Tumblr MCP Server
Posts, queue and asks on your Tumblr blogs, worked by your agent.
Hosted MCP Server
npx add-mcp 'https://cotlet.dev/mcp/v1/tumblr'Installs into Claude Code, Codex, Cursor and more
Documentation
Cotlet · Integrations · How it works · Security · For developers · For automation agencies · Blog · API docs · Help center · Changelog · Contact · Pricing · Sign up
Tumblr API and MCP server
Tumblr has a full public API v2 with OAuth for posts, queue, drafts, submissions, follows and notes, but no official MCP server (checked 17 Oct 2026). You register an app to get a key, and each app key is capped at 1,000 calls an hour and 5,000 a day.
Posts, queue and asks on your Tumblr blogs, worked by your agent. Use it in ChatGPT, Claude or any AI agent over MCP, or in n8n, Make and scripts over REST.
Blogging network where people post text, photos and links, reblog each other, take questions in an inbox and line posts up in a queue.
What is the Tumblr API?
Cotlet's Tumblr API exposes 15 endpoints for your own Tumblr account: list blogs, get blog, list posts, get post, list queue, list drafts, list asks, get post notes, create post, edit post, reblog post, answer ask, delete ask, delete post and follow blog. The list_blogs endpoint returns blogs your Tumblr account can post to, with name, title and URL. Each endpoint takes simple JSON inputs like blog, post_id or limit and works both as an operation of the tumblr_read or tumblr_write MCP tool for agents and as a REST call for scripts.
- Category: Creators & communities
- Endpoints: 15 (8 read, 7 write)
- Updated: 2026-11-10
Tumblr has a full public API v2 with OAuth for posts, queue, drafts, submissions, follows and notes, but no official MCP server (checked 17 Oct 2026). Cotlet is a hosted MCP server and REST API for Tumblr with 15 endpoints (8 read, 7 write): you sign in once in your own cloud browser, your AI agent does the work.
Does Tumblr have an official API?
Tumblr has a full public API v2 with OAuth for posts, queue, drafts, submissions, follows and notes, but no official MCP server (checked 17 Oct 2026). You register an app to get a key, and each app key is capped at 1,000 calls an hour and 5,000 a day.
| Task | Tumblr official | Cotlet |
|---|---|---|
| Create a post | Yes: Tumblr API, NPF post format; you build the content blocks yourself | Yes |
| Schedule a post or add it to the queue | Yes: Tumblr API: state queue, with publish_on for a set time | Yes |
| Edit or delete a post | Yes: Tumblr API; editing works on posts created in NPF and on legacy text posts | Yes |
| Reblog a post | Yes: Tumblr API; needs the parent blog UUID, post ID and reblog key | Yes |
| Read the queue and drafts | Yes: Tumblr API, OAuth, 20 posts per page | Yes |
| Read the ask inbox | Partly: Tumblr API lists submissions; the docs have no dedicated method to reply | Yes |
| Follow a blog | Yes: Tumblr API, up to 200 follows a day | Yes |
| Read notes on a post | Yes: Tumblr API, modes for likes, reblogs and replies | Yes |
Sources: Tumblr API v2 documentation, Tumblr API documentation source on GitHub, Tumblr Help: Queued posts, Zapier: Tumblr triggers and actions
Quick reference
Tumblr has a full public API v2 with OAuth for posts, queue, drafts, submissions, follows and notes, but no official MCP server (checked 17 Oct 2026). You register an app to get a key, and each app key is capped at 1,000 calls an hour and 5,000 a day.
Cotlet provides a hosted MCP server and REST API for Tumblr: 15 tools (8 read, 7 write).
Access Sign up at https://cotlet.dev/app/signup?app=tumblr and request the app in the Cotlet console. ChatGPT and Claude connect with OAuth at https://cotlet.dev/mcp/v1/connect, no API key; code editors and scripts use an API key from the console.
