What is openair-3-mcp-server-oss CLAUDE.md?

Instructions for an MCP server that connects AI assistants to R's openair package, a toolkit for analysing air-quality and atmospheric data. It describes how the server discovers tools from R scripts and the data formats those tools accept.

Use it when building, extending, or connecting to openair tools for CSV, public-data, time-series, wind, or trajectory analysis.

It gives developers the boundaries and expected input types needed to extend or use the server correctly.

How miguel-escribano/openair-3-mcp-server-oss configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to miguel-escribano/openair-3-mcp-server-oss. 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/miguel-escribano/openair-3-mcp-server-oss/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/miguel-escribano/openair-3-mcp-server-oss

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/miguel-escribano/openair-3-mcp-server-oss/claude-md/github.svg)](https://agentmods.dev/instructions/miguel-escribano/openair-3-mcp-server-oss/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/miguel-escribano/openair-3-mcp-server-oss/claude-md"><img src="https://agentmods.dev/badge/instructions/miguel-escribano/openair-3-mcp-server-oss/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/miguel-escribano/openair-3-mcp-server-oss/claude-md"><img src="https://agentmods.dev/badge/instructions/miguel-escribano/openair-3-mcp-server-oss/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,023 This file is loaded in full into every session.

When invoked 1,023 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	$0.01023	$0.01023
Opus 5	$0.00511	$0.00511
Sonnet 5	$0.00205	$0.00205
Haiku 4.5	$0.00102	$0.00102

Measured 11d ago against content hash 2705f4feb38c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

openair-3-mcp-server-oss 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 11d 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 · 103 lines

How it starts

The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.

openair-3-mcp — agent notes

MCP server (FastMCP 3.x) wrapping the R openair package. See README.md for full tool catalogue and setup.

References

openair R package: https://github.com/openair-project/openair
openair reference: https://openair-project.github.io/openair/reference/index.html
openair book: https://github.com/openair-project/book/
FastMCP docs: https://gofastmcp.com/llms.txt

Architecture

Tools are auto-discovered at startup from r/scripts/. Each .R file with a valid # MANIFEST: header becomes one MCP tool. No Python change needed to add a tool.

server.py → scans r/scripts/ → parses manifests → mcp.add_tool() per script.

Boundaries

Generic openair MCP — CSV, public imports, SeriesV1 JSON. No vendor-specific integrations.
Any MCP client connects via HTTP/SSE endpoint (+ optional token).

Input/output types

`input_type` in manifest	Pydantic class	Use for
`series`	`SeriesV1`	All non-wind tools
`wind_series`	`WindSeriesV1`	Polar/directional tools
`traj_series`	`TrajSeriesV1`	Trajectory tools
`import_params`	`ImportParamsV1`	Import tools

`output_type`	Return value	Use for
`image`	`ToolResult([summary text, Image])` → MCP `[text, image]`	All plot tools
`stats`	`dict` (JSON)	Stats/utility tools
`series`	`dict` (SeriesV1-shaped JSON)	Import tools

Built-in documentation tools

openair_docs() returns official documentation entry points:
- package repo
- reference index
- openair book (repo + published site)
openair_function_help(function_name) returns canonical URLs for one function.
prepare_series_for_openair(data, ...) prepares aligned deterministic timestamps/values before plotting. Data must come from load/upload/import tools or json_exports from another MCP — never client-built arrays.
load_series_from_upload(content_base64, file_type, ...) parses CSV/xlsx uploaded as base64 (max 1 MB raw; see INGEST_MAX_BYTES in openair_mcp/utils.py).

Read the full file on GitHub · 103 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.

11d ago First seen · 103 lines · 1,023 tokens per session scan A 2705f4feb38c

Subscribe to this mod's changes

openair-3-mcp-server-oss CLAUDE.md is an instructions file published in the GitHub repository miguel-escribano/openair-3-mcp-server-oss (0 stars, last pushed 9d ago), licensed MIT. It adds 1,023 tokens to every session, about $0.0051 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.

Scientific

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

openair-3-mcp-server-oss: Instructions file for Claude Code