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/mcp

Claude (Desktop and claude.ai)

1. Go to Customize > Connectors > Click + > Add custom connector.

2. Enter the Rally MCP URL: https://mcp.rallyuxr.com/mcp

3. Click Add. Claude will open your browser to sign in to Rally.

4. 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

1. Open your MCP configuration file (.cursor/mcp.json in your project, or your user-level MCP settings).

2. Add the following entry:

{
  "mcpServers": {
    "rally": {
      "url": "https://mcp.rallyuxr.com/mcp"
    }
  }
}

3. 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/mcp

Claude 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

Study design and setup

build_study - Creates a new study or updates one that already exists - name, description, incentive, audience, consent, scheduling setup, quotas - and works on drafts as well as studies that have already gone live, though individual fields lock in place once recruiting activity starts.

• Try: "Set up a new interview study for our checkout redesign."

build_screener - Writes or revises the qualifying questions for an interview or unmoderated-test study, including which answers qualify or disqualify someone, before the study goes live.

• Try: "Add a screener question about how often they shop online."

build_survey - Writes or revises a survey study's own questions - the ones every participant answers, not qualification criteria - before the study goes live.

• Try: "Write survey questions about our new pricing page."

search_survey_connectors - Lists which outside survey tools (like Qualtrics, SurveyMonkey, or Typeform) your workspace has connected, and finds a specific survey in one of them by name, for studies whose questions live outside Rally's own builder.

• Try: "Which Qualtrics survey should I link to this study?"

search_properties - Looks up the fields Rally tracks about people - built-in ones like email, plus any custom ones your workspace has added - including their possible values.

• Try: "Do we track company size as a property?"

map_question_properties - Automatically links a study's screener or survey answers to matching person fields already in your workspace, so responses get saved onto people's profiles; it only maps to fields that already exist, it won't create new ones.

• Try: "Map these screener answers to person properties."

get_consent_forms - Lists the consent forms available in your workspace, so you can pick one to attach to a study.

• Try: "What consent forms do we have set up?"

search_studies - Looks up studies across your workspace - active, paused, closed, or drafts that never launched - along with each one's recruiting progress.

• Try: "Show me all my active studies."

get_study - Pulls up a study's full configuration and current recruiting numbers - how many have been reached, applied, or booked - in one place.

• Try: "What's the current status of my onboarding study?"

show_study_card - Displays a visual summary of a draft study's setup - audience, screener, scheduling, messages, incentive - so you can review it before going further.

• Try: "Show me the study card for this draft."

Recruitment planning

check_recruiting_feasibility - Checks whether enough matching people already exist in your workspace, and if not, whether a paid external panel could fill the gap - the first step before deciding how to recruit for a study.

• Try: "Can I find 20 designers with a full seat to interview?"

build_recruiting - Lines up recruiting for a study that isn't live yet - either an invitation schedule with a preview of exactly what participants will see, or turning on the study's public sign-up link - but this only prepares the plan; someone still has to approve it before anything goes out.

• Try: "Set up recruiting to invite this list of people."

start_recruiting - Takes a reviewed recruiting plan live, moving the study from draft to active and queuing the first invitations (or switching on the sign-up link) - only after a person has reviewed and approved the plan, never on its own. For a paid external panel, this instead publishes the study without spending anything; reserving the money still happens as a separate confirmation.

• Try: "Go ahead and launch recruiting for this study."

search_external_panel_targeting_options - Shows exactly what a paid external panel (Respondent or User Interviews) can target - job titles, industries, countries, age ranges - and the exact values to use when setting that targeting.

• Try: "What countries can this panel recruit from?"

build_external_panel_audience - Sets who a paid external panel should recruit - audience type, participant time commitment, targeting criteria - and returns a running cost estimate as you adjust it; it doesn't launch anything or reserve any money on its own.

• Try: "Target senior product managers in fintech for this panel."

review_external_panel_launch - Gives the final itemized cost quote and readiness check for a paid external-panel study right before launch. It can't start recruiting by itself - you still confirm and reserve funds separately.

• Try: "What will this panel study cost, and are we ready to launch?"