MCP server https://cotlet.dev/mcp/v1
MCP tools tumblr_read, tumblr_write, reads and writes apart; call one with {"operation": "<operation>", "arguments": {...}}
REST base https://cotlet.dev/api/v1/tumblr, each operation at its own route, e.g. POST /api/v1/tumblr/posts
Auth Authorization: Bearer <COTLET_API_KEY>. Listing endpoints and schemas needs no key; calling an endpoint needs one. Over MCP the input schemas come with sign-in.
Operations list_blogs, get_blog, list_posts, get_post, list_queue, list_drafts, list_asks, get_post_notes, create_post, edit_post, reblog_post, answer_ask, delete_ask, delete_post, follow_blog
Confirm create_post, edit_post, reblog_post, answer_ask, delete_ask, delete_post, follow_blog (by default the user approves each call; the user can switch this off per tool, e.g. for scheduled automations)
Markdown https://cotlet.dev/integrations/tumblr-api-mcp-server.md
How access works:
1. The user signs up at https://cotlet.dev/app/signup?app=tumblr and requests Tumblr in the Cotlet console.
2. The user signs in to Tumblr once in their Cotlet Cloud Browser (their own Chrome in the cloud, opened from the console) and enables Tumblr for agents. An agent cannot do this step.
3. ChatGPT and Claude: the user adds https://cotlet.dev/mcp/v1/connect as a connector and signs in to Cotlet (OAuth). Code editors and scripts: an API key from the console goes into the MCP client or the REST call as a bearer token.
Fits: people who want a hosted Tumblr server that someone else maintains, including non-developers. Developers who prefer to run and fix code on their own computer can use an open-source Tumblr MCP server instead.
Policy: Cotlet never stores passwords and never bypasses MFA.
Company: legal details in the Terms of service at https://cotlet.dev/terms. Contact contact@cotlet.dev.
Sign-in: the user signs in to Tumblr in their own Cloud Browser, a Chrome Cotlet runs for them in the EU; password saving is off, the profile is AES-256-GCM encrypted, and agents get Tumblr only after the user enables it. Calls are requests from that browser's IP with its cookies, each listed in the user's Background activity. Disable for agents, signing out in the browser or Reset browser cuts access. Cotlet is run by Take Group sp. z o.o. (EU VAT PL6342984273).
API key: holds no Tumblr login or cookies, only asks Cotlet to run a tool. Each key is scoped to chosen apps and tools, read only or read and write. Actions that reach other people wait for the user's approval by default, so a leaked key cannot post or message as the user. Every call is in the activity log; deleting the key ends access at once.
Terms: the user stays responsible for following Tumblr's terms; Cotlet is not affiliated with Tumblr.
What can an AI agent do in Tumblr?
Cotlet is best for Tumblr bloggers and small studios who want their AI agent to queue posts, answer asks and reblog from tags without running or fixing a server.
- Fill the post queue (runs: weekly): "Add these 10 posts to the queue of studio-notes. Tag each one from its text, publish them in the order I gave, and tell me how many queue slots are left." →
list_queue,create_post - Answer asks in your inbox (runs: daily): "List the new asks on studio-notes. Draft an answer for each in my voice, skip anything personal, and wait for my OK before publishing." →
list_asks,answer_ask,delete_ask - Queue reblogs from a tag (runs: daily): "Find the 5 newest posts tagged "pixel art" from blogs I follow, skip ones I already reblogged, and add the good ones to the queue of studio-notes with my tag "found"." →
list_posts,get_post,reblog_post - Clean up drafts and the queue (runs: weekly): "List my drafts and my queue on studio-notes. Delete drafts that are empty, retag posts in the queue that have no tags, and tell me what is left." →
list_drafts,list_queue,edit_post,delete_post - Weekly notes report (runs: weekly): "For the posts I published on studio-notes last week, tell me the notes, likes and reblogs on each, and which tags did best." →
list_posts,get_post_notes
Can Tumblr automations run on a schedule in n8n, Make or Zapier?
