Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/henfrydls/actual-budget-mcpWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/plugins/henfrydls/actual-budget-mcp/gemini-extension)<a href="https://agentmods.dev/plugins/henfrydls/actual-budget-mcp/gemini-extension"><img src="https://agentmods.dev/badge/plugins/henfrydls/actual-budget-mcp/gemini-extension/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/plugins/henfrydls/actual-budget-mcp/gemini-extension"><img src="https://agentmods.dev/badge/plugins/henfrydls/actual-budget-mcp/gemini-extension.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
actual-budget scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
{
"name": "actual-budget",
"version": "0.9.0",
"description": "Ask your Actual Budget where the money went, and let it write back safely: every delete previews first and asks before it destroys anything.",
"settings": [
{
"name": "Actual server URL",
"description": "Where your Actual Budget server is reachable, for example http://localhost:5006",
"envVar": "ACTUAL_SERVER_URL"
},
{
"name": "Server password",
"description": "The password for your Actual server. Leave empty if your server uses OIDC and you set a session token instead.",
"envVar": "ACTUAL_PASSWORD",
"sensitive": true
},
{
"name": "Budget Sync ID",
"description": "Actual shows this under Settings > Show advanced settings. It is the Sync ID, not the Budget ID shown above it — the two look alike and only the Sync ID works.",
"envVar": "ACTUAL_BUDGET_ID"
},
{
"name": "Session token (OIDC servers only)",
"description": "For servers behind OIDC, which have no password. Use this instead of the password; if both are set, the token wins.",
"envVar": "ACTUAL_SESSION_TOKEN",
"sensitive": true
},
{
"name": "Read-only mode",
"description": "Set to 1 to expose only the read and analysis tools. The write tools are not registered at all, so they never reach tool discovery.",
"envVar": "ACTUAL_READ_ONLY"
}
],
"mcpServers": {
"actual": {
"command": "npx",
"args": ["-y", "actual-budget-mcp"]
}
}
}
What ships with it
1 file beside gemini-extension.json in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 41 lines scan A 822ec84c03cf
actual-budget is a plugin published in the GitHub repository henfrydls/actual-budget-mcp (6 stars, last pushed 2d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-13.
Other plugins, from other repositories
you
You.com skills for search, contents, research, finance, and integration discovery with MCP, ARD, API-key, OAuth, and MPP/x402 payment guidance.
ynab-mcp-server
YNAB MCP connector for budgets, transactions, categories, scheduled transactions, accounts, months, payees, and budget review workflows.
secedgar-mcp-server
Query SEC EDGAR filings, XBRL financials, and company data through MCP. STDIO & Streamable HTTP.
drillr
drillr financial data and research MCP for AI agents — filings, statements, earnings, ownership, events, executives, analyst data, company discovery and research signals for US, China and Japan. Ten tools, browser sign-in, every figure traced to its filing.
treasury-fiscaldata-mcp-server
Query US Treasury national debt, interest rates, exchange rates, and fiscal datasets via MCP.
Headless Oracle
Real-time, cryptographically signed (Ed25519) market status for 23 global exchanges. Fail-closed architecture designed for autonomous trading agents.