People and participants

search_people - Searches and filters everyone in your workspace's participant pool by almost any trait - role, location, contact history, opt-out status - and saves the result as a reusable selection.

• Try: "Find designers in San Francisco who speak Spanish."

search_participants - Lists the people already enrolled in one study and where each stands - invited, screening, scheduled, done - with filters like consent status or quota group.

• Try: "Who's still pending an incentive on this study?"

get_study_participant - Pulls up everything about one person's participation in a study - their screener answers, approval status, incentives, and most recent interview booking.

• Try: "Show me this participant's full details."

get_person - Pulls up one person's full profile across your workspace - contact info, custom properties, notes, and past participation ratings.

• Try: "Show me everything we know about this person."

add_people_to_study - Adds a saved selection or specific people onto a study's roster, on a draft or an already-live study, optionally straight into a quota group.

• Try: "Add these 20 people to the study."

update_participants - Moves participants between quota groups on a live study, or takes them out of one, to rebalance recruiting mid-study.

• Try: "Move these three participants into the Enterprise quota."

import_people - Imports a list of people you paste or type in directly into one of your workspace's populations; this runs as a background job you check on rather than finishing instantly.

• Try: "Import this list of 40 people into our Enterprise population."

prepare_file_upload - Sets up the upload slot for a people-list file so its bytes can reach Rally - the first step before importing a spreadsheet of people.

• Try: "I want to upload a CSV of participants - how do I start?"

import_people_from_upload - Finishes importing a people list from a file already staged with a prior upload step, into one of your workspace's populations.

• Try: "Import the CSV I just uploaded into our panel."

create_population - Creates a new named group of people (a population or panel) to import people into, or to use as a public sign-up destination.

• Try: "Create a new population for our beta testers."

search_populations - Looks up your workspace's existing named people groups by name, so you can pick one as an import or recruiting destination.

• Try: "Do we have a population called Enterprise Panel?"

append_note_to_participant - Adds a note to a participant's record in a study, underneath whatever's already there - it can't replace or clear existing notes.

• Try: "Note that this participant asked to reschedule twice."

Email and outreach

draft_message - Composes a one-off, ad-hoc email (like a thank-you note) for a specific group of participants without touching the study's saved templates; save it, then send it separately.

• Try: "Draft a thank-you email for everyone who finished last week."

preview_message - Shows exactly what a study's email will look like to participants - rendered with a real person's name and details when you give one - without sending or changing anything.

• Try: "Show me what the invitation email looks like."

send_message - Proposes sending an invitation, or a drafted one-off message, to a specific group of participants; nothing actually goes out until a person reviews and approves it in Rally.

• Try: "Send the booking invite to these five people."

edit_study_message_template - Rewrites one of a study's permanent emails - the invitation, screener invite, reminders, and so on - for future sends; it never changes a message that has already gone out.

• Try: "Update the wording on our interview reminder email."

list_study_message_templates - Lists every email and text-reminder template configured on a study, so you know what it sends before editing or previewing one.

• Try: "What emails does this study send?"

get_study_message_tokens - Shows the dynamic placeholders - a participant's name, a booking link - available for a study's email, so copy can be personalized instead of hardcoded.

• Try: "What personalization tokens can I use in this email?"

search_email_sender_addresses - Lists the personal and team email addresses you're allowed to send study emails from.

• Try: "What sender addresses can I use for this study?"

list_message_campaigns - Lists every email send a study has made, with delivery, open, and bounce counts for each one.

• Try: "How did yesterday's invitation batch perform?"

pause_message_campaign - Temporarily stops one specific email send from continuing, without touching the rest of the study; it can be resumed later.

• Try: "Pause the reminder campaign for now."

resume_message_campaign - Restarts a paused email send from where it left off.

• Try: "Resume that campaign I paused earlier."

cancel_message_campaign - Permanently stops one email send so its remaining invitations never go out - this can't be undone, unlike pausing.

• Try: "Cancel that invitation campaign for good."

get_study_email_activity - Reports overall email performance for a study - sent, delivered, opened, bounced - broken down by email type.

• Try: "How are this study's emails performing overall?"

get_participant_email_activity - Shows every email one participant was sent for a study, and whether it was opened or bounced.

