Skip to main content
Glama

medium-ops

PyPI version PyPI downloads Python 3.12+ License: MIT MCP compatible MCP Registry Anthropic DXT Glama MCP server MCP Badge

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 — install with uv / uvx, not unrelated npx packages from “Medium MCP” searches. Canonical listing: Glama — 06ketan/medium-ops.

Related MCP server: Substack-OPS

Works with (MCP)

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

Open source–oriented hosts

Host

Documentation

Typical wire-up

OpenCode

OpenCode MCP servers

uvx medium-ops mcp install opencode

Continue

Continue

uvx medium-ops mcp install print — paste the snippet into Continue’s MCP settings

Zed

Zed

Configure stdio MCP per Zed’s docs

Cline

Cline

MCP setup per extension / marketplace docs

Goose

Goose

MCP extensions per Goose docs

Large commercial stacks

Host

Documentation

Typical wire-up

Cursor

Cursor MCP

uvx medium-ops mcp install cursor

Claude (Desktop / Code)

Claude Desktop, Claude Code

mcp install claude-desktop / claude-code

GitHub Copilot

Copilot

MCP in VS Code where supported — use print + host docs

ChatGPT

OpenAI

Connector flows — often REST for tools without MCP

Google Gemini

Gemini

Gemini CLI / IDE features per Google docs

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)

Command

What it does

auth verify

Probe both integration token (/me) and sid cookie (GraphQL Viewer).

auth test

Same but exits non-zero on failure (CI-friendly).

auth setup

Interactive: paste token / sid / uid / username to .env.

Read — Stories (5)

Command

What it does

posts list [--user] [--limit]

Latest stories by a user (default: self).

posts show <id_or_url>

Story metadata (title, clap count, response count).

posts content <id> [--md]

Body HTML (or Markdown with --md).

posts search <query> [--limit]

Medium-side full-text search.

`posts publish -t "..." -f body.md [--pub] [--status draft

public

Read + Write — Responses (3)

Command

What it does

responses list <post_id> [--limit]

Top-level responses table.

responses tree <post_id> [--out file.json]

Full response + reply tree JSON.

responses add <post_id> "body" [--parent <r_id>] [--no-dry-run]

Post a response or reply.

Read + Write — Claps (2)

Command

What it does

claps count <post_id>

Total claps.

claps give <post_id> [--claps N] [--no-dry-run]

Clap 1-50 times. Dedup-protected.

Read — Discovery + Profile (5)

Command

What it does

feed list [--tab home|following|tag-{slug}] [--limit]

Reader feed.

profile me

Your full profile (GraphQL).

profile get <username>

Any user's public profile.

profile stats [--days N]

Per-post views / reads / fans (dashboard scrape).

profile publications

Publications you can publish to (integration token).

Reply engine (3)

Command

What it does

reply template <post_id> --template thanks

Rule-based replies (no LLM).

reply bulk <post_id> --out drafts.json

Draft every response to a file.

reply bulk-send drafts.json [--no-dry-run]

Post only action=approved rows. Dedup-checked.

Operations + safety (2)

Command

What it does

audit search [--kind] [--target] [--status] [--since 7d]

Query the JSONL audit log.

audit dedup-status

Counts in the dedup SQLite DB.

MCP server (3)

Command

What it does

mcp install <cursor|claude-desktop|claude-code|opencode|print> [--dry-run]

Auto-merge config into your host.

mcp serve

stdio MCP server (22 tools).

mcp list-tools

Print the tool registry.

Other (1)

Command

What it does

quickstart

Print a quickstart checklist.

Reply modes

Mode

What it does

Safety

template

YAML keyword rules under src/medium_ops/templates/*.yaml

dry-run default

bulk

LLM drafts every response to drafts.json. Edit, set action: "approved"

offline review, dedup-checked on send

bulk-send

Posts only items with action: "approved"

dry-run default; dedup DB prevents dup replies

MCP propose_reply → confirm_reply

Host LLM drafts, you approve per-item, token-gated

5-min token TTL, idempotent, no API key

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:

Tool

What it does

get_unanswered_responses

Worklist — responses where you haven't replied.

propose_reply

Dry-run only. Returns a token + payload preview.

confirm_reply

Posts the staged reply by token. Idempotent via dedup DB. Token TTL 5 min.

bulk_draft_replies / send_approved_drafts

File-based offline review loop.

audit_search / dedup_status

Read the audit log + dedup counts.

