# Rally MCP connector The Rally connector lets Claude, ChatGPT, Cursor, or any MCP client search your studies, build screeners, check recruiting, and manage participants in Rally, with each person's own access and every action logged. Source: https://elaichi.ai/connectors/rally-uxr/ ## Facts | | | | --- | --- | | Application | Rally | | Category | Survey | | AI tools | 68 | | Authentication | Connects over OAuth | | Bring your own OAuth app | No | | Native MCP | Yes. Rally builds and runs this MCP server. Elaichi adds sign-in, access controls and an audit log on top | | Support for its tools | help.rallyuxr.com/en | | MCP endpoint | https://api.elaichi.ai/mcp | | Works with | Claude, ChatGPT, Cursor, any MCP client, and the Elaichi Agent | | Tools advertised by name | No. Connected tools are never listed one by one, however few there are. The endpoint advertises `search_tools` and `execute_tool` instead | ## What you can ask once Rally is connected - Check recruiting feasibility for 12 enterprise admins in our onboarding study - Add past participants who mentioned pricing to the checkout study - Draft a screener for the mobile navigation study from our usual template ## Connect Rally in Elaichi This happens once for the organization, before any client is involved. 1. Open Connections, choose Add connection, and pick Rally. 2. Optionally set Share with, then press Connect. 3. Approve it in Rally. Rally's own window opens. Whoever approves it decides what this connection can reach. Credentials are vaulted and nobody, including the AI, reads them back. The connection becomes a toolbox immediately, so you can curate which Rally tools are exposed, rename them, or freeze arguments before anyone points a client at it. ## Rally MCP connector for Claude Endpoint: https://api.elaichi.ai/mcp 1. Open Customize, then Connectors. 2. Press Add. 3. Name it, paste the MCP server URL, then Continue. 4. Sign in and approve. On Team and Enterprise, an Owner adds it once. Everyone else turns it on for themselves. ## Rally MCP connector for ChatGPT Endpoint: https://api.elaichi.ai/mcp 1. Open Plugins, then press the + button. 2. Name it and paste the endpoint into Server URL. 3. Leave Authentication on OAuth, then tick the risk acknowledgement. 4. Press Create, then sign in and approve. Works on the web today. The plugin directory lives at chatgpt.com/plugins. ## Rally MCP connector for Cursor Endpoint: https://api.elaichi.ai/mcp 1. Open `~/.cursor/mcp.json`. 2. Add the endpoint under `mcpServers`. 3. Reload Cursor, then sign in and approve. Set up per machine, so repeat it on each computer you work from. ## Connect Rally to any MCP client Endpoint: https://api.elaichi.ai/mcp 1. Add the endpoint as a remote MCP server. 2. Sign in and approve. The Elaichi Agent already has these tools, with nothing to set up. ## What the consent screen decides Only Read is granted by default, which is not enough to call a Rally tool. Over MCP there is no trusted place to confirm a write in the moment, so the consent screen is the standing approval rather than a formality. Grant Read and Run tools. Think hard before granting Delete, which reaches into connected apps and cannot be undone. ## What teams do with Rally through Elaichi ### Set up a study before the kickoff UX Research. Describe what you want to learn and have a study, screener, and survey drafted in Rally from one of your templates. You review it before anything goes out to participants. ### Check feasibility before promising a date Research Ops. Ask whether Rally can recruit enough participants who match your criteria before you commit to a timeline. Once the numbers look right, start recruiting from the same conversation. ### Reuse past participants for a new question Product. Search people in Rally by what they took part in before and add the right ones to the new study, without rebuilding a list by hand. ### Build an external panel audience Design. Say who you need to hear from and have the external panel targeting options in Rally searched, the audience built, and the launch review handed to you to sign off. ### Import a customer list for a survey Marketing. Hand over a list of customers and have them imported into Rally as people, then added to the right study ready for the screener. ### Prepare for an interview in one ask Customer Insights. Before a session, pull the participant's record from Rally, which studies they have joined, and the consent forms attached, so nothing is missed on the call. ## Elaichi vs Zapier MCP vs Composio for Rally All three can connect Rally to an AI assistant, and all three have admin controls. They differ in where access lives and how you pay. | What to check | Elaichi | Zapier MCP | Composio | | --- | --- | --- | --- | | Where the AI connects | One address for the whole organization. Endpoint: https://api.elaichi.ai/mcp | A server per member, created at sign-in. | An MCP endpoint per team, or an SDK. | | Control over Rally tools | Allow or restrict single Rally tools, per role or user. | App and action restrictions on the account. | Role permissions, down