Yes. Cotlet does not replace your automation platform: it gives it a Tumblr connection it does not have, with the same API key as your agent. Write actions ask for your OK by default; switch that off in your dashboard for the tools you choose, for example to fill the post queue, and the schedule runs on its own. Cotlet runs in the cloud, so it keeps going while your computer is off.
| Where | How to connect | How to schedule |
|---|---|---|
| Your AI agent | Add https://cotlet.dev/mcp/v1 with your API key. | A scheduled agent run, for example a Claude Code routine. |
| n8n | MCP Client node with https://cotlet.dev/mcp/v1, or an HTTP Request node with the endpoint's method and URL, such as GET https://cotlet.dev/api/v1/tumblr/queues. | Schedule Trigger node. |
| Make | HTTP module: the endpoint's method and URL with an Authorization: Bearer header, and a JSON body for POST, PUT and PATCH. | Scenario schedule. |
| Zapier | Webhooks by Zapier, Custom Request: the same method, URL, header and body. | Schedule by Zapier trigger. |
| Your own script | GET https://cotlet.dev/api/v1/tumblr/queues with your API key. | cron or GitHub Actions. |
Tools
For AI agents: Every endpoint and its schema is public. The 15 endpoints on this page, with parameters and example responses, can be listed without an account. Calling one returns 401 without an API key and 403 while the key has no access to Tumblr.
list_blogs
Blogs your Tumblr account can post to, with name, title and URL. Access: read. REST: GET /api/v1/tumblr/blogs. MCP: tumblr_read → list_blogs.
No parameters.
Returns every blog on the signed-in account, the primary blog first. Use the name field as the blog parameter of the other endpoints. Posts is the count Tumblr shows on the blog.
Example response:
{
"blogs": [
{
"name": "studio-notes",
"title": "Studio notes",
"url": "https://studio-notes.tumblr.com",
"primary": true,
"posts": 1840
},
{
"name": "studio-sketches",
"title": "Sketches",
"url": "https://studio-sketches.tumblr.com",
"primary": false,
"posts": 212
}
]
}
get_blog
Title, description and ask settings of one blog. Access: read. REST: GET /api/v1/tumblr/blog. MCP: tumblr_read → get_blog.
| Parameter | Type | Required | Description |
|---|---|---|---|
blog | string | yes | Blog name, e.g. 'studio-notes' for studio-notes.tumblr.com. Names come from list_blogs. |
Returns the blog title, description, post count and whether asks and anonymous asks are on. It also returns how many posts wait in the queue and how many drafts there are, so you can see room left before the 1,000-post queue limit.
Example response:
{
"blog": "studio-notes",
"title": "Studio notes",
"description": "Ink drawings and prints.",
"posts": 1840,
"asks_open": true,
"anonymous_asks": true,
"queued": 14,
"drafts": 6
}
list_posts
Posts on a blog or under a tag, newest first. Access: read. REST: GET /api/v1/tumblr/posts. MCP: tumblr_read → list_posts.
| Parameter | Type | Required | Description |
|---|---|---|---|
blog | string | yes | Blog name, e.g. 'studio-notes' for studio-notes.tumblr.com. Names come from list_blogs. |
tag | string | no | Read posts under this tag instead of the blog own posts. |
visibility | enum | no | published or private. Default: published. |
limit | integer | no | 1 to 20. Default: 20. |
cursor | string | no | Next page cursor from the previous call. |
Lists published posts of one blog, newest first. Set tag to read posts under a tag instead, from any public blog, and set private to read your private posts. Pages hold up to 20 posts; pass next_cursor back as cursor for the next page. Each item has the post text, tags, note count and the reblog key that reblog_post needs.
