, you can:
Send a template study message, like an invitation or scheduler link
Send a one-off custom email
What you want to do | Example prompt | Tool |
|---|---|---|
Send a study message | "Send P3 my scheduler." |
|
Send a custom email | "Email P3 to bring their laptop to the session." |
|
Drive recruitment
Once a study is live, the MCP gives you a way to check on the participant pipeline and prepare outreach whenever you ask.
With the MCP connected, you can:
Check whether your panel can support a target audience before you launch
Prepare and send recruitment email campaigns to your audience
Check for pending recruitment decisions and approve them
See what email campaigns are running on a study
Check email activity such as sends, opens, and bounces
Pause, resume, or close recruitment on a study
What you want to do | Example prompt | Tool |
|---|---|---|
Check recruiting feasibility | "Can we target 20 Senior Engineers in fintech that have been active in the last 28 days from our existing panel?" |
|
Start outreach | "Start reaching out to the audience." |
|
Approve a recruitment decision | "Approve the recruitment proposal for the onboarding study." |
|
See a study's email campaigns | "What campaigns are running on this study? Which are paused?" |
|
Check email activity | "How many invites went out? Any bounces?" |
|
Pause recruiting | "Pause recruiting while we fix the screener." |
|
Handle incentives
After a completed interview, the MCP gives you a way to check on and act on participant payouts, this means no manual queue to dig through.
With the MCP connected, you can:
Check for pending incentive sends and approve them
Resend or cancel an incentive that didn't go through
Log an incentive that was sent outside of Rally, like swag or a gift card
What you want to do | Example prompt | Tool |
|---|---|---|
Approve pending incentives | "Approve incentive sends for yesterday's interviews." |
|
Resend or cancel an incentive | "Resend P2's gift card, it bounced." |
|
Log a manual incentive | "Set up a custom incentive of a $50 Amazon gift bag, and log it as sent for Priya." |
|
Close a study
Once a study hits its participant target, the MCP gives you a way to check on it and close it out.
With the MCP connected, you can:
Check whether a study has hit quota
Approve closing the study
What you want to do | Example prompt | Tool |
|---|---|---|
Approve closing a study | "Approve closing the cookware study." |
|
Security and privacy
Permission-bound access
The Rally MCP operates entirely within the permission boundaries of the authenticated Rally user. It does not have, and cannot obtain, access to any data that the user itself cannot access through the Rally platform directly. If a piece of data is restricted from your Rally account, it is equally restricted when accessed through the MCP.
Revocable at any time
OAuth sessions can be revoked from your Rally account settings whenever you choose.
Deactivating a user within Rally will automatically revoke MCP permissions.
Troubleshooting
OAuth sign-in doesn't complete
Make sure your browser is allowing pop-ups for your AI client. Some clients open the sign-in page in a new tab or window. If the page doesn't appear, try restarting your client.
"Unauthorized" or 401 errors
Try disconnecting and reconnecting the server in your client to start a new sign-in.
Connection times out
Verify you're using the correct URL: https://mcp.rallyuxr.com/mcp. The trailing /mcp path is required.
Tools aren't showing up
After connecting, it may take a moment for your client to discover the available tools. Try sending a message like "ping Rally" or "search my studies" to trigger tool discovery.