Borrowing it
Nothing to install: this file belongs to gelse/caldav-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.
curl -O https://raw.githubusercontent.com/gelse/caldav-mcp/main/AGENTS.mdgit clone --depth 1 https://github.com/gelse/caldav-mcpWrote 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.
[](https://agentmods.dev/instructions/gelse/caldav-mcp/agents-md)<a href="https://agentmods.dev/instructions/gelse/caldav-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/gelse/caldav-mcp/agents-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.
<a href="https://agentmods.dev/instructions/gelse/caldav-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/gelse/caldav-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.02217 | $0.02217 |
| Opus 5.5 | $0.00887 | $0.00887 |
| Sonnet 5.5 | $0.00443 | $0.00443 |
| Haiku 4.5 | $0.00222 | $0.00222 |
Grade A, and why
caldav-mcp AGENTS.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.
How it starts
The opening of the file, as written. The whole thing — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — caldav-mcp
TL;DR: An MCP server that gives AI assistants read/write access to CalDAV calendars (Nextcloud, Radicale, Baikal, etc.) via 14 tools.
Project Goal
Bridge MCP-compatible AI clients (e.g. Claude, Codex) to CalDAV servers. The server is stateless — credentials travel per-request in HTTP headers — and exposes calendar operations as MCP tools over Streamable HTTP transport.
Architecture
| Component | Detail |
|---|---|
| Language | Python 3.13, Dockerized (Alpine multi-stage) |
| MCP Framework | FastMCP v3.4.7, Streamable HTTP |
| CalDAV Client | python-caldav v3.2.1 |
| iCalendar | icalendar v7.2.2 (RFC 5545) |
| Entrypoint | server.py → FastMCP HTTP on 0.0.0.0:<port>/mcp |
Project Structure
caldav-mcp/
├── server.py # Thin entrypoint, launches FastMCP
├── caldav_mcp/ # Core package
│ ├── tools/ # MCP tool handlers
│ │ ├── queries.py # Read-only tools
│ │ ├── mutations.py # Write tools
│ │ └── attendees.py # Attendee management
│ ├── app_config.py # Read-only startup config singleton (env/header/db modes)
│ ├── auth.py # Two-layer auth (API key + CalDAV creds)
│ ├── calendar.py # CalDAV calendar selection & serialization
│ ├── client_cache.py # Thread-safe LRU cache for DAVClient
│ ├── config.py # Env var parsing, header constants
│ ├── config_schema.py # Pydantic startup validation
│ ├── config_store.py # SQLite-backed configuration store
│ ├── config_cli.py # CLI for managing the config store
│ ├── config_crypto.py # Fernet encryption for stored credentials
│ ├── db_loader.py # Pro-mode DB loader (store → AppConfig + users)
│ ├── fanout.py # Fan-out executor, per-remote aggregation
│ ├── addressing.py # Dotted-path calendar addressing (pro mode)
│ ├── key_hash.py # PBKDF2-HMAC-SHA256 key hashing
│ ├── datetime_utils.py # Date/time parsing, timezone helpers
│ ├── errors.py # Typed exceptions, ToolResult dataclass
│ ├── event_builder.py # Pure iCalendar VEVENT construction
│ ├── sanitizers.py # Input sanitization, field length limits
│ ├── rate_limit.py # Sliding-window rate limiter
│ ├── audit.py # Structured JSON audit logging
│ ├── constants.py # Shared string constants
│ └── types.py # CalDAVClient Protocol definition
├── tests/ # Unit, integration, performance
├── docs/ # Architecture, API, contributing docs
├── Dockerfile # Multi-stage Docker build
├── docker-compose.yaml # Production compose (port 8600→8080)
├── docker-compose.test.yaml # Test compose with Radicale
├── requirements.txt # Runtime dependencies
├── pyproject.toml # Dev config and dependencies
└── Makefile # Build/test shortcuts
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 · +16 lines · +640 tokens per session 8b4e03344a33
- 1mo ago Changed · -2 tokens per session 496f47d88693
- 1mo ago First seen · 141 lines · 1,579 tokens per session scan A 1f89a673aded
caldav-mcp AGENTS.md is an instructions file published in the GitHub repository gelse/caldav-mcp (6 stars, last pushed today), licensed MIT. It adds 2,217 tokens to every session, about $0.0089 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.
Other instructions, from other repositories
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
vscode model-prompts.instructions.md
Model-specific prompt authoring and registry guidelines.