substack-publisher-mcp AGENTS.md

substack-publisher-mcp AGENTS.md is an instructions file for Codex, OpenCode from dkships/substack-publisher-mcp. It costs 735 tokens per session, scanned A, original, MIT.

An MCP server that lets coding agents work with Substack publications through the Substack Publisher API, a programmatic interface for publishing tools.

In plain words
What is it for?
It is for adding Substack publication actions to an MCP-compatible coding agent and returning structured Substack data for the agent to use.
Why use it?
It removes the need to connect to Substack manually for supported publication tasks. The instructions also define how the server validates inputs, handles errors, and keeps API keys out of source files.

Instructions file for CodexOpenCode

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/dkships/substack-publisher-mcp/agents-md
Clone the repo
git clone --depth 1 https://github.com/dkships/substack-publisher-mcp

Made for: Codex, OpenCode.

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.

agentmods badge for substack-publisher-mcp AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/dkships/substack-publisher-mcp/agents-md.svg)](https://agentmods.dev/instructions/dkships/substack-publisher-mcp/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/dkships/substack-publisher-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/dkships/substack-publisher-mcp/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 735 This file is loaded in full into every session.
When invoked 735 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.

ModelPer sessionOnce invoked
Fable 5 $0.00735 $0.00735
Opus 5 $0.00367 $0.00367
Sonnet 5 $0.00147 $0.00147
Haiku 4.5 $0.00073 $0.00073

Measured 4d ago against content hash bffcce0b62ff, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

substack-publisher-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 4d 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.

AGENTS.md · 59 lines

How it starts

The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Substack Publisher MCP — Agent Instructions

What This Is

MCP server providing Substack Publisher API access. Enables agents to interact with Substack publications programmatically.

Tech Stack

  • TypeScript, ES modules, Node 18+
  • @modelcontextprotocol/sdk with stdio transport
  • zod for input validation
  • Native fetch for Substack Publisher API calls (no HTTP framework)

Scope And Boundaries

  • This is a self-managed repo (dkships/substack-publisher-mcp)
  • Keep secrets out of committed files — env vars come from the MCP client config or shell (the server never loads .env)
  • Return raw structured data from tools — let the LLM do synthesis

Working Rules

  • All API clients in their own module under src/
  • Handle errors with isError: true responses
  • Use registerTool / registerResource for MCP registration
  • Test manually via MCP client after changes
  • Codex has an enabled found-substack MCP server pointing at dist/index.js; run npm run build after source changes before testing through Codex MCP.
  • Use inherited SUBSTACK_API_KEY_* env vars; never copy token values into config or docs.

Hallucination Prevention

See ~/.agents/AGENTS.md. For this MCP server: sources = code and Substack API responses.

Definition Of Done

  • Changes compile (npm run build)
  • Tests pass (npm test)
  • MCP server starts without errors (npm start)

Code style

Adapted from Fabien Sanglard's agent.md (2026-08-21).

  • Avoid magic numbers and strings. Extract recurring or meaningful values into named constants or enums; leave self-explanatory one-off values inline. A value defined by a spec (HTTP 200, a protocol byte) gets a constant regardless.
  • Reduce indentation. Use early returns and continue instead of nesting.
  • Keep function names under 30 characters.
  • Use an enum or a string-literal union instead of a boolean parameter.
  • Put blank lines between logical blocks. Let the reader breathe.
  • Comment what a block does and why, briefly. Use an example where it helps; offer an ASCII diagram when explaining a whole system.
  • Treat a visibility change as a breaking design shift. Keep things private or unexported unless the design requires external access, and ask before widening one.
  • Program to levels of abstraction. Low-level mechanics (raw SQL, socket streams, vendor SDK calls, file parsing) live behind a driver or service layer; callers work in domain concepts.
  • Hold the layer boundaries. Each layer talks only to the one directly below it, with no holes punched through: a UI component never calls the database or a raw HTTP client directly.
  • Don't touch code unrelated to the feature you're implementing, including adding comments to blocks you didn't write. Minimize changed lines.
  • Always use braces, even on a one-line if.
  • Fixing a bug: write the failing test first, watch it fail, then write the fix and watch it pass.

Read the full file on GitHub · 59 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.

  1. 4d ago First seen · 59 lines · 735 tokens per session scan A bffcce0b62ff

Subscribe to this mod's changes

substack-publisher-mcp AGENTS.md is an instructions file published in the GitHub repository dkships/substack-publisher-mcp (6 stars, last pushed 11d ago), licensed MIT. It adds 735 tokens to every session, about $0.0037 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.

Related

Other instructions, from other repositories

builtwith-api CLAUDE.md

Claude Code instructions for zcaceres/builtwith-api, covering claude.md — builtwith-api, project overview, tech stack, key conventions and commands.

zcaceres/builtwith-api · 713 tokens

tray-api-ai-plugin AGENTS.md

Instructions for tray-tecnologia/tray-api-ai-plugin, covering tray api plugin, regras obrigatórias para toda sessão, autenticação, url e formato and rate limit.

tray-tecnologia/tray-api-ai-plugin · 2,529 tokens

tray-api-ai-plugin copilot-instructions.md

Instructions for tray-tecnologia/tray-api-ai-plugin, covering tray api plugin, regras obrigatórias para toda integração tray, autenticação oauth 2.0, formato de requisições and rate limit.

tray-tecnologia/tray-api-ai-plugin · 1,646 tokens

tray-api-ai-plugin CLAUDE.md

Instructions for tray-tecnologia/tray-api-ai-plugin, covering tray api plugin — contexto para claude, regras obrigatórias, bloco mandatory e lint de skills, validação local and busca em docs.

tray-tecnologia/tray-api-ai-plugin · 1,730 tokens

developer AGENTS.md

AGENTS.md instructions for smarterweather/developer, covering agents.md — smarter weather developer platform, surfaces, preferred onboarding path, auth and errors and docs.

smarterweather/developer · 686 tokens

wpconvert-devtools AGENTS.md

AGENTS.md instructions for FTWAgency/wpconvert-devtools, covering contributor instructions (wpconvert-devtools), source of truth, validation, secrets and what does not belong here.

FTWAgency/wpconvert-devtools · 413 tokens