uc-mcp-proxy: Instructions file for Claude Code

CLAUDE.md

uc-mcp-proxy CLAUDE.md is an instructions file for Claude Code from IceRhymers/uc-mcp-proxy. It costs 2,876 tokens per session, scanned A, original, MIT.

Project instructions for uc-mcp-proxy, a tool that connects the MCP protocol to Databricks services and handles Databricks OAuth login. OAuth is a standard way for an application to obtain permission without receiving your password.

In plain words
What is it for?
Use them when installing, testing, linting, type-checking, formatting, or building uc-mcp-proxy, including deciding which tests belong in CI.
Why use it?
They document the commands and test rules needed to work on the proxy safely, especially because integration tests can open a browser and use real authentication.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md.

This is IceRhymers/uc-mcp-proxy's own configuration. It tells Claude Code how to work on uc-mcp-proxy 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 uc-mcp-proxy configures →

Reuse

Borrowing it

Nothing to install: this file belongs to IceRhymers/uc-mcp-proxy. 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/IceRhymers/uc-mcp-proxy/master/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/IceRhymers/uc-mcp-proxy

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 uc-mcp-proxy CLAUDE.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/icerhymers/uc-mcp-proxy/claude-md"><img src="https://agentmods.dev/badge/instructions/icerhymers/uc-mcp-proxy/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,876 This file is loaded in full into every session.
When invoked 2,876 The same file — it is already loaded in full.
Security scan A 0 findings. 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 $0.02876 $0.02876
Opus 5 $0.01438 $0.01438
Sonnet 5 $0.00575 $0.00575
Haiku 4.5 $0.00288 $0.00288

Measured 8d ago against content hash 281bc85bf7a6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

uc-mcp-proxy CLAUDE.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 8d 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.

CLAUDE.md · 221 lines

How it starts

The opening of the file, as written. The whole thing — 221 lines — stays where its author put it; the contents beside it link to each section on GitHub.

uc-mcp-proxy

MCP stdio-to-Streamable-HTTP proxy with Databricks OAuth.

Commands

  • uv sync — install all dependencies (including dev)
  • make test / make test-unit — run unit tests only (default, what CI runs)
  • make test-cov — unit tests with coverage
  • make test-integration — run integration tests only (fires real Databricks auth, can open a browser)
  • make test-all — run unit + integration
  • make check — ruff lint + ruff format-check + mypy
  • make fmt — auto-format and fix lint
  • uv build — build sdist + wheel into dist/

Test policy

Integration tests intentionally exercise the real preflight auth flow, including databricks auth login (which pops a browser). They must never run in CI and should not be the default target. make test runs unit tests only to match CI.

Two things the suite quietly depends on:

  • Every test file must declare pytestmark. make test is pytest -m unit, and an unmarked test is silently deselected — no warning, and --strict-markers only validates markers that are present. A new file with no marker makes "tests green" mean nothing. The deselected count is an assertion: it should stay at 8.
  • --tb=short in addopts is load-bearing, not cosmetic. A long traceback from inside exchange_pat would dump its locals, which include a live PAT.

Architecture

Package in src/uc_mcp_proxy/:

  • __main__.py — CLI entry point, DatabricksAuth (httpx auth flow), bridge() (bidirectional stdio↔HTTP stream copy), run() (async main)
  • auth.py — credential preflight, auto-login, auth-type-specific remediation
  • errors.py — HTTP error diagnosis and reporting from the remote server
  • token_exchange.py — RFC 8693 exchange of a PAT for an app-scoped OAuth token
  • app_discovery.py — App-host / classic-PAT detection and lookup of an app's oauth2_app_client_id + scopes from workspace metadata (drives auto-exchange)
  • _compat.py — MCP SDK major-version shim (see below)
  • __init__.py — re-exports DatabricksAuth

Read the full file on GitHub · 221 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. 8d ago First seen · 221 lines · 2,876 tokens per session scan A 281bc85bf7a6

Subscribe to this mod's changes

uc-mcp-proxy CLAUDE.md is an instructions file published in the GitHub repository IceRhymers/uc-mcp-proxy (5 stars, last pushed 1mo ago), licensed MIT. It adds 2,876 tokens to every session, about $0.0144 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.

Related

Other instructions, from other repositories

vibe-coding-prompt-template backend.instructions.md

Instructions for KhazP/vibe-coding-prompt-template: Read AGENTS.md, agentdocs/techstack.md, and agentdocs/codepatterns.md.

KhazP/vibe-coding-prompt-template · 139 tokens

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