tremendous-mcp
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@tremendous-mcp Send a $25 Amazon gift card to jane@example.com"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
tremendous-mcp
An MCP server for the Tremendous rewards API. Use it to send rewards from an AI assistant, see who has received rewards, and manage orders that need approval.
The server runs on your computer over stdio. It works with Claude Desktop, Claude Code and other MCP clients. Two tools also show interactive views in clients that support MCP Apps.
This project is not affiliated with Tremendous.
Features
Send rewards to one or more recipients (email, SMS or link delivery), with a campaign or a list of products.
See who received rewards: one summary for each recipient (number of rewards, total, last date), with filters for email, name, dates, campaign and delivery status.
Fix failed deliveries: resend a reward (optionally to a corrected email or phone), or cancel it.
Approve or reject orders in
PENDING APPROVAL.Read the account: organization, funding sources and balance, product catalog, campaigns, orders.
Interactive views (MCP Apps): a rewards dashboard and an editable send form.
Sandbox by default: the server uses the Tremendous sandbox (fake money) until you set
TREMENDOUS_ENV=production.
Related MCP server: Africa’s Talking MCP
Requirements
Node.js 20.11 or later.
A Tremendous account with admin access, to register an OAuth app.
Optional: the 1Password CLI, if you want to keep the client secret out of your shell environment.
Setup
1. Register a Tremendous OAuth app
Start in the sandbox: https://testflight.tremendous.com.
Go to Team settings → Developers → Developer apps and click Register app.
Set the redirect URI to
https://localhost:8787/callback. Tremendous accepts onlyhttpsredirect URIs. No server has to run at this address (see step 3).Keep the client ID and the client secret.
For production, register a second app at https://api.tremendous.com.
2. Install and build
git clone https://github.com/Bryan21B/tremendous-mcp.git
cd tremendous-mcp
npm install
npm run build3. Log in
Give the client credentials to the login script in one of these two ways.
Option A: environment variables:
export TREMENDOUS_CLIENT_ID=...
export TREMENDOUS_CLIENT_SECRET=...
npm run loginOption B: 1Password references:
cp .env.op.example .env.op # then edit the op:// paths
op run --env-file=.env.op -- npm run loginThe login opens your browser:
Log in to Tremendous and allow access.
Tremendous sends the browser to
https://localhost:8787/callback. The script listens there with a self-signed certificate (it makes one withopensslthe first time, in~/.config/tremendous-mcp/tls/). The browser warns that the connection is not private: click Advanced, then Proceed to localhost.The page says "Code received", and the script continues by itself.
If that does not work (for example, openssl is not installed), copy the callback address, which starts with https://localhost:8787/callback?code=, go back to the terminal and press Enter. The script reads the address from the clipboard, or you can paste it. Chrome can keep the Tremendous address in the address bar when the redirect fails. In that case, find the callback address in chrome://history.
The script then shows "Connected to: ".
The script writes the tokens to ~/.config/tremendous-mcp/tokens.<env>.json, with mode 0600. Tremendous refresh tokens are single-use. The server refreshes them under a file lock, so two clients can run the server at the same time.
Reading the clipboard uses
pbpaste(macOS). On other systems, paste the address into the terminal.
4. Add the server to your MCP client
The server needs the client credentials at run time, because it refreshes the tokens.
Claude Code
claude mcp add tremendous -s user \
-e TREMENDOUS_ENV=sandbox \
-e TREMENDOUS_CLIENT_ID=... \
-e TREMENDOUS_CLIENT_SECRET=... \
-- node /absolute/path/to/tremendous-mcp/build/index.jsClaude Desktop (claude_desktop_config.json, in mcpServers)
"tremendous": {
"command": "node",
"args": ["/absolute/path/to/tremendous-mcp/build/index.js"],
"env": {
"TREMENDOUS_ENV": "sandbox",
"TREMENDOUS_CLIENT_ID": "...",
"TREMENDOUS_CLIENT_SECRET": "..."
