What is missive-mcp CLAUDE.md?

A repository guide for Claude Code and other AI contributors. It explains the project's MCP server, which lets AI assistants work with the Missive messaging service through defined tools.

Understanding the repository structure and coding conventions, checking required safeguards, and making compatible changes to its Missive integration.

It puts the project's rules and design decisions in one place before code is changed. It also highlights safety limits, such as not sending external messages or adding deletion tools.

How kanjidoc/missive-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to kanjidoc/missive-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/kanjidoc/missive-mcp/main/CLAUDE.md

Clone the repo

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

Your own site

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

Per session 2,567 This file is loaded in full into every session.

When invoked 2,567 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	$0.02567	$0.02567
Opus 5.5	$0.01027	$0.01027
Sonnet 5.5	$0.00513	$0.00513
Haiku 4.5	$0.00257	$0.00257

Measured 1mo ago against content hash 8d2d93d21926, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

missive-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 1mo 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 · 177 lines

How it starts

The opening of the file, as written. The whole thing — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Guidance for Claude Code (and any AI agent or contributor) working in this repository. This file is committed on purpose — it contains no secrets, only project conventions. The credential lives only in .env, which is gitignored.

What this is

A Model Context Protocol (MCP) stdio server that exposes the Missive REST API as 36 tools for AI assistants (Claude Desktop, Claude Code). Tools are prefixed missive_. It is modeled on the FreshBooks-MCP project but has no OAuth layer — Missive uses a static personal access token.

Non-negotiables (read before editing)

Never send external email/SMS. Sending in Missive is the send / send_at / auto_followup flags on the drafts endpoint. src/tools/drafts.ts must never expose or set them. test/tools.test.ts asserts the draft body contains none of these keys — keep it green.
No delete tools. There is no DELETE in the client's HttpMethod union, so a delete call won't even type-check. Don't add one without explicit owner sign-off.
Internal posts and conversation merge ARE allowed (missive_create_post, missive_merge_conversations) — they act only within Missive. Merge is irreversible and annotated destructiveHint: true.
Never write to stdout. This process speaks MCP JSON-RPC over stdout; a single stray byte corrupts the stream. Only console.error (stderr) is safe. src/load-env.ts uses dotenv … { quiet: true } for exactly this reason.
Read MISSIVE_API_TOKEN lazily, never at import time, so tests can run without it (getApiToken() in src/missive-client.ts).
CommonJS build. tsconfig is module:"commonjs", target:"ES2022", no "type":"module" in package.json. The reused require("../package.json") (version.ts) and __dirname (load-env.ts) depend on this.
No any. @typescript-eslint/no-explicit-any is enabled for src/.

Architecture

Read the full file on GitHub · 177 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.

1mo ago Changed · +32 lines · +525 tokens per session 8d2d93d21926
2mo ago First seen · 145 lines · 2,042 tokens per session scan A 3709c5b8e3fd

Subscribe to this mod's changes

missive-mcp CLAUDE.md is an instructions file published in the GitHub repository kanjidoc/missive-mcp (1 stars, last pushed 1mo ago), licensed MIT. It adds 2,567 tokens to every session, about $0.0103 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.

missive-mcp CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
missive-mcp CLAUDE.mdkanjidoc/missive-mcp	Instructions file	1	1mo ago	MIT	A	2,567	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

missive-mcp: Instructions file for Claude Code