Convert PDF bank statements to checked Excel, CSV or JSON with balance validation.
Maintain this server? Claim it
Call this server's tools from your browser. Nothing to install.
Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.
Tool list from our last check. Connect live to refresh it.
Convert one PDF bank statement through the complete MainBook workflow: create a job, upload, start, poll, and return structured data. This creates a job and spends page credits; it is not read-only.
Public HTTPS URL of a PDF for remote mode. Redirects and non-public network addresses are rejected. Exactly one source is required.
Path to a PDF on the MCP server machine. This field is only available over stdio and is rejected in HTTP mode; remote clients must use file_url. The path must be inside the allowed folders, which default to Downloads, Desktop, and Documents. Exactly one of file_path and file_url is required.
Optional absolute result file or existing folder on the MCP server machine. Only available over stdio and only inside the allowed folders. The file extension is corrected to match result_type.
JSON is returned inline. Over stdio, XLSX or CSV is written to an allowed local folder and the full path is returned. HTTP mode returns safe download instructions. Binary bytes never enter model context.
Optional value forwarded verbatim in the Idempotency-Key REST header.
Internal polling budget from 30 to 900 seconds. Timeout leaves the job running and returns its job_id for get_conversion. The default stays under the 60-second request timeout most MCP clients enforce; a client that gives up first discards the job_id and the conversion looks lost.
This tool isn't marked read-only, so it may change something on the server or in an account you connected.
Convert one PDF bank statement through the complete MainBook workflow: create a job, upload, start, poll, and return structured data. This creates a job and spends page credits; it is not read-only.
| Argument | Type | Description |
|---|---|---|
| file_url | any | Public HTTPS URL of a PDF for remote mode. Redirects and non-public network addresses are rejected. Exactly one source is required. |
| file_path | any | Path to a PDF on the MCP server machine. This field is only available over stdio and is rejected in HTTP mode; remote clients must use file_url. The path must be inside the allowed folders, which default to Downloads, Desktop, and Documents. Exactly one of file_path and file_url is required. |
| output_path | any | Optional absolute result file or existing folder on the MCP server machine. Only available over stdio and only inside the allowed folders. The file extension is corrected to match result_type. |
| result_type | string | JSON is returned inline. Over stdio, XLSX or CSV is written to an allowed local folder and the full path is returned. HTTP mode returns safe download instructions. Binary bytes never enter model context. |
| idempotency_key | any | Optional value forwarded verbatim in the Idempotency-Key REST header. |
| timeout_seconds | integer | Internal polling budget from 30 to 900 seconds. Timeout leaves the job running and returns its job_id for get_conversion. The default stays under the 60-second request timeout most MCP clients enforce; a client that gives up first discards the job_id and the conversion looks lost. |
{
"type": "object",
"title": "convert_bank_statementArguments",
"properties": {
"file_url": {
"anyOf": [
{
"type": "string",
"minLength": 1
},
{
"type": "null"
}
],
"title": "File Url",
"default": null,
"description": "Public HTTPS URL of a PDF for remote mode. Redirects and non-public network addresses are rejected. Exactly one source is required."
},
"file_path": {
"anyOf": [
{
"type": "string",
"minLength": 1
},
{
"type": "null"
}
],
"title": "File Path",
"default": null,
"description": "Path to a PDF on the MCP server machine. This field is only available over stdio and is rejected in HTTP mode; remote clients must use file_url. The path must be inside the allowed folders, which default to Downloads, Desktop, and Documents. Exactly one of file_path and file_url is required."
},
"output_path": {
"anyOf": [
{
"type": "string",
"minLength": 1
},
{
"type": "null"
}
],
"title": "Output Path",
"default": null,
"description": "Optional absolute result file or existing folder on the MCP server machine. Only available over stdio and only inside the allowed folders. The file extension is corrected to match result_type."
},
"result_type": {
"enum": [
"json",
"xlsx",
"csv"
],
"type": "string",
"title": "Result Type",
"default": "json",
"description": "JSON is returned inline. Over stdio, XLSX or CSV is written to an allowed local folder and the full path is returned. HTTP mode returns safe download instructions. Binary bytes never enter model context."
},
"idempotency_key": {
"anyOf": [
{
"type": "string",
"maxLength": 255,
"minLength": 1
},
{
"type": "null"
}
],
"title": "Idempotency Key",
"default": null,
"description": "Optional value forwarded verbatim in the Idempotency-Key REST header."
},
"timeout_seconds": {
"type": "integer",
"title": "Timeout Seconds",
"default": 50,
"maximum": 900,
"minimum": 30,
"description": "Internal polling budget from 30 to 900 seconds. Timeout leaves the job running and returns its job_id for get_conversion. The default stays under the 60-second request timeout most MCP clients enforce; a client that gives up first discards the job_id and the conversion looks lost."
}
}
}Return total, reserved, and available MainBook credits. Every value is measured in PDF pages.
No arguments.
{
"type": "object",
"title": "get_balanceArguments",
"properties": {}
}Get the current state of one MainBook conversion. When successful, return JSON inline or save XLSX/CSV locally over stdio. HTTP mode returns safe download instructions. Use this after convert_bank_statement times out.
| Argument | Type | Description |
|---|---|---|
| job_id* | string | Conversion job UUID returned by MainBook. |
| output_path | any | Optional absolute result file or existing folder on the MCP server machine. Only available over stdio and only inside the allowed folders. |
| result_type | string | Result representation to retrieve after the job succeeds. |
{
"type": "object",
"title": "get_conversionArguments",
"required": [
"job_id"
],
"properties": {
"job_id": {
"type": "string",
"title": "Job Id",
"minLength": 1,
"description": "Conversion job UUID returned by MainBook."
},
"output_path": {
"anyOf": [
{
"type": "string",
"minLength": 1
},
{
"type": "null"
}
],
"title": "Output Path",
"default": null,
"description": "Optional absolute result file or existing folder on the MCP server machine. Only available over stdio and only inside the allowed folders."
},
"result_type": {
"enum": [
"json",
"xlsx",
"csv"
],
"type": "string",
"title": "Result Type",
"default": "json",
"description": "Result representation to retrieve after the job succeeds."
}
}
}List one cursor page of conversion jobs visible to the MainBook account. Pass the returned next_cursor to continue.
| Argument | Type | Description |
|---|---|---|
| limit | integer | Jobs on this page, from 1 to 100. |
| cursor | any | Opaque next_cursor from the previous page. |
{
"type": "object",
"title": "list_conversionsArguments",
"properties": {
"limit": {
"type": "integer",
"title": "Limit",
"default": 25,
"maximum": 100,
"minimum": 1,
"description": "Jobs on this page, from 1 to 100."
},
"cursor": {
"anyOf": [
{
"type": "string",
"minLength": 1
},
{
"type": "null"
}
],
"title": "Cursor",
"default": null,
"description": "Opaque next_cursor from the previous page."
}
}
}