Example response:
{
"posts": [
{
"post_id": "7712345600123",
"blog": "pixel-lab",
"type": "image",
"summary": "Harbor town sprite sheet",
"tags": [
"pixel art",
"sprites"
],
"note_count": 842,
"published_at": "2026-10-16T18:40:00Z"
}
],
"next_cursor": "eyJvZmZzZXQiOjIwfQ"
}
get_post
One post with its full content, tags and trail. Access: read. REST: GET /api/v1/tumblr/posts/{post_id}. MCP: tumblr_read → get_post.
| Parameter | Type | Required | Description |
|---|---|---|---|
blog | string | yes | Blog name, e.g. 'studio-notes' for studio-notes.tumblr.com. Names come from list_blogs. |
post_id | string | yes | Post ID from list_posts, list_queue or list_drafts. |
Returns the whole post: text blocks, image and link blocks, tags, state and, for a reblog, the trail of earlier posts. Use it before edit_post or reblog_post to see what a post holds.
Example response:
{
"post_id": "7712345600123",
"blog": "pixel-lab",
"state": "published",
"content": [
{
"type": "text",
"text": "Harbor town sprite sheet, 16 colors."
},
{
"type": "image",
"alt": "Sprite sheet of a harbor town"
}
],
"tags": [
"pixel art",
"sprites"
],
"note_count": 842,
"url": "https://pixel-lab.tumblr.com/post/7712345600123"
}
list_queue
Posts waiting in the queue, in publishing order, with their Queue settings. Access: read. REST: GET /api/v1/tumblr/queues. MCP: tumblr_read → list_queue.
| Parameter | Type | Required | Description |
|---|---|---|---|
blog | string | yes | Blog name, e.g. 'studio-notes' for studio-notes.tumblr.com. Names come from list_blogs. |
limit | integer | no | 1 to 20. Default: 20. |
cursor | string | no | Next page cursor from the previous call. |
Lists queued posts in the order Tumblr will publish them, 20 per page. Posts scheduled for a set time show publish_on; the rest follow the blog Queue settings, which come back as queue_settings. Tumblr holds at most 1,000 queued posts and publishes at most 50 a day.
Example response:
{
"queue_settings": {
"posts_per_day": 3,
"window": "09:00-21:00"
},
"queued": 14,
"posts": [
{
"post_id": "771204518830",
"summary": "New print: harbor at dawn",
"tags": [
"studio notes",
"print"
],
"publish_on": null
}
],
"next_cursor": null
}
list_drafts
Drafts on a blog, newest first. Access: read. REST: GET /api/v1/tumblr/drafts. MCP: tumblr_read → list_drafts.
| Parameter | Type | Required | Description |
|---|---|---|---|
blog | string | yes | Blog name, e.g. 'studio-notes' for studio-notes.tumblr.com. Names come from list_blogs. |
limit | integer | no | 1 to 20. Default: 20. |
cursor | string | no | Next page cursor from the previous call. |
Lists drafts of one blog, newest first, 20 per page. A queued post that fails to publish ends up here. Use post_id with edit_post to move a draft into the queue.
Example response:
{
"drafts": [
{
"post_id": "771198400021",
"summary": "(no text)",
"tags": [],
"saved_at": "2026-10-12T20:11:00Z"
}
],
"next_cursor": null
}
list_asks
Asks waiting in the blog inbox, oldest first. Access: read. REST: GET /api/v1/tumblr/asks. MCP: tumblr_read → list_asks.
| Parameter | Type | Required | Description |
|---|---|---|---|
blog | string | yes | Blog name, e.g. 'studio-notes' for studio-notes.tumblr.com. Names come from list_blogs. |
limit | integer | no | 1 to 20. Default: 20. |
cursor | string | no | Next page cursor from the previous call. |
Lists asks in the inbox of one blog, oldest first. Each has the text, the sender name or anonymous: true, and the time received. An anonymous ask can only get a public answer. Tumblr may not deliver asks over 500 characters, so a long ask can be missing.