• Try: "Did Jane ever open our invitation?"

Screening and qualification

set_screener_qualification - Marks one or more participants as qualified or not qualified on a study's screener, overriding an automatic result if needed; it doesn't send anything or touch incentives.

• Try: "Mark these three participants as qualified."

decide_external_panel_applicants - Approves or rejects applicants waiting for review on a paid external-panel study; approving automatically invites them through the panel provider.

• Try: "Approve these five panel applicants."

Scheduling and interviews

search_interviews - Looks up interview sessions across studies - today's, this week's, a specific study's - with who's attending and their status.

• Try: "What interviews do I have today?"

get_interview - Pulls up full details on one interview - attendees, recording status, an AI summary, and a link to watch it if it was recorded.

• Try: "Show me the details for this interview."

schedule_interview - Books a new one-on-one interview for a participant already on the study, with you as host.

• Try: "Book an interview with this participant for Tuesday at 2pm."

reschedule_interview - Moves a booked one-on-one interview to a new time and notifies the participant; it doesn't apply to group or multi-session interviews.

• Try: "Move this interview to Thursday afternoon."

cancel_interview - Cancels a booked one-on-one interview and notifies everyone involved; it doesn't apply to group or multi-session interviews.

• Try: "Cancel my interview with this participant."

search_availability - Shows a study's open interview time slots across its hosts, for a given date range.

• Try: "What times are open for interviews next week?"

get_my_availability - Shows your own default interview hours and booking limits, the ones that apply across every study that uses your personal calendar.

• Try: "What are my current interview hours set to?"

update_my_availability - Changes your own default interview hours, weekly booking caps, or calendar-conflict rules, across every study that uses your personal availability.

• Try: "Open up my Tuesday afternoons for interviews."

mark_attendance - Records whether a participant showed up or no-showed for a specific interview session.

• Try: "Mark this participant as a no-show."

change_interview_host - Swaps the host on an already-booked interview without changing the time.

• Try: "Have someone else host this interview instead of me."

add_interview_guest - Adds an extra live attendee or a silent observer to a scheduled one-on-one interview.

• Try: "Add my manager as a silent observer on this call."

Incentives

log_custom_incentive - Records that a non-cash incentive (swag, credits, and the like) was given to participants - Rally just tracks that it happened; the actual reward is handled outside Rally.

• Try: "Log that these participants received their gift bags."

resend_incentive - Re-sends a participant's gift-card or redemption email if they say they never got it.

• Try: "Resend the incentive email to this participant."

cancel_incentive - Cancels a participant's incentive before it's been claimed.

• Try: "Cancel the incentive for this participant."

Reading results

get_raw_transcript - Retrieves the full word-for-word transcript of a recorded interview, with speaker labels and timestamps.

• Try: "Get me the full transcript from this interview."

search_study_responses - Shows what people answered on a study's screener or survey, question by question.

• Try: "Show me the survey responses so far."

Managing a study's life

pause_study - Temporarily stops a study's recruiting and new participants, while anything already booked or in progress carries on; reversible.

• Try: "Pause recruiting on this study for now."

resume_study - Restarts a paused study's recruiting.

• Try: "Resume recruiting on this study."

close_study - Permanently stops recruiting on a study and cancels its active outreach - already-booked participation still finishes out, but this can't be undone.

• Try: "Close out this study, we're done recruiting."

Across your workspace

These aren't part of any single study's lifecycle - they work at the workspace level, across studies, plus the playbooks that shape how a common research task gets run.

get_current_user - Tells you who you are in Rally - your role, team, and workspace - useful for resolving "my studies" style questions.

• Try: "Which team am I on in Rally?"

search_users - Looks up your teammates by name or email, to find who to assign as an interview host, guest, or observer.

• Try: "Who on my team could host this interview?"

search_pending_decisions - Lists what's still waiting on your approval for a study - like a recruiting round ready to review - with a link to act on it.

• Try: "What do I still need to approve on this study?"

get_research_playbook - Loads Rally's own step-by-step method for a common research task, like prepping for an interview or designing a screener, so it gets done the way Rally recommends.

• Try: "Walk me through prepping for this interview."

Security and privacy

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.