Connect Givebutter to ChatGPT: Manage Campaigns and Donor Relations

If you need to connect Givebutter to ChatGPT to automate donor relations, track campaign performance, or manage ticketing workflows, you need a Model Context Protocol (MCP) server. This server acts as the translation layer between ChatGPT's tool calls and Givebutter's REST APIs. You can either build and maintain this infrastructure yourself, or use a managed integration platform like Truto to dynamically generate a secure, authenticated MCP server URL.

If your team uses Claude, check out our guide on connecting Givebutter to Claude or explore our broader architectural overview on connecting Givebutter to AI Agents.

Giving a Large Language Model (LLM) read and write access to a fundraising platform is an engineering challenge. You have to handle complex relational data payloads, map dynamic custom fields to MCP tool definitions, and deal with sensitive financial transactions. Every time a developer adds a new campaign type or updates a webhook schema in Givebutter, your custom server code must be updated, redeployed, and tested.

This guide breaks down exactly how to use Truto to generate a secure, managed MCP server for Givebutter, connect it natively to ChatGPT, and execute complex donor workflows using natural language.

The Engineering Reality of the Givebutter API

A custom Givebutter MCP server is a self-hosted integration layer. While the open MCP standard provides a predictable way for models to discover tools, implementing it against Givebutter's specific architectural quirks is painful.

If you decide to build a custom Givebutter MCP server, you own the entire API lifecycle. Here are the specific integration challenges that break standard CRUD assumptions when working with Givebutter:

Tag Syncing Destructiveness

Contact tags in Givebutter are not managed as simple string arrays attached to a standard PUT request. The API dictates distinct operations for tag management: tags/add, tags/remove, and tags/sync. If an LLM decides to update a contact by passing an incomplete array of tags to a standard update endpoint, it might not work as expected. To replace a contact's entire tag set, you must use the explicit sync operation. An effective Givebutter ChatGPT integration must surface these exact operations as distinct tools, rather than relying on generic update methods.

SSO vs Standard Authentication Boundaries

Givebutter's API surface is split across different authentication guards. Standard endpoints live under /v1, while single sign-on administrative functions live under /sso/v1. These paths sit behind entirely different authentication guards. A call to an SSO endpoint without the correct specific key will return a flat "Unauthenticated" error, even if the primary API token is valid. Your MCP server must route calls correctly based on the endpoint documentation, or ChatGPT will fail to retrieve account-level data.

Rate Limit Handling and Backoff

Givebutter enforces rate limits on high-volume endpoints like transactions and contacts. When connecting AI agents, they can easily trigger a spike of concurrent requests. It is a critical factual note that Truto does not retry, throttle, or apply backoff on rate limit errors. When the upstream Givebutter API returns an HTTP 429, Truto passes that error directly to the caller. Truto normalizes upstream rate limit information into standardized headers (ratelimit-limit, ratelimit-remaining, ratelimit-reset) per the IETF specification. The caller (the LLM client) is strictly responsible for interpreting these headers and executing retry and backoff logic.

Step-by-Step: Generate a Givebutter MCP Server

Truto's MCP servers feature turns your connected Givebutter account into an MCP-compatible tool server. Tool generation is dynamic and documentation-driven. Rather than hand-coding tool definitions, Truto derives them from Givebutter's documented endpoints. If a resource method lacks documentation, it is excluded - acting as a quality gate to ensure ChatGPT only sees well-defined tools.

You can generate the Givebutter MCP server using either the Truto dashboard or the API.

Method 1: Via the Truto UI

For administrators who want a visual configuration interface:

1. Log into your Truto account and navigate to the Integrated Accounts page.
2. Select your connected Givebutter instance.
3. Click the MCP Servers tab.
4. Click Create MCP Server.
5. Select your desired configuration. You can name the server, filter allowed methods (e.g., read-only), select specific resource tags, and set an expiration date.
6. Click save and copy the generated MCP server URL.

Method 2: Via the Truto API

For developers automating infrastructure provisioning, you can generate the MCP server programmatically. The API validates that the Givebutter integration has documented tools available, generates a cryptographically secure token, and returns a ready-to-use URL.

