Connect
Optimize
Secure
The #1 agentic semantic tool search: 91.6% first-try accuracy on S1 Search Bench • Explore Tool Discovery →
StackOne's Plaid MCP server gives AI agents 60 ready-to-use actions for Plaid — with built-in authentication, security, governance, token efficiency, and high tool-calling accuracy.
Coverage
Create, read, update, and delete across Plaid — and extend your agent's capabilities with custom actions.
Authentication
Per-user OAuth in one call. Your Plaid MCP server gets session-scoped tokens with zero credentials stored on your infra.
Agent Auth →Security
Every Plaid tool response scanned for prompt injection in milliseconds — 88.7% accuracy, all running on CPU.
Prompt Injection Defense →Performance
Free up to 96% of your agent's context window to enhance reasoning and reduce cost, on every Plaid call.
Tools Discovery →A Plaid MCP server lets AI agents read and write Plaid data through the Model Context Protocol — Anthropic's open standard for connecting LLMs to external tools. StackOne's Plaid MCP server ships with 60 pre-built actions, fully extensible via the Connector Builder — plus managed authentication, prompt injection defense, and optimized agent context. Connect it from MCP clients like Claude Desktop, Claude Code, Cursor, Goose, and VS Code, or from agent frameworks like OpenAI Agents SDK, LangChain, and Vercel AI SDK.
Every action from Plaid's API, ready for your agent. Create, read, update, and delete — scoped to exactly what you need.
Create an Asset Report for the linked Item, providing a point-in-time snapshot of account balances, transactions, and identity data for lending and verification via POST /asset_report/create
Retrieve a completed Asset Report containing account balances, transaction history, and identity data via POST /asset_report/get
Permanently delete an Asset Report and invalidate its token via POST /asset_report/remove
Retrieve a paginated list of all Plaid-supported financial institutions with filtering by country, products, and routing numbers via POST /institutions/get
Search Plaid's institution directory by name or query string with optional product and country filters via POST /institutions/search
Retrieve metadata and health status for a linked financial institution Item via POST /item/get
Permanently remove a linked Item, invalidating its access_token and ending all associated billing via POST /item/remove
Create a link_token to initialize Plaid Link, the client-side UI component for bank account connection, via POST /link/token/create
Retrieve metadata and configuration details for a previously created link_token via POST /link/token/get
Retrieve a list of available bank statements for all accounts linked to an Item via POST /statements/list
Download a single bank statement PDF by its statement ID via POST /statements/download
Fetch historical transaction data within a specified date range with pagination and optional enrichment fields via POST /transactions/get
Get incremental transaction updates using Plaid's recommended cursor-based sync approach, returning added, modified, and removed transactions since the last sync via POST /transactions/sync
Initiate a money movement using a previously-approved authorization, returning the transfer_id and initial status (pending) via POST /transfer/create
Retrieve the current state and metadata of a single transfer by transfer_id via POST /transfer/get
List transfers with optional filters by date range, account, status, or originator via POST /transfer/list
List historical lifecycle events across transfers with date and status filters via POST /transfer/event/list
Incrementally pull transfer lifecycle events using a monotonically-increasing event_id cursor via POST /transfer/event/sync
Refund some or all of a posted/settled transfer back to the user's bank via POST /transfer/refund/create
Retrieve refund details and current status by refund_id via POST /transfer/refund/get
Generate a fresh Consumer Report (Plaid Check) for a user, kicking off async aggregation of bank, income, and cashflow data via POST /cra/check_report/create
Authorize a money movement before creating a transfer, returning a Plaid risk decision (approved, declined, user_action_required) via POST /transfer/authorization/create
Retrieve all financial accounts (checking, savings, credit, loan, investment) linked to an Item via POST /accounts/get
Fetch real-time balance data directly from the financial institution for all or specific accounts via POST /accounts/balance/get
Download a completed Asset Report as a formatted PDF document (binary response, application/pdf) for sharing with lenders and verifiers via POST /asset_report/pdf/get
Retrieve bank account numbers and routing numbers needed to initiate ACH, EFT, BACS, and wire transfers via POST /auth/get
Retrieve the base bank/cash-flow Consumer Report containing items, accounts, balances, and transactions via POST /cra/check_report/base_report/get
Retrieve the income-stream-analysis section of the Consumer Report (recurring deposits clustered into employer streams) via POST /cra/check_report/income_insights/get
Retrieve cashflow-pattern analysis (income vs expense, NSF events, savings trends) of the Consumer Report via POST /cra/check_report/cashflow_insights/get
Retrieve Plaid's proprietary LendScore (cash-flow-based credit score) for the user via POST /cra/check_report/lend_score/get