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 <token>. 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 devtools HAR export

Refreshing auth from a HAR

When cookies rotate or Medium changes a GraphQL schema, the fastest fix is:

  1. Open medium.com in Chrome with devtools → Network panel.

  2. Reproduce the failing action (publish a draft, post a response, etc.).

  3. Right-click any request → "Save all as HAR with content".

  4. medium-ops auth har ./medium.har

This:

  • merges fresh sid, uid, xsrf, cf_clearance cookies into .env (preserving everything else)

  • writes a redacted snapshot to .cache/har-snapshot.json listing every Medium GraphQL operation observed plus its request-variable / response-data key shapes — useful for diffing against the queries hard-coded in client.py to spot schema drift before users hit it.

Don't have these yet? See docs/AUTH-SETUP.md for a 5-minute browser-DevTools walkthrough. The Medium Integration Token API has been deprecated since 2023 — most users today use cookie-based auth via MEDIUM_SID.

Env vars (or ~/.cursor/mcp.json → mcpServers.medium-ops.env):

MEDIUM_INTEGRATION_TOKEN=2fb00...     # optional, for writes
MEDIUM_SID=1:...                      # optional, for reads
MEDIUM_UID=...                        # optional
MEDIUM_USERNAME=yourhandle            # optional but recommended

Architecture

mcp.json | env                  →  auth.py
                                      │
                            MediumConfig (token? sid? uid? username?)
                                      │
                                MediumClient (httpx)
                              ┌───────┼──────────┐
                              ▼       ▼          ▼
                   api.medium.com  medium.com/  medium.com/_/
                     /v1/* (REST)    _/graphql   api/* (dashboard)
                       │              │           │
                   Bearer token    sid cookie    sid cookie
                                      │
          ┌──────┬──────┬────────────┬──────┬────────┬──────────┐
          ▼      ▼      ▼            ▼      ▼        ▼          ▼
        posts  responses  claps  profile  stats  feed  reply_engine
                                                            │
                                        ┌───────────────────┼───────────────┐
                                        ▼                   ▼               ▼
                                    template            ai_bulk       MCP propose/confirm
                                        └───────────────────┬───────────────┘
                                                            ▼
                                                   base.post_response
                                                            │
                                                  ┌─────────┼─────────┐
                                                  ▼         ▼         ▼
                                                dedup     audit   dry_run
                                                (SQLite)  (jsonl)

 mcp/server.py ──── 22 tools ─── all share MediumClient

Endpoints used

Action

Method + URL

Auth: integration token

GET https://api.medium.com/v1/me

Auth: sid cookie

POST https://medium.com/_/graphql (Viewer)

User profile

POST /_/graphql (UserProfileQuery)

List stories

POST /_/graphql (UserStreamOverview)

Story metadata

POST /_/graphql (PostViewer)

Story body

POST /_/graphql (PostContent)

Story search

POST /_/graphql (SearchPosts)

Responses

POST /_/graphql (PostResponses)

Feed

POST /_/graphql (HomeFeed / FollowingFeed / TagFeed)

Publish story

POST https://api.medium.com/v1/users/{id}/posts

Publish to pub

POST https://api.medium.com/v1/publications/{pub_id}/posts

Own pubs

GET https://api.medium.com/v1/users/{id}/publications

Clap

POST https://medium.com/_/api/posts/{id}/clap (undocumented)

Post response

POST https://medium.com/_/api/posts (undocumented)

Stats

GET https://medium.com/@{username}/stats?count=... (undocumented)

Tests

uv run pytest -q

Coverage: auth loading, client transports + XSSI stripping, dedup DB, audit log search, MCP tool registry + dispatcher, MCP install host-config merging, propose/confirm flow + token expiry, reply-engine template matching + dedup+audit flow, subprocess LLM detection.

