What is mcp-server CLAUDE.md?

A set of project instructions for maintaining the AIPost MCP server, a tool that lets coding agents work with AIPost. It covers version updates, Smithery deployment settings, Windows setup, and sender filtering.

Use it when changing the server version, publishing through Smithery, adding environment settings, or configuring sender blacklists and whitelists.

It keeps version numbers and deployment settings consistent, reducing stale releases and configuration mistakes. It also records a Windows-specific installation problem and its workaround.

mcp-server CLAUDE.md — Instructions file for coding agents by AIPOST-EMAIL: A set of project instructions for maintaining the AIPost…

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods

npx agentmods add instructions/aipost-email/mcp-server/claude-md

Clone the repo

git clone --depth 1 https://github.com/AIPOST-EMAIL/mcp-server

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/aipost-email/mcp-server/claude-md.svg)](https://agentmods.dev/instructions/aipost-email/mcp-server/claude-md)

Your own site

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

Per session 996 This file is loaded in full into every session.

When invoked 996 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	$0.00996	$0.00996
Opus 5	$0.00498	$0.00498
Sonnet 5	$0.00199	$0.00199
Haiku 4.5	$0.00100	$0.00100

Measured yesterday against content hash 8bad75df2c88, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

mcp-server 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 · 72 lines

How it starts

The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — AIPost MCP Server

Version management

The canonical version is only in package.json:3 ("version": "1.1.6"). No other file hardcodes it.
smithery.yaml MUST be updated every release. The npx arg pins the version explicitly (@aipost/[email protected]). Without a version tag, Smithery's npx cache can serve a stale old version indefinitely — this is why Smithery was stuck on 1.1.1 while npm had 1.1.6.
After pushing smithery.yaml changes, rebuild the Smithery deployment on smithery.ai. Smithery reads smithery.yaml at deploy time, not at runtime.

Smithery configSchema

smithery.yaml defines a configSchema that prompts each user for values on the Smithery deployment page.
Adding a new env var that users should configure → add a field to configSchema.properties AND wire it into commandFunction's env object.
Changing commandFunction does NOT take effect until the deployment is rebuilt on Smithery.
Example: AIPOST_SENDER_WHITELIST is exposed as aipostSenderWhitelist in the schema.

Windows caveat

On Windows, npx -y @aipost/mcp-server fails because the mcp-server bin entry is not found (shebang issue).
- Workaround: use the aipost-mcp bin instead: npx -y -p @aipost/mcp-server aipost-mcp
This affects local development on Windows; Smithery runs Linux so it's not affected there.

Sender filter (blacklist / whitelist)

Controlled by two env vars: AIPOST_SENDER_WHITELIST and AIPOST_SENDER_BLACKLIST.
Whitelist takes precedence: if both are set, blacklist is ignored.
The filter applies to all mail/contact tools — inbox, outbox, threads, events, directory, send_message, reply_to, get_message, delete_message. It does NOT apply to upload_image, upload_audio, or create_blog_post (no sender/recipient).
Implementation: src/filter.ts → SenderFilter class, used in src/server.ts createAipostServer().
For local stdio MCP clients, set env vars in the MCP client config's env block.
For Smithery HTTP deployments, env vars must be configured through the configSchema flow (see above).

Read the full file on GitHub · 72 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 · +25 tokens per session 8bad75df2c88
5d ago First seen · 72 lines · 971 tokens per session scan A e7b05ba1749d

Subscribe to this mod's changes

mcp-server CLAUDE.md is an instructions file published in the GitHub repository AIPOST-EMAIL/mcp-server (0 stars, last pushed 3d ago), licensed MIT. It adds 996 tokens to every session, about $0.0050 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.

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

mcp-server CLAUDE.md