}
}With 1Password, do not put the secrets in the configuration file. Launch through op run instead:
"tremendous": {
"command": "op",
"args": ["run", "--env-file=/absolute/path/to/tremendous-mcp/.env.op", "--",
"node", "/absolute/path/to/tremendous-mcp/build/index.js"],
"env": { "TREMENDOUS_ENV": "sandbox" }
}Claude Desktop does not use your shell PATH. If it cannot find op or node, use the full path (for example /opt/homebrew/bin/op). Restart Claude Desktop after you change the file.
Tools
Tool | Type | What it does |
| read | Organization, environment, funding sources and balance |
| read | Balance, cards, bank accounts, invoice |
| read | Reward catalog. Filter by country, currency, name and category |
| read | Campaigns (reward templates) |
| read | Orders. Filter by date, campaign, |
| read | One reward and its delivery status |
| read + view | Who received rewards. Filter by email, name, dates, campaign and delivery status |
| read + view | Check a batch and show the send form. This tool sends nothing |
| write | Send rewards. Makes one order for each recipient |
| write | Resend after a delivery failure |
| write | Cancel a reward that is not redeemed |
| write | New redemption link (LINK rewards only). Anyone with the link can redeem the reward |
| write | Orders in |
The typical flow to send rewards is review_rewards, then the user checks the draft, then send_rewards with the same draft_id.
Interactive views (MCP Apps)
Rewards dashboard (
list_rewards): totals, search, delivery-status filters, a "by recipient" or "all rewards" table, Resend and Cancel buttons on failed rewards, and Load more for older rewards.Send form (
review_rewards): edit the recipients, amounts, campaign, funding source, delivery method and message, then click Send and Confirm. The form then shows the result for each recipient.
All tools also return a text summary, for clients that do not show the views.
Safety
Sandbox first. The default environment is the sandbox. Each tool result shows
SANDBOXorPRODUCTION.Write tools are marked. Tools that spend money or cannot be undone have
destructiveHint: true. Most clients then ask you before each call. This does not occur if you select "Always allow". Do not select "Always allow" for the write tools.Buttons in the views call tools directly. Your client may not ask you first. In the send form, the two clicks (Send, then Confirm) are the only check.
No double payments on retry.
send_rewardsgives each reward the Tremendousexternal_idmcp-<draft_id>-<hash of the recipient>. The hash comes from the email, else the phone, else the name. If you send the same draft again, Tremendous returns the existing order for each recipient who was already paid. This is also true if you remove, reorder or add recipients. If you change the amount for a recipient who was already paid, Tremendous returns a 409 conflict and does not make a second payment.Insufficient funds stop the batch. After a
402response, the server does not try the remaining recipients.No step-up authentication. The OAuth login gives full access within the granted scope.
Configuration
Variable | Default | Use |
|
|
|
| none | OAuth app credentials |
|
| OAuth scopes |
|
| Must be the same as the redirect URI of the app |
|
| Folder for the token files |
Use production
Register an app at https://api.tremendous.com with the same redirect URI.
Log in with the production credentials:
TREMENDOUS_ENV=production npm run login.Set
TREMENDOUS_ENV=productionin your MCP client configuration.
The sandbox and production use different token files, so you can keep both.
Notes and limitations
Recipient search scans rewards. The Tremendous API cannot filter rewards by recipient.
list_rewardsreads up tomax_scanrewards (default 5,000, 500 for each request) and filters them. With a date range or a campaign, the tool reads orders instead, because the API can filter orders by date and campaign. If the result is truncated, call the tool again withoffset=next_offset, or click Load more in the dashboard.One order for each reward. The Tremendous API requires this. A batch of N recipients makes N requests, one after the other.
Not verified yet:
PKCE support. The login does not use PKCE.
Whether the
defaultscope is sufficient for order approvals.