Known gaps

  • Medium stopped issuing new Integration Tokens in 2023. If you never got one, publish_post / list_own_publications will 401. The read + response + clap paths still work via sid. The RSS read path needs no credentials at all.

  • RSS is capped at ~10 posts and lacks clap/response counts and stats. When you need more, pass --source graphql (requires sid) or set --limit > 10 and the client will auto-fall back to GraphQL.

  • GraphQL operation names and schemas change silently. The queries in client.py mirror what the dashboard uses today — expect breakage every couple of months. Pin this package's version.

  • post_response uses GraphQL savePostResponse(deltas: [Delta!]!, inResponseToPostId: ID!). Delta shape is {type: 1, index: N, paragraph: {type: 1, text, markups: []}} (type=1 means insert; paragraph.type=1 is P). Reverse-engineered from error messages.

  • update_draft_content uses dashboard POST /p/{id}/deltas with {baseRev, rev, deltas}. For a brand-new draft, baseRev=-1, rev=0. Subsequent edits should bump both.

  • clap_post still uses the undocumented /_/api/posts/{id}/clap shape; not yet re-validated against the new GraphQL surface. Dry-run first.

  • Members-only stories return a paywall preview unless the sid belongs to a paying member.

  • No "restack" equivalent. Medium doesn't have reshares; the closest is a clap + a response. Use clap_post + post_response together for that.

  • No notes / short-form. Medium killed short-form in 2018.

  • Chrome cookie auto-grab (the auth_chrome flow from substack-ops) is not yet implemented. Paste your sid into .env for now.

  • TUI not yet implemented; the extras pin is there for future work.

License

MIT. See LICENSE.

Available Tools

23 tools
bulk_draft_repliesA

WRITE TO LOCAL FILE (no Medium call). Generate reply drafts for every response on a post using the daemon-path LLM. Output is JSON with action='pending'; edit to 'approved', then run send_approved_drafts.

Inputs: post_id (required), out, model.

clap_postA

WRITE. Clap a story 1-50 times. Uses the undocumented dashboard endpoint — fragile. Dedup-protected per post. Dry-run by default.

Inputs: post_id (required), claps, dry_run.

confirm_replyA

EXECUTE the staged write. Look up the token, post to Medium, log to audit.jsonl, persist dedup row. Idempotent. Tokens are single-use.

Inputs: token (required), force.

dedup_statusA

Read-only. Counts from the local dedup SQLite DB (claps, responses, publishes) used to prevent the same write running twice. Call this after writes to confirm the ledger advanced, or if a write inexplicably skipped (status='deduped' in audit_search).

Inputs: no named parameters.

get_clap_countA

Read-only. Total claps (sum across all clappers, max 50 each) on a single story. Use this for engagement checks before/after posting a response. Faster than get_post when you only need the number.

Inputs: post_id (required).

get_feedA

Read-only. Reader feed. tab='home' for recommended, 'following', or 'tag-{slug}' (e.g. 'tag-programming').

Inputs: tab, limit.

get_own_profileA

Read-only. Return the authenticated user's profile from the dashboard GraphQL API: id, username, name, bio, follower/following counts. Use this when you need 'who am I' context for downstream calls. For any other user pass the @handle to get_profile instead.

Inputs: no named parameters.

get_postA

Read-only. Story metadata by Medium post id (12+ char hex, e.g. 'a1b2c3d4e5f6'): title, url, claps, response count, publication, publishedAt. For the article body use get_post_content. For the comment thread use list_responses.

Inputs: post_id (required).

get_post_contentB

Read-only. Return the story body as HTML. Set as_markdown=true to convert to Markdown. Members-only stories need a member sid.

Inputs: post_id (required), as_markdown.

get_profileA

Read-only. Public profile for any Medium user by @username (id, name, bio, follower count). Use list_posts after this to fetch their stories. For the authed user prefer get_own_profile.

Inputs: username (required).

get_response_repliesA

Read-only. Nested replies under a single top-level response. Use list_responses first to get response ids, then call this per response to walk the thread.