Example response:
{
"asks": [
{
"ask_id": "ask_5521e0",
"from": null,
"anonymous": true,
"text": "What paper do you use for ink?",
"received_at": "2026-10-16T21:03:00Z"
},
{
"ask_id": "ask_5521e1",
"from": "pixel-lab",
"anonymous": false,
"text": "Would you take a commission for a poster?",
"received_at": "2026-10-17T07:15:00Z"
}
],
"next_cursor": null
}
get_post_notes
Likes, reblogs and replies on one post. Access: read. REST: GET /api/v1/tumblr/posts/{post_id}/notes. MCP: tumblr_read → get_post_notes.
| Parameter | Type | Required | Description |
|---|---|---|---|
blog | string | yes | Blog name, e.g. 'studio-notes' for studio-notes.tumblr.com. Names come from list_blogs. |
post_id | string | yes | Post ID from list_posts, list_queue or list_drafts. |
mode | enum | no | all, likes, conversation, rollup or reblogs_with_tags. Default: all. |
Returns the notes on one post, newest first, with the totals. Set mode to likes, reblogs_with_tags, conversation or rollup to narrow them; all is the default. Use it for a report of what a post earned.
Example response:
{
"total_notes": 842,
"total_likes": 610,
"total_reblogs": 232,
"notes": [
{
"type": "reblog",
"blog": "tiny-pixels",
"tags": [
"pixel art"
],
"at": "2026-10-17T06:55:00Z"
}
]
}
create_post
Publish a post, add it to the queue, schedule it or save a draft. Access: write, asks the user first. REST: POST /api/v1/tumblr/posts. MCP: tumblr_write → create_post.
| Parameter | Type | Required | Description |
|---|---|---|---|
blog | string | yes | Blog name, e.g. 'studio-notes' for studio-notes.tumblr.com. Names come from list_blogs. |
content | string | yes | Post text. Links and images go in as URLs. |
tags | string[] | no | Tags without the # sign. |
state | enum | no | published, queue, draft or private. Default: published. |
publish_on | datetime | no | ISO 8601 time to publish. Only used when state is queue. |
Creates a post on your blog under your name. Set state to published (default), queue, draft or private. With state queue and no publish_on, the post joins the end of the queue and follows the blog Queue settings. With publish_on it publishes at that time. Private posts cannot be queued. A full queue or the daily limit returns an error. By default you confirm each call; you can switch that off for this tool.
Example response:
{
"post_id": "771204518830",
"blog": "studio-notes",
"state": "queue",
"publish_on": "2026-10-19T09:00:00+02:00",
"tags": [
"studio notes",
"ink",
"print"
]
}
edit_post
Change the text, tags or state of a post, or move a draft into the queue. Access: write, asks the user first. REST: PATCH /api/v1/tumblr/posts/{post_id}. MCP: tumblr_write → edit_post.
| Parameter | Type | Required | Description |
|---|---|---|---|
blog | string | yes | Blog name, e.g. 'studio-notes' for studio-notes.tumblr.com. Names come from list_blogs. |
post_id | string | yes | Post ID from list_posts, list_queue or list_drafts. |
content | string | no | New post text. Omit to keep the current text. |
tags | string[] | no | Tags without the # sign. |
state | enum | no | published, queue, draft or private. Default: published. |
publish_on | datetime | no | ISO 8601 time to publish. Only used when state is queue. |
Changes one post of yours: its text, tags or state. Set state to queue to move a draft into the queue, and publish_on to give it a set time. Editing works on posts created in the new Tumblr format and on legacy text posts. A published post changes for everyone who sees it. By default you confirm each call; you can switch that off for this tool.
Example response:
{
"post_id": "771198400021",
"blog": "studio-notes",
"state": "queue",
"tags": [
"studio notes"
]
}
reblog_post
Reblog a post to your blog now, into the queue or as a draft. Access: write, asks the user first. REST: POST /api/v1/tumblr/posts/{post_id}/reblog. MCP: tumblr_write → reblog_post.
| Parameter | Type | Required | Description |
|---|---|---|---|
blog | string | yes | Blog name, e.g. 'studio-notes' for studio-notes.tumblr.com. Names come from list_blogs. |
from_blog | string | yes | Blog the post is on, e.g. pixel-lab. |
post_id | string | yes | ID of the post to reblog, from list_posts. |
comment | string | no | Your text added on top of the post. |
tags | string[] | no | Tags without the # sign. |
state | enum | no | published, queue, draft or private. Default: published. |
hide_trail | boolean | no | true shows only your comment. Default: false. |
Reblogs a post from another blog onto yours, with your own comment and tags if you add them. The agent takes the reblog key from list_posts or get_post. Set hide_trail to show only your comment. Set state to queue to spread reblogs over the day. A reblog counts toward Tumblr's daily limit of new posts. By default you confirm each call; you can switch that off for this tool.