to the action. | | Record of calls | One audit entry per Rally call. | A History tab of tool calls. | A log of every tool call. | | Single sign-on | SAML or OIDC, plus SCIM, on Gold. | SAML on Enterprise. | SAML and OIDC on Enterprise. | | Price | $15 per user per month. | 2 tasks per successful call. | Billed per tool call. | Sources: Zapier MCP [docs](https://docs.zapier.com/mcp/get-started/quickstart), [security](https://docs.zapier.com/mcp/manage/security), [usage](https://docs.zapier.com/mcp/features/usage); Composio [docs](https://docs.composio.dev/docs/composio-connect), [gateway](https://composio.dev/mcp-gateway), [enterprise](https://composio.dev/enterprise), [pricing](https://composio.dev/pricing). Checked September 2026. Longer take: [Zapier MCP alternative](/blog/zapier-mcp-alternative/) and [when you don't need an MCP gateway](/blog/when-you-dont-need-an-mcp-gateway/). ## Frequently asked questions ### How do I connect Rally to Claude? Connect Rally in Elaichi first: pick Rally from the catalog and sign in to your Rally account over OAuth, with no OAuth application to register and no client ID or secret to generate. Then in Claude go to Customize, then Connectors, then Add, and paste https://api.elaichi.ai/mcp. Claude signs you in through Elaichi and Rally is available in your next conversation. ### Does Rally work with ChatGPT and Cursor as well as Claude? Yes. Rally is connected once in Elaichi, and the same endpoint, https://api.elaichi.ai/mcp, works in Claude, ChatGPT, Cursor, any MCP client, and the Elaichi Agent. There is nothing to set up again for each client. ### What can an AI agent actually do with my Rally data? An agent can search your Rally studies and templates, draft a study, screener, or survey, check whether a recruit is feasible, start recruiting, and build an external panel audience for you to review. It can also search people and participants, add or remove them from a study, import a list, and pull up consent forms. Short, specific asks such as "find participants from the checkout study" work better in Rally than long paragraphs. ### Does connecting Rally give the AI access to every study and participant? No. Every call into Rally runs as the person who signed in, so the agent sees the studies, participants, and people that person already has access to in Rally. Elaichi can narrow that further with roles and restrictions, and it can never widen it beyond what Rally itself allows. ### Can my team share one Rally connection? Yes. One person connects Rally in Elaichi and shares the connection with a team, and nobody else ever handles a credential. Each teammate still signs in to Elaichi as themselves, so every action in Rally is logged under their own name, not the name of the person who connected it. ### Can I stop an agent from removing participants or changing studies in Rally? Yes. Restrictions in Elaichi work per action, so you can allow searching studies and people in Rally while blocking removing participants, starting recruiting, or importing lists. A restricted action is never advertised to Claude, ChatGPT, or any other client, so no prompt can reach it. ### What happens to a Rally connection when someone leaves? Offboarding a person in Elaichi ends their access to Rally through every client at once. A Rally connection shared with a team keeps working for everyone else. If you disconnect Rally in Elaichi, it is removed from Claude, ChatGPT, Cursor, and every other client in one step. ### Does the Rally MCP connector work with Gemini, Codex, Claude Code or other MCP clients? Yes. Rally is reached over the same MCP endpoint every client uses, so anything that speaks MCP can call it — Gemini, Codex, Claude Code, Windsurf, Cline, Zed and OpenCode among them — alongside Claude, ChatGPT, Cursor, and the Elaichi Agent. The tools on offer and the access behind them are identical whichever client asks. Only the setup screen differs. ### Is Elaichi an alternative to Zapier MCP for Rally? Yes. Both let Claude, ChatGPT or Cursor use Rally. Zapier MCP fits a team that already automates in Zapier, since each person signs in and acts as themselves in that account. Elaichi fits when IT wants one address for the whole company, per-tool rules by role, and a record of every Rally call. ### How is Elaichi different from Composio for Rally? Composio gives AI agents tools and sign-in handling across 1,000+ apps, for developers building agents or people using an assistant, billed per tool call. Elaichi gives a company's own people governed access to Rally: one address, restrictions per role or user, and $15 per user per month. Both have role permissions and a log of every call. ## All 68 Rally tools Every tool below is callable through https://api.elaichi.ai/mcp once Rally is connected, subject to the toolbox it is in and the restrictions on the caller. - **Build study** (Action). Creates a new study or edits an existing one, draft or live, and hands back its whole configuration - name, incentive, target, consent, and more. On a live study most fields still change, but anything recruiting