Auth (expensebot) MCP Server
@expensebot/mcp-server-auth
npm
v0.6.22
Published by @expensebot — no publish provenance, so origin is unverified, but the source is public: the repository link below is self-declared yet readable, so you can inspect the code before adopting it.
Authenticated MCP server for ExpenseBot — lets Claude Desktop, Cursor, and other AI assistants search your expenses, create reports, and analyze spending using your actual ExpenseBot data.
The grade answers one question — how safe is this server for you to adopt — so it is computed in two auditable stages. Nothing below is an opinion or an LLM's guess; every line is a real term the deterministic engine applied, and the same input always yields the same number.
1. Threat score — 100 − 0 = 100. What the published surface and source actually contain:
The deterministic scan raised no scored threat in the surface it inspected — the threat score stayed at 100. Capability observations and advisory notes are recorded but never lower it.
2. Client adoption risk — 100 − 7 = 93. Three small, subtract-only factors that reflect your risk in adopting it — a clean scan proves less on a powerful, unverified or barely-inspectable package, so the grade says so plainly:
| Points | Adoption-risk factor |
|---|---|
| −6 | capability blast radius (high) — client exposure if the model is manipulated |
| −1 | publisher verification (public source) — no provenance, but the source is public and inspectable |
Capability observations and info notes are shown under Findings but never scored.
Open any row's finding below for the file, line and evidence behind a deduction.
Findings 1
high Shell/command execution in server code (src/test.js)MTC-SRC-002
In the server's implementation (`src/test.js:17`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: rt { spawn } from "node:child_process"; import { readFileSync } from "node:fs"; import { fileURLToPath } from "node:url"
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server src/test.js
Tools 56
Each tool and what it can reach — statically extracted from the published source.
export_reportingests untrusted inputget_expense_by_idingests untrusted inputadd_cash_expenseno sensitive capabilityadd_incomeno sensitive capabilityadd_income_from_csvno sensitive capabilityadd_income_from_fileno sensitive capabilityadd_mileage_entryno sensitive capabilitycheck_complianceno sensitive capabilitycheck_featureno sensitive capabilitycheck_tax_deductibilityno sensitive capability
Show 46 more tools ↓
correct_expensesno sensitive capabilitycreate_reportno sensitive capabilityfix_complianceno sensitive capabilityget_accounting_integration_statusno sensitive capabilityget_accounting_push_statusno sensitive capabilityget_client_advance_balancesno sensitive capabilityget_credits_refundsno sensitive capabilityget_deep_analyticsno sensitive capabilityget_expense_splitsno sensitive capabilityget_income_summaryno sensitive capabilityget_last_receipt_resultno sensitive capabilityget_mileage_summaryno sensitive capabilityget_monthly_books_reviewno sensitive capabilityget_per_tag_pnlno sensitive capabilityget_pnlno sensitive capabilityget_pricingno sensitive capabilityget_recent_activityno sensitive capabilityget_report_detailsno sensitive capabilityget_scan_statusno sensitive capabilityget_signup_linkno sensitive capabilityget_spending_summaryno sensitive capabilityget_spreadsheet_urlno sensitive capabilityget_subscription_auditno sensitive capabilityget_trip_suggestionsno sensitive capabilitygroup_expensesno sensitive capabilitylist_categoriesno sensitive capabilitylist_client_invoicesno sensitive capabilitylist_income_categoriesno sensitive capabilitylist_reportsno sensitive capabilitylist_tagsno sensitive capabilityparse_expenseno sensitive capabilityprocess_gmail_receiptsno sensitive capabilityrequest_accounting_integrationno sensitive capabilityscan_gmailno sensitive capabilityscan_gmail_yearsno sensitive capabilitysearch_expensesno sensitive capabilitysearch_knowledgeno sensitive capabilitysend_report_to_accountingno sensitive capabilityshare_reportno sensitive capabilitystart_trial_linkno sensitive capabilitysubmit_receiptno sensitive capabilitytrace_documentno sensitive capabilityupdate_expenseno sensitive capabilitywhatif_affordno sensitive capabilitywhatif_clientno sensitive capabilitywhatif_tax_setasideno sensitive capability
What this scan could not see
- Tools were statically extracted from the published source (56 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".
Versions 10
Scan history per published version. The engine is deterministic — the same version always yields the same score, so a changed score means the package itself changed.
| Version | Score | Findings | Engine | Scanned |
|---|---|---|---|---|
v0.6.22 latest |
A 93/100 | 1 | 1.13.0 | 2026-09-07 |
v0.6.21 |
A 93/100 | 1 | 1.12.1 | 2026-08-16 |
v0.6.20 |
A 93/100 | 1 | 1.12.1 | 2026-08-13 |
v0.6.17 |
A 92/100 | 1 | 1.12.1 | 2026-08-12 |
v0.6.13 |
A 92/100 | 1 | 1.12.1 | 2026-08-10 |
Show 5 more versions ↓
v0.6.9 |
A 92/100 | 1 | 1.12.1 | 2026-08-07 |
v0.6.7 |
A 92/100 | 1 | 1.12.1 | 2026-08-06 |
v0.6.5 |
A 92/100 | 1 | 1.12.1 | 2026-08-05 |
v0.6.4 |
A 92/100 | 1 | 1.12.1 | 2026-08-04 |
v0.6.3 |
A 92/100 | 1 | 1.12.1 | 2026-08-02 |
Embed this score
Show this server's live Trust Score in your README, docs or website. The badge is served straight from the registry and updates automatically after every rescan — no API key needed. It links back to this page, so anyone who sees the grade can also read the findings behind it instead of taking a number on faith.
Verify this score yourself
The score above is reproducible: the same package version always yields the same result. Run it locally or over the free API — no account, no LLM, fully deterministic.
npx mcptrustchecker scan @expensebot/mcp-server-auth --onlineOther implementations of Auth 3
Independent packages implementing the same tool, scanned with the same engine. Compare all 4 side by side →
Plug and play auth for Model Context Protocol (MCP) servers
SDK for building OAuth-protected Remote MCP servers on Cloudflare Workers with pluggable auth adapters (Supabase already implemented).
Civic Auth integration for MCP servers
More in AI & Agents
Authenticated MCP transport with HTTP Signatures for AAuth agents
Local-first MCP server for parallel AI coding agents to claim file ownership before edits, preventing stomping on each other in the same worktree.
Agent-agnostic intercommunication system — sessions, messaging, channels, shared state, and real-time events
MCP server for AI agent task communication and delegation with diagnostic lifecycle visibility
Programmatic add/link/unlink for MCP servers across 23 AI coding agents (Claude Code, Claude Desktop, Cursor, VS Code, Codex, Gemini CLI, Zed, Cline, OpenCode, Goose, Kiro, Windsurf, and more). Functional API with dry-run support.
MCP server layer exposing agent-mesh orchestrator as an MCP agent