Retrieve partner-derived cash-flow insights computed by Plaid's underwriting partners via POST /cra/check_report/partner_insights/get
Download the Consumer Report as a formatted PDF document for sharing with lenders via POST /cra/check_report/pdf/get
Retrieve personal identity information (name, email, phone, address) for account holders directly from the financial institution via POST /identity/get
Retrieve completed Bank Income reports (income streams identified from bank deposits) for a user via POST /credit/bank_income/get
Download a Bank Income report as a formatted PDF document for sharing with lenders via POST /credit/bank_income/pdf/get
Retrieve verified payroll-system-sourced income data for a user (W-2, paystubs, employer info) via POST /credit/payroll_income/get
Retrieve fraud risk signals on parsed payroll documents (paystubs, W-2s) via POST /credit/payroll_income/risk_signals/get
Retrieve employment verification data (employer name, employment dates, status) sourced from payroll provider via POST /credit/employment/get
List the user's Income / Consumer-Report Link sessions and their final statuses via POST /credit/sessions/get
Retrieve detailed metadata for a single financial institution by its Plaid institution_id via POST /institutions/get_by_id
Retrieve current investment portfolio holdings including stocks, bonds, mutual funds, and ETFs for linked brokerage and retirement accounts via POST /investments/holdings/get
Retrieve investment transactions (buys, sells, dividends, fees, transfers) within a specified date range for linked brokerage accounts via POST /investments/transactions/get
Retrieve detailed liabilities data for credit cards, student loans, and mortgages associated with an Item via POST /liabilities/get
Fetch Plaid-detected recurring transaction patterns (subscriptions, income deposits, bills) for accounts associated with an Item via POST /transactions/recurring/get
Determine RTP eligibility and other transfer capabilities for a Plaid Item via POST /transfer/capabilities/get
Update or set the webhook URL for receiving real-time event notifications for an Item via POST /item/webhook/update
Create a refreshed copy of an existing Asset Report with updated data from the financial institutions via POST /asset_report/refresh
Create a filtered copy of an Asset Report with specified accounts excluded via POST /asset_report/filter
Enrich your own (non-Plaid-sourced) transactions with merchant info, categorization, and counterparty data via POST /transactions/enrich
Exchange a single-use public_token for a permanent access_token via POST /item/public_token/exchange
Create a test public_token for a sandbox Item, simulating the Plaid Link flow without user interaction, via POST /sandbox/public_token/create
Score the ACH return risk of a proposed debit transaction and apply Dashboard rulesets via POST /signal/evaluate
Pre-warm Plaid's risk model for an Item so the next /signal/evaluate completes faster via POST /signal/prepare
Report whether you proceeded with or blocked the ACH debit after a Signal score, used to refine Plaid's model via POST /signal/decision/report
Report a returned ACH transaction back to Plaid with the return code so its risk model can learn via POST /signal/return/report
Trigger on-demand extraction of bank statements for a specified date range via POST /statements/refresh
Trigger an on-demand refresh of transaction data for an Item, bypassing the normal automatic update schedule, via POST /transactions/refresh
Cancel a transfer that has not yet posted to the bank network via POST /transfer/cancel
Cancel an unused transfer authorization before it expires via POST /transfer/authorization/cancel
Cancel a pending refund before it posts to the network via POST /transfer/refund/cancel
Connect your AI agent to Plaid and help your team scale the finance operations they run by hand today.
Automate invoice processing with AI agents connected to your ERP, accounting software, and AP tools through StackOne.
ViewUse StackOne to connect your AI agent to your accounting, CRM, and messaging systems to automate Accounts Receivable dunning and payment follow-up.
ViewUse StackOne to connect your AI agent to your accounting, email, and document management systems to automate invoice processing and purchase order matching.
ViewOne endpoint. Any framework. Your agent is talking to Plaid in under 10 lines of code.
MCP Clients
Agent Frameworks
{
"mcpServers": {
"stackone": {
"command": "npx",
"args": [
"-y",
"mcp-remote@latest",
"https://api.stackone.com/mcp?x-account-id=<account_id>",
"--header",
"Authorization: Basic <YOUR_BASE64_TOKEN>"
]
}
}
}138+ actions
125+ actions
107+ actions
105+ actions
95+ actions
82+ actions
70+ actions
Anthropic's code_execution processes data already in context. Custom MCP code mode keeps raw tool responses in a sandbox. 14K tokens vs 500.
11 min
Benchmarking BM25, TF-IDF, and hybrid search for MCP tool discovery across 916 tools. The 80/20 TF-IDF/BM25 hybrid hits 21% Top-1 accuracy in under 1ms.
10 min
MCP tools that read emails, CRM records, and tickets are indirect prompt injection vectors. Here's how we built a two-tier defense that scans tool results in ~11ms.
12 min
origin_owner_id.All the tools you need to build and scale AI agent integrations, with best-in-class connectivity, execution, and security.