banksync-mcp: Instructions file for Claude Code

CLAUDE.md

banksync-mcp CLAUDE.md is an instructions file for Claude Code from banksynchq/banksync-mcp. It costs 791 tokens per session, scanned A, original, MIT.

Repository instructions for BankSync's thin MCP client, which connects coding agents to the remote BankSync MCP server. MCP is a standard way for an AI agent to call external tools.

In plain words
What is it for?
Use them when developing or reviewing the TypeScript or Python clients, their MCP bridge, registry files, or tool documentation.
Why use it?
They explain the repository structure, connection design, required API key, and development commands before you change the client.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions AGENTS.md.

This is banksynchq/banksync-mcp's own configuration. It tells Claude Code how to work on banksync-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything banksync-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to banksynchq/banksync-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/banksynchq/banksync-mcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/banksynchq/banksync-mcp

Made for: Claude Code.

Wrote 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.

agentmods badge for banksync-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/banksynchq/banksync-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/banksynchq/banksync-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/banksynchq/banksync-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/banksynchq/banksync-mcp/claude-md/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.

agentmods 80×15 button for banksync-mcp CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/banksynchq/banksync-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/banksynchq/banksync-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 791 This file is loaded in full into every session.
When invoked 791 The same file — it is already loaded in full.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00791 $0.00791
Opus 5 $0.00396 $0.00396
Sonnet 5 $0.00158 $0.00158
Haiku 4.5 $0.00079 $0.00079

Measured 9d ago against content hash 9622cb071c47, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

banksync-mcp CLAUDE.md scanned grade A with 1 finding 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 9d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

3. Once merged, `release.yml` runs automatically: tags `v<version>`, creates the GitHub release, then publishes to npm and PyPI in the same run. Confirm both via `npm view @banksync/mcp version` and `curl -s https://pypi
CLAUDE.md · 66 lines

How it starts

The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.

BankSync MCP Server

This is a thin MCP client that bridges stdio to the remote BankSync MCP server at https://mcp.banksync.io.

Repository Structure

banksync-mcp/
├── typescript/     # Node.js thin client (@banksync/mcp on npm)
├── python/         # Python thin client (banksync-mcp on PyPI)
├── docs/           # Documentation (TOOLS.md, ARCHITECTURE.md, AGENTS.md)
├── server.json     # MCP Registry metadata
├── smithery.yaml   # Smithery registry config
└── glama.json      # Glama registry metadata

Architecture

Both clients validate BANKSYNC_API_KEY then bridge stdio to https://mcp.banksync.io via Streamable HTTP. No business logic lives here — everything is handled by the remote server.

  • Node.js: Spawns mcp-remote as a child process
  • Python: Uses the MCP SDK's async streamablehttp_client

Key Files

  • typescript/src/index.ts — Node.js entry point (thin client)
  • python/banksync_mcp/server.py — Python entry point (thin client)
  • server.json — MCP Registry manifest (schema version 2025-12-11)
  • docs/TOOLS.md — All 28 tools with parameters
  • docs/AGENTS.md — Agent integration guide

Development

# TypeScript
cd typescript && pnpm install && pnpm build && pnpm check

# Python
cd python && uv sync && uv run ruff check && uv run pytest

Publishing

Publishing is automated by .github/workflows/release.yml, which fires on pushes to main that touch server.json. The workflow tags the new version, creates a GitHub release, then invokes publish-npm.yml and publish-pypi.yml via workflow_call in the same run (this avoids the GITHUB_TOKEN cascade-suppression that would otherwise prevent the publish workflows from firing).

To cut a release:

  1. On a branch, bump the version in all five places so they stay in sync:
    • typescript/package.json
    • python/pyproject.toml
    • server.json (top-level version plus both packages[].version)
    • mcpb/manifest.json
    • mcpb/package.json
  2. Open a PR and rebase-merge (not squash). Put the bump as the last commit so the previous commit's message ends up in the auto-generated CHANGELOG (release.yml runs git log PREV..HEAD~1, which excludes the tip commit).
  3. Once merged, release.yml runs automatically: tags v<version>, creates the GitHub release, then publishes to npm and PyPI in the same run. Confirm both via npm view @banksync/mcp version and curl -s https://pypi.org/pypi/banksync-mcp/json | jq -r .info.version.

Read the full file on GitHub · 66 lines

Changes

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.

  1. 9d ago First seen · 66 lines · 791 tokens per session scan A 9622cb071c47

Subscribe to this mod's changes

banksync-mcp CLAUDE.md is an instructions file published in the GitHub repository banksynchq/banksync-mcp (2 stars, last pushed 4mo ago), licensed MIT. It adds 791 tokens to every session, about $0.0040 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,735 tokens