Example response:
{
"post_id": "771204600412",
"blog": "studio-notes",
"state": "queue",
"reblogged_from": "pixel-lab",
"tags": [
"found",
"pixel art"
]
}
answer_ask
Answer an ask from the inbox, publicly on your blog or privately. Access: write, asks the user first. REST: POST /api/v1/tumblr/asks/{ask_id}/replies. MCP: tumblr_write → answer_ask.
| Parameter | Type | Required | Description |
|---|---|---|---|
blog | string | yes | Blog name, e.g. 'studio-notes' for studio-notes.tumblr.com. Names come from list_blogs. |
ask_id | string | yes | Ask ID from list_asks. |
answer | string | yes | Answer text. |
visibility | enum | no | public or private. Default: public. Anonymous asks allow only public. |
state | enum | no | published, queue, draft or private. Default: published. |
Answers one ask. With visibility public, the answer is published to your blog with the question. With private, only the sender gets it. An anonymous ask can only be answered publicly. Set state to queue or draft to hold a public answer back. By default you confirm each call; you can switch that off for this tool.
Example response:
{
"post_id": "771205011190",
"ask_id": "ask_5521e0",
"blog": "studio-notes",
"state": "published",
"visibility": "public"
}
delete_ask
Remove an ask from the inbox without answering it. Access: write, asks the user first. REST: DELETE /api/v1/tumblr/asks/{ask_id}. MCP: tumblr_write → delete_ask.
| Parameter | Type | Required | Description |
|---|---|---|---|
blog | string | yes | Blog name, e.g. 'studio-notes' for studio-notes.tumblr.com. Names come from list_blogs. |
ask_id | string | yes | Ask ID from list_asks. |
Deletes one ask from the inbox. Tumblr cannot restore a deleted ask, so the call asks for your OK like the others. By default you confirm each call; you can switch that off for this tool.
Example response:
{
"ask_id": "ask_5521e2",
"status": "deleted"
}
delete_post
Delete one of your posts, from the queue, drafts or the blog. Access: write, asks the user first. REST: DELETE /api/v1/tumblr/posts/{post_id}. MCP: tumblr_write → delete_post.
| Parameter | Type | Required | Description |
|---|---|---|---|
blog | string | yes | Blog name, e.g. 'studio-notes' for studio-notes.tumblr.com. Names come from list_blogs. |
post_id | string | yes | Post ID from list_posts, list_queue or list_drafts. |
Deletes one post of yours. A published post disappears from your blog and from followers' dashboards, and a deleted post cannot be brought back with this tool. By default you confirm each call; you can switch that off for this tool.
Example response:
{
"post_id": "771198400021",
"status": "deleted"
}
follow_blog
Follow a blog from your account. Access: write, asks the user first. REST: POST /api/v1/tumblr/blog/follow. MCP: tumblr_write → follow_blog.
| Parameter | Type | Required | Description |
|---|---|---|---|
url | string | yes | Blog URL, e.g. https://pixel-lab.tumblr.com. |
Follows one blog from your account by its URL. The blog owner sees the new follower. Following is undone by unfollowing in Tumblr. By default you confirm each call; you can switch that off for this tool.
Example response:
{
"url": "https://pixel-lab.tumblr.com",
"status": "following"
}
How do I connect Tumblr to ChatGPT, Claude, Cursor or Codex?
Connecting Tumblr takes three steps: sign up, sign in to Tumblr once in your Cloud Browser and enable it for agents, then add Cotlet to ChatGPT or Claude as a connector, with no API key, or add one MCP server or call the REST API with an API key.
Connect Tumblr to your agent.
