What is abis-mcp CLAUDE.md?

Project instructions for an ABIS MCP server, a service that gives coding agents access to tools through the Model Context Protocol. They describe its commands, structure, security, and important files.

Developing, reviewing, or debugging the ABIS MCP server, including its Node.js entry point, API wrapper, tools, database connection, and access controls.

They give an agent the project context needed to work safely and consistently, including how the server runs, authenticates requests, and stores data.

How cijlabs/abis-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to cijlabs/abis-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/cijlabs/abis-mcp/master/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/cijlabs/abis-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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/cijlabs/abis-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/cijlabs/abis-mcp/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/cijlabs/abis-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/cijlabs/abis-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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/cijlabs/abis-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/cijlabs/abis-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 689 This file is loaded in full into every session.

When invoked 689 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.

Model	Per session	Once invoked
Fable 5.1	$0.00689	$0.00689
Opus 5.5	$0.00276	$0.00276
Sonnet 5.5	$0.00138	$0.00138
Haiku 4.5	$0.00069	$0.00069

Measured 2mo ago against content hash 094c49ce7e35, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

abis-mcp 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 2mo 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 · 65 lines

How it starts

The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ABIS MCP Server

Overview

MCP (Model Context Protocol) server for ABIS. 37 tools v3.5.0, dual-mode SSE + stdio, raw Node.js (ESM), deployed on Railway.

Commands

npm install        # Install dependencies
npm run dev        # Start with --watch (port 3100)
node index.js      # Start MCP server (stdio mode)

Architecture

Transport: Dual-mode — SSE (HTTP for Railway) + stdio (for Claude Desktop/Code)
Backend: Proxies to Railway FastAPI at RAILWAY_URL
Persistence: MongoDB Atlas via MONGODB_URI
Auth: ABIS_ADMIN_KEY sent as X-Admin-Key (GET) and X-API-Key (POST)

Security

Per-tool auth gates (free/pro/admin tiers)
Input validation with 11-model allowlist
Per-key rate limits: free=30, pro=120, admin=300 req/min
Hono CVE patched

Key Files

index.js           # Entry point, registers all 37 tools
config.js          # Environment variable exports
db.js              # MongoDB connection, index creation
api.js             # Railway API fetch wrapper (10s timeout)
tools/*.js         # One file per tool (37 files)

MongoDB Collections

mcp_sessions — Session starts (ambient_status)
mcp_message_scores — Scored messages with drift + whisper level
mcp_conversation_logs — Conversation turns with drift scores
mcp_benchmark_triggers — Benchmark run triggers

Known API Quirks

/drift/all returns empty — use /aggregate instead
/scorecard/all returns no_data — use /scorecard/latest/{model}
POST endpoints require X-API-Key; GET endpoints use X-Admin-Key (same key value)
/version-changes returns 404 (not deployed)

Drift Thresholds

<0.40: stable (green)
0.40-0.65: monitor (yellow)
0.65-0.90: alert (red)
0.90: critical — likely baseline issue, not genuine drift

Monitored Models (11)

gpt-4o, claude-opus-4.6, claude-sonnet-4.5, claude-haiku-4.5, deepseek-v3.2, deepseek-r1, gpt-5.2, gpt-5.2-instant, gemini-2.5-pro, gemini-2.5-flash, gemini-3-flash

Deploy

Railway project: loyal-victory URL: https://abis-mcp-production.up.railway.app Known issue: healthcheck failing on commit f968a60, last working deploy was 3266bb5

Read the full file on GitHub · 65 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.

2mo ago First seen · 65 lines · 689 tokens per session scan A 094c49ce7e35

Subscribe to this mod's changes

abis-mcp CLAUDE.md is an instructions file published in the GitHub repository cijlabs/abis-mcp (1 stars, last pushed 8d ago), licensed MIT. It adds 689 tokens to every session, about $0.0028 per session on Opus 5.5. 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.

abis ai-monitoring behavioral-intelligence claude deepseek drift-detection

abis-mcp CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
abis-mcp CLAUDE.mdcijlabs/abis-mcp	Instructions file	1	8d ago	MIT	A	689	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

abis-mcp: Instructions file for Claude Code

Borrowing it

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

ABIS MCP Server

Overview

Commands

Architecture

Security

Key Files

MongoDB Collections

Known API Quirks

Drift Thresholds

Monitored Models (11)

Deploy

What this file has done since we first saw it

abis-mcp CLAUDE.md compared with instructions from other repositories