Make a POST request to /integrated-account/:id/mcp:

curl -X POST https://api.truto.one/integrated-account/$INTEGRATED_ACCOUNT_ID/mcp \
  -H "Authorization: Bearer $TRUTO_API_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
    "name": "Givebutter Campaign Manager for ChatGPT",
    "config": {
      "methods": ["read", "write"],
      "tags": ["campaigns", "contacts", "transactions"]
    }
  }'

The response contains the server record and the critical url field:

{
  "id": "mcp-12345678",
  "name": "Givebutter Campaign Manager for ChatGPT",
  "config": { 
    "methods": ["read", "write"],
    "tags": ["campaigns", "contacts", "transactions"]
  },
  "expires_at": null,
  "url": "https://api.truto.one/mcp/a1b2c3d4e5f67890"
}

This URL (https://api.truto.one/mcp/<token>) encodes the account context and authentication. Treat it like a secret.

Step-by-Step: Connect the MCP Server to ChatGPT

Once you have your Givebutter MCP server URL, you must register it with ChatGPT so the LLM can discover and invoke the tools. You can do this via the ChatGPT desktop interface or through a manual configuration file if you are running a custom client.

Method 1: Via the ChatGPT UI

If you are using a ChatGPT Pro, Plus, Business, Enterprise, or Education account, you can connect the server directly:

1. Open ChatGPT and navigate to Settings -> Apps -> Advanced settings.
2. Toggle Developer mode to ON.
3. Under the MCP servers / Custom connectors section, click to add a new server.
4. Enter a name (e.g., "Givebutter via Truto").
5. Paste the Truto MCP URL into the Server URL field and click Add.

ChatGPT will immediately connect, perform the MCP handshake, and list the available Givebutter tools.

Method 2: Via Manual Config File

If you are using a local AI agent framework or an MCP-compatible IDE that uses JSON configuration files, you can connect via the Server-Sent Events (SSE) transport. Create an mcp.json file:

{
  "mcpServers": {
    "givebutter": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-sse",
        "--url",
        "https://api.truto.one/mcp/a1b2c3d4e5f67890"
      ]
    }
  }
}

When your agent boots up, it runs the npx @modelcontextprotocol/server-sse command to bridge the standard I/O connection to Truto's remote JSON-RPC 2.0 endpoint.

Hero Tools for Givebutter Automation

When ChatGPT connects to the Givebutter MCP server, it executes a tools/list request. Truto dynamically builds a list of operations based on the underlying API documentation. The LLM sees a flat argument namespace; Truto handles parsing query parameters versus request bodies automatically.

Here are the most critical, high-leverage tools available for Givebutter.

List All Campaigns

Tool Name: list_all_givebutter_campaigns

This tool retrieves all active fundraising campaigns, events, and forms. Truto handles the pagination schema, returning the current page (up to a limit of 100) and the next_cursor. The LLM is instructed to pass the cursor back exactly as received to fetch subsequent pages.

"Fetch all of our active Givebutter campaigns and summarize the total funds raised across the top 3 campaigns."

Create a Contact

Tool Name: create_a_givebutter_contact

Used to programmatically insert new donors, sponsors, or volunteers into the Givebutter CRM. This is the foundation for automating lead capture from external forms or chat interactions.

"Create a new Givebutter contact for Jane Doe (jane.doe@example.com) and associate her with our main household."

Bulk Update Contact Tags

Tool Name: givebutter_contact_tags_bulk_update

Because Givebutter requires explicit tag operations, this tool replaces a contact's entire tag set with the specified array (executing a POST to .../tags/sync). Any existing tags not included in the payload will be removed, making it perfect for status transitions.

"Update the tags for contact ID 55432 to just 'Major Donor' and 'Gala 2026 VIP', clearing out any old event tags."

List All Transactions

Tool Name: list_all_givebutter_transactions

Retrieves the detailed financial ledger of donations, ticket purchases, and merchandise sales. This tool is essential for financial reconciliation and tracking donor activity over time.

"Pull the most recent 100 transactions from Givebutter and flag any donation that exceeds $1,000."

Create a Campaign Discount Code

Tool Name: create_a_givebutter_campaign_discount_code

Allows the LLM to generate promotional codes for specific event campaigns dynamically. Requires campaign_id, type, active, amount, and code parameters.

"Create a new active discount code 'EARLYBIRD20' for campaign ID 9876 offering a 20% discount on event tickets."

List All Payouts

Tool Name: list_all_givebutter_payouts

Retrieves payout records detailing when funds were transferred from Givebutter to the organization's bank account. Useful for answering accounting queries and matching bank deposits.

"List all recent Givebutter payouts and match them against the total transaction volume for the past 30 days."

To view the complete inventory of available tools and their required JSON schemas, visit the Givebutter integration page.

Workflows in Action

Once the Givebutter MCP server is connected, ChatGPT can orchestrate complex, multi-step operations that would traditionally require custom scripts or heavy UI navigation. Here are concrete examples of domain-specific workflows.