Development
Command | What it does |
| Compile the server to |
| Unit and contract tests with a fake Tremendous API (no network) |
| Type-check the server and the views |
| Biome lint and format check ( |
| Lint, typecheck, tests and build (what CI and the pre-push hook run) |
| Interactive OAuth login |
| Live test against the sandbox only: sends a 1.00 reward to |
Project layout:
src/
index.ts stdio entry point
server.ts MCP server: tools and UI resources
tools/read.ts read-only tools (including the two view tools)
tools/write.ts tools that spend money or cannot be undone
rewards-query.ts paging and filtering for list_rewards
client.ts REST client: refresh on 401, backoff on 429, readable errors
token-store.ts token file, locked single-use refresh
login.ts OAuth login script
ui/ MCP Apps views (plain TypeScript and CSS, bundled with Vite)
test/ Vitest tests and a fake Tremendous APIReleases and versioning
This project uses Semantic Versioning. The version in package.json is the single source of truth. The server reports it to MCP clients, and the views use it too.
Releases are automatic. On each push to main, CI runs the checks. If they pass, semantic-release reads the commit messages since the last tag. It then sets the next version, updates CHANGELOG.md and package.json, tags v<version> and makes the GitHub release.
Commit messages must follow Conventional Commits. The type sets the version:
Commit type | Release |
| minor (0.x.0) |
| patch (0.x.y) |
| minor while the version is below 1.0.0 |
| no release |
The public interface is the tool names, their input fields and their results. A change that breaks it is a breaking change.
Git hooks
npm install installs these hooks (husky):
commit-msg: rejects a subject that is not a Conventional Commit.
pre-commit: Biome on the staged files, then the typecheck.
pre-push: a secret scan of the commits to push, then
npm run check(lint, typecheck, tests, build).
License
Available Tools
16 toolsapprove_orderApprove orderADestructive
Approve an order in status PENDING APPROVAL so Tremendous executes it and sends the reward(s). Needs "Allow approvals via API" in Tremendous Team settings → Order approvals, otherwise Tremendous answers 403. Use list_orders with status "PENDING APPROVAL" to find them.
Inputs: id (required).
cancel_rewardCancel rewardADestructive
Cancel a reward and refund its value. Tremendous only allows this for rewards that are not redeemed and not expired (typically after a delivery failure).
Inputs: id (required).
generate_reward_linkGenerate reward linkADestructive
Create a new redemption link for a LINK-delivery reward (other rewards return 403). WARNING: anyone with this link can redeem the reward. Share it only with the recipient.
Inputs: id (required).
get_accountTremendous accountARead-only
Show the connected Tremendous organization, the environment (SANDBOX or PRODUCTION) and the funding sources with their balances. Call this first to know which account you act on.
Inputs: no named parameters.
get_campaignGet campaignBRead-only
Get one campaign with its products and email settings.
Inputs: id (required).
get_orderGet orderBRead-only
Get one order with its status, payment and rewards.
Inputs: id (required).
get_rewardGet rewardBRead-only
Get one reward: recipient, value, delivery method and delivery status.
Inputs: id (required).
list_campaignsList campaignsARead-only
List Tremendous campaigns (reward templates with products, message and branding). Use a campaign_id in send_rewards.
Inputs: no named parameters.
list_funding_sourcesList funding sourcesARead-only
List the funding sources (balance, card, bank, invoice) that can pay for rewards. Balances in this list can be a little stale.
Inputs: no named parameters.
list_ordersList ordersARead-only
List orders, newest first. Filter by creation date range, campaign, external_id, or status (for example PENDING APPROVAL to find orders that wait for approval).
Inputs: limit, since, until, offset, +3 more.
list_productsList reward productsARead-only
List the reward products (gift cards, PayPal, Visa, charity, ...) in the catalog. Filter by country/currency and by a name search. Use product IDs in send_rewards.products.
Inputs: limit, search, country, category, +1 more.
list_rewardsWho received rewardsARead-only
Find which people received rewards. Filter by recipient email or name (substring), date range, campaign and delivery status. Returns one summary per recipient (count and total) and the reward rows, and shows an interactive table. Tremendous cannot filter by recipient, so this scans up to max_scan rewards (newest first); if truncated is true, call again with offset=next_offset.
Inputs: name, email, since, until, +4 more.
reject_orderReject orderADestructive
Reject an order in status PENDING APPROVAL; its rewards are not sent. Needs "Allow approvals via API" in Tremendous Team settings → Order approvals, otherwise Tremendous answers 403. Use list_orders with status "PENDING APPROVAL" to find them.