has already touched locks progressively as it goes (the incentive… - **Build screener** (Action). Writes or revises the qualifying questions for an interview or unmoderated-test study, applying feedback one change at a time, and returns the full question list with its qualify/disqualify logic. Survey studies use survey questions instead - screeners don't apply there. - **Build survey** (Action). Writes or revises a survey study's own questions - the ones every participant answers, not qualification criteria - and returns the resulting set. Only applies when the survey's questions live in Rally's own builder; a survey handed off to an external tool is edited there… - **Search survey connectors** (Search). Lists which external survey tools (Qualtrics, SurveyMonkey, Typeform) this workspace has connected, or finds a specific survey within one of them, for a survey study whose questions live outside Rally. - **Map question properties** (Action). Matches a screener or survey's questions to existing fields on people's profiles, so answers are saved there automatically. It only connects to fields the workspace already has - it never creates new ones. - **Search properties** (Search). Looks up the custom and built-in fields the workspace tracks about people, including what values each one allows. Useful before writing questions or personalizing outreach. - **Get consent forms** (Get). Lists the consent forms available in the workspace, so one can be attached to a study. - **Search study templates** (Search). Lists the templates a study can be created from, and whether each belongs to the whole workspace or one team. - **Search studies** (Search). Searches every study you can access - active, paused, closed, or never launched - and returns each one's recruiting progress. - **Get study** (Get). Pulls the full detail on one study: its configuration, screener, status, and recruiting progress. - **Check recruiting feasibility** (Action). Checks whether a described audience can be found in the workspace's own people, returning a match estimate and a recommendation - recruit from the panel, or import a list because the data isn't there yet. Where a paid external panel is available and could help, it's surfaced… - **Build recruiting** (Action). Turns a chosen selection of people into a plan to review before anything moves - the daily send size and the invitation exactly as participants will see it - for a study recruiting from the workspace's own people or its public sign-up link. This planning step doesn't apply to… - **Start recruiting** (Start). Takes an approved plan live: adds the selected people and queues the first round, or switches a sign-up link on. Nothing sends until that first round is separately approved. For a paid external panel, this is what publishes the study once its cost sheet is confirmed. - **Build external panel audience** (Action). Sets who a paid external panel (Respondent or User Interviews) should recruit - the audience type, participant time commitment, and targeting criteria - and returns a running cost estimate. Locks once recruiting has started. Only User Interviews gives a reach estimate before… - **Search external panel targeting options** (Search). Looks up exactly what a paid external panel can target and the specific options available for each criterion, so targeting can be set precisely. - **Review external panel launch** (Action). The final check before launching a paid external panel: whether it's ready, what's blocking it, and the full itemized cost. This doesn't launch anything itself - going live still needs confirmation on Rally's cost sheet. - **Search people** (Search). Searches the workspace's people from a plain description and returns how many matched, which fields it filtered on, and a sample. While recruiting for a specific study, the count narrows to who can actually be added to it. - **Search participants** (Search). Lists a study's participants and where each stands - invited, screening, done, and so on - with filters for stage, status, or quota group. - **Get person** (Get). Pulls one person's full profile: contact info, custom field values, notes, and past study ratings. - **Get study participant** (Get). Pulls one participant's full picture on a study: screener answers, consent status, quota group, and their latest interview booking. - **Add people to study** (Add). Adds people to a study, draft or live, from a saved selection or a specific list. Nothing is sent and no outreach starts - they simply arrive ready to be reached. - **Remove participants from study** (Delete). Takes someone off a study's participant list. Only works for people who haven't engaged yet or whose involvement ended without a result - anyone who has gone further stays, since removing them would take their research record along too. - **Import people** (Import). Imports people - pasted rows or a staged file - into a chosen population, optionally straight onto a study. Runs as a background job rather than finishing instantly, and newly imported people may not show up in a search right away. - **Import