📅 Book a 30-min Demo📞 Call/text (571) 293-0242
Connector · Financial data and account-linking API

Plaid MCP Server & Agent Skill

Last updated

ibl.ai publishes a free Plaid agent skill: a SKILL.md that teaches an AI agent to read and write Plaid data and expose it as an MCP tool. Download it, connect your own Plaid credentials, and run the agent on ibl.ai Agentic OS, where you own all the code and the data.

Plaid connects apps to people's bank, card and investment accounts. Through it an app reads account and routing numbers, balances, transactions and identity data, and can move money with Transfer.

What is the Plaid API, and what can an agent read from it?

JSON over HTTPS POST. A user links accounts in Link; the app exchanges the public_token for an access_token per Item, then calls product endpoints. Errors come back as error_code and error_type.

  • API: Plaid API (Auth, Transactions, Balance, Identity, Transfer) (REST)
  • Access: Public, self-serve
  • Base URL: https://sandbox.plaid.com (Sandbox) / https://production.plaid.com (Production)
  • Authentication: API key (client_id and secret); Link token flow (public_token exchanged for access_token)

Sign up in the Plaid Dashboard for a client_id and a secret per environment. Sandbox uses test credentials and simulated data; Production access is approved per product.

Send client_id and secret in the JSON body or as PLAID-CLIENT-ID and PLAID-SECRET headers. /link/token/create starts Link; /item/public_token/exchange returns an access_token to keep server-side.

What can an agent read from Plaid?

  • Account and routing numbers — /auth/get returns account and routing numbers for checking and savings accounts on an Item.
  • Transactions — /transactions/sync returns added, modified and removed transactions since the last cursor.
  • Real-time balance — /accounts/balance/get fetches current balances from the institution.
  • Identity — /identity/get returns account-holder names, addresses, emails and phone numbers.
  • Item status — /item/get returns institution, products, consent and error status for an Item.

What can an agent write to Plaid?

  • Link token — /link/token/create starts a Link session for a user.
  • Transfers — /transfer/authorization/create then /transfer/create moves money from a linked account. Confirm with the user first.
  • Cancel transfer — /transfer/cancel cancels a pending transfer. Confirm with the user first.
  • Remove Item — /item/remove invalidates the access_token and related processor tokens; cannot be undone. Confirm with the user first.

Limits: Production defaults, fixed windows: /accounts/balance/get 5/min and 30/hour per Item; /transactions/sync 50/min per Item; /auth/get and /identity/get 15/min per Item; client-wide caps also apply.

Account and routing numbers, balances, transactions and identity data are GLBA nonpublic personal information. access_tokens are long-lived secrets and must stay on the server.

How do I connect Plaid to an AI agent over MCP?

Plaid publishes an official MCP server: Plaid Dashboard MCP server.

Remote server at https://api.dashboard.plaid.com/mcp/ for Production Item debugging, Link analytics and usage; OAuth scope mcp:dashboard. Not for end-user account data.

You can register that server on ibl.ai as it is, or use the SKILL.md below when you want the agent to call the Plaid API (Auth, Transactions, Balance, Identity, Transfer) directly.

On ibl.ai an MCP connection is three records, and a working integration always needs all three:

  1. Register the server — POST …/mcp-servers/ with its URL, a transport (sse, websocket or streamable_http) and an auth_type of none, token or oauth2.
  2. Create a connection that holds the credential, scoped to the whole organization (platform), to a single agent, or to each user (user).
  3. Enable it on the agent — mcp-tool in tool_slugs and the server id in mcp_servers. Both lists are replaced, not merged, so read the settings first.

For an API key or a service credential, one token connection at platform scope serves the whole organization; scope a connection to a single agent when that agent needs narrower access than the rest.

The field reference is in MCP server connections, and the /iblai-api-agent-mcp skill runs all three steps from a coding agent.

What does the Plaid agent skill do?

The Plaid skill is one SKILL.md file named iblai-connect-plaid. It gives an agent the auth conventions, what to read, which writes need a person's confirmation, the ibl.ai MCP wiring, example prompts and guardrails.

Download the Plaid SKILL.md

Save it as .claude/skills/iblai-connect-plaid/SKILL.md, or in your agent's skills folder. The ibl.ai platform skills it calls come from one install:

$ npx skills add iblai/vibe --all

This connector skill is a starting point maintained on ibl.ai, not part of the iblai/vibe repository.

It was checked against Plaid's documentation on October 20, 2026. Test it against your own Plaid setup before you rely on it.

What can I ask a Plaid agent to do?

  • “Sync new transactions for this user's linked checking account since the last cursor”
  • “What is the available balance on the account we will debit for this payment?”
  • “Why did Link conversion drop for Chase users last week?”
  • “Debug why this Item is returning ITEM_LOGIN_REQUIRED”

How do I run a Plaid agent on ibl.ai?

Agentic OS is where the agent runs on ibl.ai: it holds the Plaid MCP connection, the model the agent uses, its instructions and its conversation history.

On ibl.ai you own all the code and the data, run it model-agnostic across any LLM, and pay with no per-seat pricing — so you can deploy anywhere, from your own cloud to a fully air-gapped network.

Which ibl.ai agents work with Plaid data?

Which ibl.ai platform skills does a Plaid agent use?

What else should I know before connecting Plaid to an AI agent?

Is there an official Plaid MCP server?

Yes. Plaid publishes Plaid Dashboard MCP server.

You can register it on ibl.ai as an MCP server, or use the SKILL.md when you want the agent to call the Plaid API (Auth, Transactions, Balance, Identity, Transfer) directly.

Who can get Plaid API credentials?

Sign up in the Plaid Dashboard for a client_id and a secret per environment. Sandbox uses test credentials and simulated data; Production access is approved per product.

Does Plaid data leave my infrastructure when an ibl.ai agent uses it?

On ibl.ai, you own all the code and the data. Self-hosted in your cloud or data center, the agent, its MCP connections and its conversation logs stay inside your perimeter.

Because the platform is model-agnostic, you can point the agent at a model you host, so Plaid records need not reach a third-party model provider.

Is the Plaid agent skill free to use?

Yes. The SKILL.md is a free download with no sign-up. It assumes you already have Plaid credentials, and your agreement with Plaid still governs how you use its API.

Which other data sources can an AI agent connect to alongside Plaid?

Which other Financial Services systems have a connector?

Every connector, grouped by sector, is on the connectors hub.