medium-ops

medium-ops

Standalone Medium CLI + 22-tool MCP server for Cursor MCP, Claude MCP, OpenCode MCP, and any stdio MCP host. Your IDE drafts the replies. Zero AI API keys.

Stories, responses, claps, feed, profiles, stats, reply engine, MCP server. One Python install, one binary, MIT licensed. Sibling of substack-ops.

TL;DR — MCP-native (no API key, one command)

uvx medium-ops mcp install cursor          # or claude-desktop, claude-code, opencode, print

Restart your host. Then in chat:

"list unanswered responses on post abc123def456"

"draft a warm reply to response r1"

"post that draft"

Your host's LLM (Cursor's, Claude's) does the drafting via the propose_reply / confirm_reply tools. No ANTHROPIC_API_KEY / OPENAI_API_KEY needed.

Wrong install?

This project is `medium-ops` on [PyPI](https://pypi.org/project/medium-ops/) — install with `uv` / `uvx`, not unrelated `npx` packages from “Medium MCP” searches. Canonical listing: [Glama — 06ketan/medium-ops](https://glama.ai/mcp/servers/06ketan/medium-ops).

Works with (MCP)

These rows help discovery (search keywords); confirm each host’s current MCP docs before upgrading.

Open source–oriented hosts

Large commercial stacks

OpenCode (copy-paste)

Auto-install:

uvx medium-ops mcp install opencode

Manual (~/.config/opencode/opencode.json):

{

"mcp": { "medium-ops": { "type": "local", "command": ["uvx", "medium-ops", "mcp", "serve"], "enabled": true } } }

Optional version pin: ["uvx", "medium-ops==0.1.2", "mcp", "serve"] (replace with current PyPI release).

Why a hybrid

Medium exposes three usable surfaces and we use all of them:

1. Public RSS (reads, no auth). medium.com/feed/@{user} returns the author's ~10 most recent stories with body_html, pubDate, tags, hero image, and dc:creator. Zero credentials, faster than GraphQL, stable. Used by default for list_posts / get_post / get_post_content. Inspired by Portfolio_V2's blog page.
2. Dashboard GraphQL (authenticated reads). medium.com/_/graphql + medium.com/_/api/* with the sid cookie. Used as a fallback when you ask for more than ~10 posts, when the post isn't in the RSS window, or for things RSS can't give you (responses, claps, feed, stats, search).
3. Official REST (writes). api.medium.com/v1/* with an Integration Token. Supports createPost, createPostInPublication, getUser, getPublications. That's it.

Force a specific transport with --source rss|graphql|auto on posts list, posts show, and posts content. The dashboard + GraphQL endpoints are undocumented and Medium can change them at any time. See Known gaps.

Setup (dev / from source)

git clone https://github.com/06ketan/medium-ops && cd medium-ops

uv sync uv sync --extra mcp # mcp SDK for the MCP server (recommended) uv sync --extra tui # textual for the TUI

Auth is read from ~/.cursor/mcp.json's mcpServers.medium-ops.env (or medium-api / medium). Override with env or .env.

uv run medium-ops auth verify

uv run medium-ops quickstart

Command surface

Every write defaults to --dry-run. Flip with --no-dry-run. All writes land in .cache/audit.jsonl and are dedup-checked against .cache/actions.db.

Auth (3)

Read — Stories (5)

Read + Write — Responses (3)

Read + Write — Claps (2)

Read — Discovery + Profile (5)

Reply engine (3)

Operations + safety (2)

MCP server (3)

Other (1)

Reply modes

MCP server

medium-ops mcp install opencode          # ~/.config/opencode/opencode.json

medium-ops mcp install cursor # auto-add to ~/.cursor/mcp.json medium-ops mcp install claude-desktop # auto-add to claude_desktop_config.json medium-ops mcp install claude-code # uses claude mcp add medium-ops mcp install print # print the snippet only medium-ops mcp serve # stdio server medium-ops mcp list-tools # 22 tools

Manual config snippet:

{

"mcpServers": { "medium-ops": { "command": "medium-ops", "args": ["mcp", "serve"] } } }

If the mcp SDK is not installed, the server falls back to a minimal stdin/stdout JSON-line dispatcher:

echo '{"tool":"list_posts","args":{"limit":3}}' | medium-ops mcp serve

MCP-native draft loop (no API key)

The safety + drafting stack that makes the unattended mode safe:

LLM strategy

Two layers, both free:

1. MCP-native (default). Host LLM drafts via propose_reply / confirm_reply. No env vars, no API key. Use this for interactive replies.
2. Subprocess CLI (daemon path). For reply bulk when no human is in the loop. Auto-detects claude (Claude Code), cursor-agent, or codex on PATH. Override with MEDIUM_OPS_LLM_CMD.

There is no paid-API-key path.

Auth setup

Medium has two auth layers that map to different feature surfaces:

1. Integration Token — Authorization: Bearer . Used against api.medium.com/v1/*. Gets you: publish_post, list_own_publications. Token generation at https://medium.com/me/settings → "Integration tokens". Note: Medium stopped issuing new tokens in 2023. If you never generated one, the write path will 401 and you'll have to use the sid-cookie response path for any writes.
2. sid cookie — from medium.com (Application → Cookies → sid). Used against medium.com/_/graphql and medium.com/_/api/*. Gets you: all reads (stories, responses, claps, feed, stats, profile), plus clap_post and post_response (fragile — undocumented).

medium-ops auth verify

medium-ops auth test medium-ops auth setup medium-ops auth har ./medium.har # ingest a Chrome dev