What is evite-mcp CLAUDE.md?

A set of project instructions for working on an Evite connection. It explains how the code is organized, how sign-in works, and which Evite actions are available.

Use it when developing the Evite integration, especially when handling login, browser sessions, read actions, or write actions that require confirmation.

It gives a coding assistant the repository-specific context needed to change or maintain the project correctly. Evite has no public API, so the instructions also explain its session-based access.

How chrischall/evite-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to chrischall/evite-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/chrischall/evite-mcp/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/chrischall/evite-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/chrischall/evite-mcp/claude-md.svg)](https://agentmods.dev/instructions/chrischall/evite-mcp/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/chrischall/evite-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/chrischall/evite-mcp/claude-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 3,426 This file is loaded in full into every session.

When invoked 3,426 The same file — it is already loaded in full.

Security scan A 0 findings. Scan, not verified.

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	$0.03426	$0.03426
Opus 5	$0.01713	$0.01713
Sonnet 5	$0.00685	$0.00685
Haiku 4.5	$0.00343	$0.00343

Measured yesterday against content hash 78dbbfd70a4d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

evite-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 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.

CLAUDE.md · 144 lines

How it starts

The opening of the file, as written. The whole thing — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

TL;DR

MCP server for Evite event management — talks to evite.com's internal /services/ (and /ajax/, /tsunami/) API using the session cookies a signed-in browser holds (Evite has no public API). Cookie-session archetype.

6 read tools + 13 confirm-gated write tools (plus evite_healthcheck). Writes default to a dry-run preview and only mutate on confirm: true.

Three auth tiers, in priority order:

EVITE_EMAIL + EVITE_PASSWORD — headless form login (POST /ajax_login). Preferred / documented default.
EVITE_SESSION_COOKIE — a raw cookie: header pasted from a signed-in evite.com tab (or set in CI). Used verbatim.
fetchproxy bootstrap — lifts the session out of the user's already-signed-in evite.com browser tab via a one-shot WebSocket bridge.

Auth resolution

src/auth.ts — resolveSession(): the three-path priority resolver (Pattern A, "browser-bootstrap + Node-direct"). It produces a ResolvedSession = { cookieHeader, csrfToken? }:

Tier-1 (preferred): if both EVITE_EMAIL and EVITE_PASSWORD are set → loginWithPassword() (src/auth-login.ts). One env var alone falls through.
Tier-2: EVITE_SESSION_COOKIE → returned verbatim as cookieHeader (no CSRF token surfaced).
Tier-3 (fallback): @fetchproxy/bootstrap opens a bridge to the signed-in tab, reads the declared cookies (x-evite-session, evtsession, x-evite-features, csrftoken — the declared key list is the security boundary), builds the cookie header in declaration order, and surfaces csrftoken as the CSRF token. Opt out with EVITE_DISABLE_FETCHPROXY=1.
Nothing resolves → SessionNotAuthenticatedError with a hint naming the env-var escape hatches.

src/auth-login.ts — loginWithPassword(): tier-1 form login. Evite's /ajax_login is Django CSRF-protected, so a real login is two requests: (1) a priming GET https://www.evite.com/ to obtain the csrftoken (+ anonymous) cookies, then (2) POST /ajax_login JSON { email, password } carrying the full priming jar back, the X-CSRFToken header, and an Origin/Referer. The login response's Set-Cookie (read via getSetCookie(), with a joined-header fallback) yields the authenticated jar. The password is never echoed in errors. fetchImpl is injectable for tests.

Read the full file on GitHub · 144 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.

yesterday Changed · +2 lines · +315 tokens per session 78dbbfd70a4d
6d ago First seen · 142 lines · 3,111 tokens per session scan A 84651659e6e8

Subscribe to this mod's changes

evite-mcp CLAUDE.md is an instructions file published in the GitHub repository chrischall/evite-mcp (0 stars, last pushed yesterday), licensed MIT. It adds 3,426 tokens to every session, about $0.0171 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.

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 · 5,182 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

evite-mcp: Instructions file for Claude Code