people from upload** (Import). An older, narrower way to import a staged file of people into a population; the current import tool covers this case too. Same background-job behavior - it may take a moment, and a search run right after can miss some of the new people. - **Prepare file upload** (Upload). The first step in importing people from a file already on your computer: stages it so its contents can then be imported. - **Create population** (Create). Creates a new named group of people to import into or to serve as the destination for a public sign-up link. - **Search populations** (Search). Looks up an existing named population or panel by name. - **Append note to participant** (Action). Adds a note to a participant, always on top of what's already there and never replacing it. - **Update participants** (Update). Moves participants between a live study's quota groups, or removes someone from their group, once quotas are set up. Applies immediately, no approval needed. - **Draft message** (Action). Composes a one-off message - like a thank-you note - for a specific group on a live study, without touching the study's saved templates, and returns a preview to review before sending. Not available for a study recruiting through a paid external panel, where the provider owns… - **Preview message** (Action). Renders a study's saved email, or a drafted one-off message, exactly as a participant would see it - with their real name and details when one is specified. Doesn't send or change anything. - **Send message** (Send). Proposes sending the study's invitation, or a drafted one-off message, to a specific group. This never sends anything directly - it creates a decision that still needs approval in Rally before anything goes out. - **Edit study message template** (Action). Rewrites one of a study's saved emails - invitation, screener invite, booking confirmation, reminders, and more - and returns it rendered as participants will see it. Applies to future sends on live studies too, but never changes a message that's already gone out or one… - **List study message templates** (List). Lists every saved email and text reminder configured on a study. - **Get study message tokens** (Get). Looks up the dynamic placeholders - names, dates, incentive amounts, links - available for a given study email, so edits use them instead of hardcoded text. - **Search email sender addresses** (Search). Lists the personal and team addresses available to send from. - **List message campaigns** (List). Lists a study's email sends - invitations, screener follow-ups, and more - most recent first, with delivery counts for each. - **Pause message campaign** (Pause). Pauses one email send so it stops going out further, without affecting the rest of the study. Reversible. - **Resume message campaign** (Resume). Picks a paused email send back up where it left off. - **Cancel message campaign** (Cancel). Permanently drops an email send's remaining, not-yet-sent invitations - this can't be undone, unlike pausing. - **Get study email activity** (Get). Reports everything a study has emailed and what's still waiting to go out, broken down by purpose - invitations, screening, scheduling, incentives - with delivery and open counts. An email with no confirmed opens may still have been opened; only a confirmed open counts as one. - **Get participant email activity** (Get). Reports one participant's full email history on a study - what was sent, delivered, opened, or bounced. - **Set screener qualification** (Set). Marks one or many participants qualified or not qualified, including overriding what the screener itself decided. Applies immediately with no approval step, since it's easy to reverse - it only sets qualification, and doesn't notify anyone or touch scheduling or incentives. - **Decide external panel applicants** (Action). Approves or rejects applicants waiting for review on a study recruiting through a paid external panel; approving invites them at the provider. Always previews the decisions first and asks for confirmation before committing. - **Search interviews** (Search). Finds interview sessions across your team, one person's day, or a single study's whole schedule. A day's results include cancelled and no-show sessions along with completed ones. - **Get interview** (Get). Pulls the full detail on one interview: who's attending, the observer room, and any recording, summary, or transcript access. - **Search availability** (Search). Finds a study's open interview slots and which hosts are free in each. - **Schedule interview** (Action). Books a new interview for a participant already on a study, with you as host, previewing the booking before it's confirmed. - **Reschedule interview** (Action). Moves a booked interview to a new time, previewing the change and open slots first, and notifies the participant once confirmed. - **Cancel interview** (Cancel). Cancels a booked interview and notifies everyone involved. - ...and 18 more tools. Call `tools/list` via the MCP endpoint, or see the full catalog via the API, for the complete set.