MCP-Access: Instructions file for Claude Code

CLAUDE.md

MCP-Access CLAUDE.md is an instructions file for Claude Code from unmateria/MCP-Access. It costs 17,437 tokens per session, scanned C, original, no licence file.

Coding-agent instructions for MCP-Access, a project that provides an MCP server with tools for connecting an agent to other systems. They describe its architecture, tools, implementation details, and data encoding.

In plain words
What is it for?
For coding tasks in the MCP-Access repository, including work on its server, tools, and encoding.
Why use it?
They give the agent project-specific rules and technical context needed to modify MCP-Access correctly.

Instructions file for Claude Code

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

This is unmateria/MCP-Access's own configuration. It tells Claude Code how to work on MCP-Access 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 MCP-Access configures →

Reuse

Borrowing it

Nothing to install: this file belongs to unmateria/MCP-Access. 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/unmateria/MCP-Access/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/unmateria/MCP-Access

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 MCP-Access CLAUDE.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/unmateria/mcp-access/claude-md"><img src="https://agentmods.dev/badge/instructions/unmateria/mcp-access/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 17,437 This file is loaded in full into every session.
When invoked 17,437 The same file — it is already loaded in full.
Security scan C 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin unknown 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 $0.17437 $0.17437
Opus 5.5 $0.06975 $0.06975
Sonnet 5.5 $0.03487 $0.03487
Haiku 4.5 $0.01744 $0.01744

Measured 5d ago against content hash dec7b05b429f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade C, and why

MCP-Access CLAUDE.md scanned grade C 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 5d 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.

Tells the agent never to refusehighAnti-refusal

Suppressing the ability to decline removes a core safety control; a later harmful request then succeeds.

### Shared opens warn, never refuse (v0.7.56)
CLAUDE.md · 1,007 lines

The source is not reproduced here

No licence file

A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.

Read it on GitHub

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. 5d ago Changed · +22 lines · +365 tokens per session dec7b05b429f
  2. 6d ago Changed · +19 lines · +232 tokens per session da3ab10fde89
  3. 29d ago Changed · +46 lines · +724 tokens per session c095d180e223
  4. 1mo ago Changed · +1 lines · +83 tokens per session dbd775623da8
  5. 1mo ago Changed · +97 lines · +1,439 tokens per session a3a47cfd1f0e
  6. 2mo ago Changed · +41 lines · +599 tokens per session 410bc40f4f5f
  7. 2mo ago Changed · +25 lines · +573 tokens per session 3dac89bac2af
  8. 2mo ago First seen · 756 lines · 13,422 tokens per session scan C 99c07a285a5d

Subscribe to this mod's changes

MCP-Access CLAUDE.md is an instructions file published in the GitHub repository unmateria/MCP-Access (61 stars, last pushed 6d ago), with no licence file. It adds 17,437 tokens to every session, about $0.0697 per session on Opus 5.5. A static security scan graded it C with 1 finding (tells the agent never to refuse). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

MCP-Access CLAUDE.md compared with instructions from other repositories

MCP-Access CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
MCP-Access CLAUDE.mdunmateria/MCP-AccessInstructions file616d agononeC17,437Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode