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.
npx agentmods add instructions/hs737/mcp-server-for-ynab/agents-mdgit clone --depth 1 https://github.com/hs737/mcp-server-for-ynabWrote 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/instructions/hs737/mcp-server-for-ynab/agents-md)<a href="https://agentmods.dev/instructions/hs737/mcp-server-for-ynab/agents-md"><img src="https://agentmods.dev/badge/instructions/hs737/mcp-server-for-ynab/agents-md.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.02408 | $0.02408 |
| Opus 5 | $0.01204 | $0.01204 |
| Sonnet 5 | $0.00482 | $0.00482 |
| Haiku 4.5 | $0.00241 | $0.00241 |
Grade A, and why
mcp-server-for-ynab AGENTS.md 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 yesterday.
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.
How it starts
The opening of the file, as written. The whole thing — 315 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This file tells AI agents and contributors how this repository works and how to extend it correctly.
What this document is for
Read this page if you need:
- implementation rules
- extension paths for raw or enriched tools
- architecture invariants that docs must match
- guidance for updating diagrams and repo docs
Adjacent docs:
Mission
mcp-server-for-ynab is an MCP server for AI agents to interact with YNAB budgets. It exposes the YNAB API through raw tools and adds enriched AI-friendly helpers on top. The goal is safe, explicit budget management rather than autonomous financial decision-making.
Start Here If You Are Modifying the Repo
- Read Architecture.
- Read Repo Structure.
- Read Tool Surface if you are touching tools.
- Read Testing before changing behavior.
- Update docs and diagrams when the structure or request flow changes.
Architecture Map
src/mcp_server_for_ynab/
├── auth/ auth abstraction + PAT implementation
├── cli/ stdio/http entrypoints and smoke helper
├── config/ env loading, runtime validation, default plan resolution
├── enriched/ AI-friendly read workflows
├── http_client/ async httpx wrapper: retries, error normalization, redaction
├── models/ typed YNAB shapes, shared error model, milliunit helpers
├── server/ MCPServer app, context, registry, error boundary, tool registration
└── ynab_client/ async wrappers for YNAB resource families
Trace a Tool from MCP Name to YNAB Request
sequenceDiagram
participant Client as MCP client
participant Server as server/app.py
participant Handler as server/tools/*
participant YClient as ynab_client/*
participant Http as http_client/client.py
participant API as YNAB API
Client->>Server: invoke tool name
Server->>Handler: registered MCPServer handler
Handler->>YClient: call resource or enriched workflow
YClient->>Http: request(...)
Http->>API: HTTP call
API-->>Http: JSON response
Http-->>YClient: dict or structured exception
YClient-->>Handler: typed model
Handler-->>Server: dict payload
Server-->>Client: MCP tool result
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.
- yesterday Changed · +68 lines · +764 tokens per session 6bd3e9cc1920
- 5d ago First seen · 247 lines · 1,644 tokens per session scan A 6bc9b733bab5
mcp-server-for-ynab AGENTS.md is an instructions file published in the GitHub repository hs737/mcp-server-for-ynab (1 stars, last pushed 2d ago), licensed Apache-2.0. It adds 2,408 tokens to every session, about $0.0120 per session on Opus 5. 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 2026-08-31.
Other instructions, from other repositories
ynab-budget-mcp AGENTS.md
AGENTS.md instructions for Orlando-Villanueva/ynab-budget-mcp, covering agents.md, purpose, project shape, core files and commands.
claude-prompts-mcp CLAUDE.md
Claude Code instructions for minipuft/claude-prompts-mcp, covering claude prompts mcp -- operator handbook, core principles, node.js support boundaries, validation gates (one contract, impact-aware subsets) and fleet standards upstream (minipuft/repository-standards).
claude-prompts-mcp AGENTS.md
AGENTS.md instructions for minipuft/claude-prompts-mcp, covering agent rules · claude prompts mcp, canonical ownership and loading, core principles, node.js support boundaries and validation gates (one contract, impact-aware subsets).
pubcrawl CLAUDE.md
Claude Code instructions for nickjlamb/pubcrawl, covering claude.md, project overview, commands, testing and architecture.
fireflyiii-mcp CLAUDE.md
Claude Code instructions for daften/fireflyiii-mcp, covering claude code instructions and claude-specific preferences.
gmail-mcp CLAUDE.md
Instructions for cunicopia-dev/gmail-mcp, covering gmail mcp — development guide, what it is, layout, module responsibilities and oauth model.