Inputs: id (required).
resend_rewardResend rewardADestructive
Resend a reward email/SMS. Tremendous only allows this after a delivery failure (delivery_status FAILED). Optionally correct the email (EMAIL rewards) or the phone (PHONE rewards), not both.
Inputs: id (required), updated_email, updated_phone.
review_rewardsReview rewards before sendingARead-only
Prepare a batch of rewards WITHOUT sending anything. Checks the recipients, amounts, campaign/products and funding source, and shows an editable review form with a Send button. Use this before send_rewards. Returns a draft_id to pass to send_rewards.
Inputs: recipients (required), message, language, products, +7 more.
send_rewardsSend rewardsADestructiveIdempotent
SEND rewards: this spends money and emails/texts the recipients. It cannot be undone once a reward is redeemed. Creates one Tremendous order per recipient. Prefer calling review_rewards first and let the user confirm. draft_id makes retries safe: with the same draft_id, a recipient who was already paid is not paid again (even if you remove, reorder or add other recipients), so after a partial failure retry with the same draft_id.
Inputs: draft_id (required), recipients (required), message, language, +8 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 16 tools
Nearly every tool targets a distinct resource plus action (approve vs reject, cancel vs resend vs generate link, review vs send). Minor overlap: get_account already surfaces funding sources with balances, which overlaps list_funding_sources, and list_rewards vs get_reward / list_orders vs get_order are close pairs but distinguished by summary vs single-record and the scan/truncation behavior is well documented.
All names are snake_case with a predictable verb_noun shape (list_*, get_*, approve_order, send_rewards), so an agent can pattern-match easily. Minor deviation is plurality: the reward-sending tools are plural (send_rewards, review_rewards) while other reward tools are singular (get_reward, cancel_reward, resend_reward), but the pattern is still readable.
16 tools is slightly above the typical 3-15 sweet spot but every tool maps to a genuine Tremendous operation (orders, rewards, campaigns, products, funding, account) without gratuitous duplication. The review/send split earns its extra tool by preventing accidental spend.
The surface covers the full reward lifecycle end-to-end: discover products/campaigns, review, send, retry, resend, regenerate links, cancel, plus order approval/rejection and account/funding context. Gaps are minor: campaigns are read-only (no create/update), and there is no dedicated order-creation or reward-detail search beyond list/get, but agents can work around these.
Maintenance
Related MCP Connectors
Send real gifts from your AI assistant: find, draft and send gifts you approve; track who redeemed.
Send real handwritten postcards, letters, notecards and gift cards from your AI assistant, preview every piece and its price first, and track QR scan results.
Secure gift, flower, occasion, reminder, approval, and growth tools for personal AI agents.
Send personalized physical gifts and letters to business contacts from AI agents
Related MCP Servers
FlicenseNot gradedqualityDmaintenanceEnables AI agents to request purchase approval from humans, receive scoped virtual cards, complete checkout, and report receipts for audit.-- AlicenseAqualityBmaintenanceEnables AI clients to check an application balance and preview or send bulk SMS and airtime, either through a hosted OAuth connection that needs no local install or via a self-hosted stdio/Cloudflare Workers deployment using your own credentials. Sending is preview-only by default and gated behind environment, recipient allowlist, and mutation opt-in settings.4MIT

Winnr MCP Serverofficial
AlicenseNot gradedqualityBmaintenanceEnables AI assistants to manage cold-email infrastructure through natural language, covering domain and mailbox provisioning, DNS setup, email warming, inbox and reply triage, exports, pre-warmed domain purchases, and webhooks. Supports hosted OAuth or local stdio installs with scoped read, write, and purchase permissions, plus two-step confirmation for anything that charges a card.45 PyPIMIT
Send4 MCP Serverofficial
AlicenseNot gradedqualityBmaintenanceConnects AI assistants to a Send4 workspace so users can ask about flows, campaigns, conversations, and usage, and make permitted changes in natural language.1MIT