bunq Banking MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| BUNQ_OP_ITEM_ID | Yes | The 1Password item ID containing the bunq API key credential and API context. | |
| BUNQ_OP_VAULT_ID | Yes | The 1Password vault ID containing the bunq item. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
Discover exact operation names with get_tool_catalog, then batch learn_tools for schemas. Use execute_tool with the learned arguments. userID is bound to the authenticated session. Pagination is explicit: follow Pagination.older_url parameters using the same operation; one page is not complete history. Money movement and trading are disabled. Nonfinancial mutations require confirm_write=true and an explicit user request for that action. Use connection_status to check authentication. Never treat an unverified write as completed.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| get_tool_catalogA | STEP 1: Browse the official bunq operations. Do not guess operation names. Includes availability and exclusions. |
| learn_toolsA | STEP 2: Learn exact argument schemas and availability for up to 20 official operation names together. |
| connection_statusA | Verify the vault-backed production connection by reading the authenticated user's monetary accounts. |
| read_account_historyA | Read all exposed Payment pages for one account; ISO dates use [start,end). |
| review_financial_recordsB | Review supplied records locally with exact decimals and conservative transfers. |
| execute_toolB | STEP 3: Execute one learned, validated operation. Nonfinancial writes need explicit action authority and confirm_write=true. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 6 tools
The catalog → learn → execute pipeline has a clear three-step separation, and read_account_history vs review_financial_records are distinguished (remote fetch vs local review). The main residual risk is that the generic execute_tool can perform the same reads (accounts, payments) as connection_status and read_account_history, so an agent must rely on the descriptions to prefer the specialized tools.
All names are snake_case and readable, with verb_led patterns (get_, learn_, read_, review_, execute_). The one deviation is connection_status, a noun phrase with no verb, breaking the otherwise predictable pattern.
Six tools is a sensible size, and the meta-tool design prevents exposing dozens of raw bunq endpoints. However, half the surface (get_tool_catalog, learn_tools, execute_tool) is discovery scaffolding, leaving only three domain-facing tools, which feels slightly heavy on pipeline overhead.
Discovery, auth verification, payment history reads, local record review, and a confirm_write-gated executor cover the main lifecycle, and execute_tool is a catch-all for other operations. Gaps exist in that only payments get a dedicated, completeness-guaranteed read path, while accounts, cards, and requests must all be routed through the generic executor.