Inputs: response_id (required), limit.

get_statsA

Read-only. Per-post views / reads / fans for the last N days. Requires sid cookie for dashboard access.

Inputs: days.

get_unanswered_responsesA

Read-only. Return responses on a post where the authed user has NOT yet replied. Canonical worklist: read each, draft a reply in your context, then propose_reply -> confirm_reply.

Inputs: post_id (required), limit.

list_own_publicationsA

Read-only. Publications the authed user can publish to as editor or writer. Returns id + name pairs; use the id with publish_post's publication_id to publish into a publication. Requires the Medium integration token (MEDIUM_INTEGRATION_TOKEN).

Inputs: no named parameters.

list_postsC

Read-only. List recent stories by a user (default: self).

Inputs: limit, username.

list_responsesA

Read-only. Top-level responses under a story (Medium's word for comments). Each response has its own id you can pass to get_response_replies for the reply thread. For the filtered 'still need a reply' worklist prefer get_unanswered_responses.

Inputs: post_id (required), limit.

post_responseA

WRITE. Post a top-level response under a story, or a reply under a response. Uses the undocumented dashboard endpoint — fragile. For interactive drafting prefer propose_reply -> confirm_reply. Dry-run by default.

Inputs: post_id (required), body (required), parent_response_id, dry_run.

propose_replyA

STAGE A WRITE (no Medium call yet). Validate a reply, compute its dedup hash, store it under a token, return token + preview. On approval call confirm_reply. Tokens expire in 5 minutes. Set parent_response_id to reply under a specific response; omit for a top-level response on the post.

Inputs: post_id (required), body (required), parent_response_id.

publish_postA

WRITE. Publish a story. content_format is markdown. Defaults to publish_status='draft' so nothing goes public by accident; set to 'public' or 'unlisted' to flip it. Uses the integration token and api.medium.com/v1/*. Dry-run by default.

Inputs: title (required), content_markdown (required), tags, publication_id, +4 more.

search_postsC

Read-only. Medium-side search across public stories.

Inputs: query (required), limit.

send_approved_draftsA

WRITE. Sequentially post every entry in drafts.json where action=='approved'. Honors rate_seconds throttle. Dry-run by default.

Inputs: drafts_path (required), dry_run, rate_seconds, force.

test_connectionA

Read-only. Verify both credentials (integration token + sid cookie) and return the authed user id, username, and publication count. Call this first if other tools 401.

Inputs: no named parameters.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A3.6/5.0

    Scored across 23 tools

    Disambiguation5/5

    Each tool has a clearly distinct purpose with no overlap. Read-only tools cover specific queries (e.g., get_post vs get_post_content, list_responses vs get_unanswered_responses), and write tools handle distinct actions (publishing, clapping, replying via staging/confirmation). Even similar operations are differentiated by their target or workflow.

    Naming Consistency4/5

    Most tools follow a verb_noun pattern (e.g., get_post, publish_post, confirm_reply). The outlier is bulk_draft_replies, which starts with a noun-like word instead of a clear verb. Overall, naming is predictable and readable.

    Tool Count4/5

    23 tools is on the higher side, but each tool serves a specific need in the Medium domain (reading various data, writing with different operations). The count is justified by the breadth of functionality without being excessive.

    Completeness4/5

    The tool set covers most core Medium interactions: reading posts, profiles, responses, search, stats; writing responses, publishing, clapping, drafting replies. Missing operations like editing or deleting posts are minor gaps, but the workflow for replies is thorough.

    Maintenance

    ActivityInactive
    ResponsivenessLimited data

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      A
      quality
      A
      maintenance
      One local gateway for all your MCP servers — shared by every AI coding tool (Claude, Cursor, VS Code, Codex). Set up each server once; keys stay in the OS keychain; lazy discovery keeps agent context small. Local-first, open source.
      4
      243
      MIT
    • A
      license
      A
      quality
      D
      maintenance
      One MCP that turns Claude Code into your whole dev stack by swallowing other MCP servers, delegating to Codex & Gemini on your CLI subscriptions, remembering projects in a searchable knowledge graph, and carrying setup across sessions — secret-free by design.
      23
      4
      MIT