BeanquerySAFE
Beancount MCP Server is an experimental implementation that utilizes the Model Context Protocol (MCP) to enable AI assistants to query and analyze Beancount ledger files using Beancount Query Language (BQL) and the beanquery tool.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
The Beancount MCP Server is an experimental implementation of the Model Context Protocol (MCP) designed to interface with Beancount ledger files. Leveraging the Beancount Query Language (BQL) and the beanquery tool, this server enables seamless querying and analysis of financial data stored in Beancount format. By integrating MCP, the server facilitates standardized communication between AI assistants and Beancount ledgers, enhancing the accessibility and utility of financial data.
Note: This server is experimental and may undergo significant changes. It is recommended to use it in a development environment and provide feedback for further improvements.
A generated sample ledger can be found in sample.bean
Available Resources and Tools
- Tools:
set_ledger_file: Set the Beancount ledger file to use for queries (if not set via environment variable).run_query: Run a BQL query against the loaded Beancount file.- Resources:
beanquery://tables: Get a list of tables that BQL can access.beanquery://accounts: Get a list of accounts in the loaded Beancount file.
Example using Claude.ai
For a screenshot with expanded MCP interactions, see here.
⚠️ Privacy Warning
This tool interfaces with language model providers (LLMs) via the Model Context Protocol (MCP), and as such may transmit parts of your Beancount ledger—including potentially confidential or private financial information—to third-party services.
Please use this tool with caution, especially when:
- Your ledger contains sensitive data (e.g., client names, salary details, health-related expenses).
- You are using a cloud-hosted or non-self-hosted LLM backend.
Recommendations:
- Mask or reda
130233d89d38OBSERVED · 2026-10-08Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control.
claude mcp add beanquery-mcp -- uvx beanquery-mcp
{
"mcpServers": {
"beanquery-mcp": {
"command": "uvx",
"args": [
"beanquery-mcp"
]
}
}
}Exposed tools (2)
0 read · 2 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
run_query | write | Run a BQL query against the loaded Beancount file. |
set_ledger_file | write | Set the Beancount ledger file to use for queries. |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- none-observed
- Shell
- none-observed
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (1)
docs/screenshot-expanded.png
Gates applied: no_behavioural_pass.
130233d89d38full audit observations/trust-audit/mcp-server/vanto__beanquery.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-08 | 130233d89d38 | SAFE | B | 89 | first audit |
Questions
What is the Beanquery MCP server?
Beancount MCP Server is an experimental implementation that utilizes the Model Context Protocol (MCP) to enable AI assistants to query and analyze Beancount ledger files using Beancount Query Language (BQL) and the beanquery tool.
What tools does Beanquery expose?
2 in total: 0 read-only, 2 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is Beanquery safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.
What credentials does Beanquery need?
No credential environment variables were found in its source, so it appears to need none.
How current is this page?
The grade is for one exact copy of the source (130233d89d38), read on 2026-10-08. The repository is watched and re-audited when it changes.