End-of-Month Donor Tagging & Transaction Sync

Nonprofits frequently need to audit end-of-month transactions and update donor segments based on giving levels. ChatGPT can automate this entire cycle.

"Find all Givebutter transactions from the past week. Identify any contacts who donated more than $500, and use the bulk update tool to set their tags to exactly 'High-Value Donor' and 'Q4 Campaign'."

Execution Steps:

1. ChatGPT calls list_all_givebutter_transactions and processes the financial records.
2. It extracts the contact_id for any transaction exceeding $500.
3. For each identified contact, it calls givebutter_contact_tags_bulk_update with the payload ["High-Value Donor", "Q4 Campaign"].
4. ChatGPT responds with a summary of which contacts were updated.

sequenceDiagram
  participant User as User
  participant ChatGPT as ChatGPT
  participant Truto as Truto MCP
  participant Givebutter as Givebutter API
  User->>ChatGPT: "Update tags for recent $500+ donors..."
  ChatGPT->>Truto: Call list_all_givebutter_transactions
  Truto->>Givebutter: GET /v1/transactions
  Givebutter-->>Truto: Return transaction array
  Truto-->>ChatGPT: Return MCP Result
  ChatGPT->>Truto: Call givebutter_contact_tags_bulk_update<br>(contact_id: 123, tags: [...])
  Truto->>Givebutter: POST /v1/contacts/123/tags/sync
  Givebutter-->>Truto: Return 200 OK
  Truto-->>ChatGPT: Return MCP Result
  ChatGPT-->>User: "Updated tags for 4 major donors."

Campaign Discount Code Generation & Auditing

Event organizers often need to spin up discount codes dynamically based on marketing partnerships and verify what codes are currently active.

"List all discount codes for our 'Spring Gala 2026' campaign. If there isn't a code for 'SPONSOR50', create one that offers a 50% discount and make sure it is active."

Execution Steps:

1. ChatGPT calls list_all_givebutter_campaigns to find the campaign_id for 'Spring Gala 2026'.
2. It calls list_all_givebutter_campaign_discount_codes using that ID.
3. It parses the results to see if 'SPONSOR50' exists.
4. If missing, it calls create_a_givebutter_campaign_discount_code with the necessary parameters.
5. ChatGPT confirms the creation of the code to the user.

Payout Reconciliation

Finance teams can use ChatGPT to bridge the gap between Givebutter's platform and their general ledger.

"Pull the most recent Givebutter payout. Then list the transactions that occurred immediately prior to that payout date to help me reconcile the bank deposit."

Execution Steps:

1. ChatGPT calls list_all_givebutter_payouts to find the latest transfer date and amount.
2. It calls list_all_givebutter_transactions to pull the ledger history.
3. It compares the transaction dates and totals against the payout record.
4. ChatGPT outputs a reconciled list of donations that comprise the payout amount.

Security and Access Control

Giving an AI agent access to financial data and donor records requires strict governance. Truto's Givebutter MCP servers provide granular access controls enforced at the server level, preventing the LLM from hallucinating unauthorized actions.

• Method Filtering (config.methods): Restrict the server to specific HTTP verbs. You can set the server to ["read"] to allow get and list operations while hard-blocking create, update, and delete. This ensures the LLM can only report on data, not alter it.
• Tag Filtering (config.tags): Scope tools down to specific functional areas. By setting tags: ["campaigns"], the server will completely hide contact, transaction, and payout tools, preventing the LLM from even knowing those endpoints exist.
• Dual-Layer Auth (require_api_token_auth): By default, possessing the MCP URL grants access. By enabling this flag, clients must also pass a valid Truto API token via a standard Bearer header, adding identity verification to the connection.
• Automatic Expiration (expires_at): You can provision temporary MCP servers for contractors, audits, or short-lived automated jobs. Once the ISO datetime is reached, the underlying token is automatically purged from distributed storage, immediately severing access.

Moving Forward with Givebutter and ChatGPT

Connecting Givebutter to ChatGPT transforms how nonprofits and event organizers interact with their CRM and financial data. Instead of navigating complex dashboards to export CSVs or manually tagging donors, teams can orchestrate full-cycle workflows using conversational instructions.

By leveraging an auto-generated MCP server, you eliminate the need to maintain boilerplate API integration code. You handle the prompts and workflows, and the integration layer handles the schemas, complex tagging logic, and routing.

If you want to give your AI agents secure, managed access to Givebutter - and over 200 other SaaS platforms - without writing custom integration code, talk to our team to get started.