General Tools
mainbook.ai
Provides general-purpose tools through the Model Context Protocol.
ENDPOINT 1
https://mcp.mainbook.ai/mcp
MCP server metadata
- Name
- mainbook
- Version
- 0.4.2
Use convert_bank_statement for a new PDF. It creates a paid page-credit job, so do not call it speculatively. Use get_conversion after a timeout.
Known tools 5
convert_bank_statementConvert one PDF bank statement through the complete MainBook workflow: create a job, upload, start, poll, and return structured data.
Potential side effectslist_conversionsList one cursor page of conversion jobs visible to the MainBook account.
Inferred read-onlyCONNECT WITH APPROVAL
Client installation
Review this server and its permissions before adding it. Secret placeholders must be set locally.
Codex
~/.codex/config.toml
[mcp_servers.mainbook]
url = "https://mcp.mainbook.ai/mcp"
enabled = true
Claude Code
.mcp.json
{
"mcpServers": {
"mainbook": {
"type": "http",
"url": "https://mcp.mainbook.ai/mcp"
}
}
}
Claude Desktop
Settings → Connectors → Add custom connector
Name: mainbook
Remote MCP URL: https://mcp.mainbook.ai/mcp
Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.
Cursor
.cursor/mcp.json
{
"mcpServers": {
"mainbook": {
"url": "https://mcp.mainbook.ai/mcp"
}
}
}
Visual Studio Code
.vscode/mcp.json
Add to Visual Studio Code{
"servers": {
"mainbook": {
"type": "http",
"url": "https://mcp.mainbook.ai/mcp"
}
}
}
Generic MCP
Client-specific MCP configuration
{
"name": "mainbook",
"transport": "streamable-http",
"url": "https://mcp.mainbook.ai/mcp"
}
MCP Inspector
Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.
TRUST AND VERIFICATION EVIDENCE
Trust Data Available
BuiltWith Trust API v2 evidence for mainbook.ai was fetched 2026-08-23T20:23:36.196Z.
mainbook.ai is assessed as Trusted: Domain runs a meaningful technology spend, consistent with a real business.
Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.