-
Create an account Sign up and add Tumblr in the console. ChatGPT and Claude need no API key: you sign in to Cotlet when you add the connector. Code editors and scripts take an API key from the console.
-
Sign in to Tumblr in your Cloud Browser Open your Cloud Browser in the console: your own Chrome in the cloud. Sign in to Tumblr there yourself, the way you always do, then press Enable for agents, read only or read and write. We never save your password, and your agent keeps working even when your computer is off.
-
Add Cotlet to ChatGPT, Claude or your agent Paste the snippet for your client. The same server and key serve every app you connect, so you do this once.
ChatGPT:
Settings > Apps & Connectors > Create
MCP server URL: https://cotlet.dev/mcp/v1/connect
Authentication: OAuth
Claude:
Settings > Connectors > Add custom connector
URL: https://cotlet.dev/mcp/v1/connect
Claude Code:
claude mcp add --transport http cotlet \
https://cotlet.dev/mcp/v1 \
--header "Authorization: Bearer $COTLET_API_KEY"
Cursor:
{
"mcpServers": {
"cotlet": {
"url": "https://cotlet.dev/mcp/v1",
"headers": {
"Authorization": "Bearer ${COTLET_API_KEY}"
}
}
}
}
Codex:
# ~/.codex/config.toml
[mcp_servers.cotlet]
url = "https://cotlet.dev/mcp/v1"
bearer_token_env_var = "COTLET_API_KEY"
- Ask your agent Ask in plain words. Your agent finds the Tumblr tools on the server and calls them for you; anything that reaches other people waits for your OK unless you switch that off for a tool.
Add these 10 posts to the queue of studio-notes. Tag each one from its text, publish them in the order I gave, and tell me how many queue slots are left.
Call Tumblr from your scripts.
- Export your API key Your scripts use the same API key as your agent. Keep it in an environment variable, never in your code.
export COTLET_API_KEY="cotlet_..."
- Call a tool Every tool is an endpoint under /api/v1/tumblr with its own method and path, listed with the endpoints above. Path parameters go in the URL; the other parameters go in the query for GET and DELETE and in a JSON body otherwise.
curl -X POST https://cotlet.dev/api/v1/tumblr/posts \
-H "Authorization: Bearer $COTLET_API_KEY" \
-H "Content-Type: application/json" \
-d '{"blog":"studio-notes","content":"New print: harbor at dawn, 40 x 60 cm, ink on paper. Available this Friday.","tags":["studio notes","ink","print"],"state":"queue","publish_on":"2026-10-19T09:00:00+02:00"}'
- Read the result You get plain JSON back, ready for your script. A failed call costs nothing.
{
"post_id": "771204518830",
"blog": "studio-notes",
"state": "queue",
"publish_on": "2026-10-19T09:00:00+02:00",
"tags": [
"studio notes",
"ink",
"print"
]
}
How to use the Tumblr REST API
Create your Cotlet API key
Create a Cotlet API key with access to Tumblr and its read operations. Store it as COTLET_API_KEY in your environment or automation platform's credential store.
Connect Tumblr in Cotlet and enable it for agents. Account access: Your own Tumblr account with access to the blog. You sign in in your own Cloud Browser and keep your own login protections.
Make your first Tumblr API request
REST:
curl https://cotlet.dev/api/v1/tumblr/blogs \
-H "Authorization: Bearer $COTLET_API_KEY"
Read blogs and apply the operation limits
A successful REST call puts the tool output in result. This illustrative response excerpt omits call IDs, messages and credit details.
Illustrative response excerpt:
{
"status": "success",
"app": "tumblr",
"tool": "list_blogs",
"result": {
"blogs": [
{
"name": "studio-notes",
"title": "Studio notes",
"url": "https://studio-notes.tumblr.com",
"primary": true,
"posts": 1840
},
{
"name": "studio-sketches",
"title": "Sketches",
"url": "https://studio-sketches.tumblr.com",
"primary": false,
"posts": 212
}
]
}
}
Returns every blog on the signed-in account, the primary blog first. Use the name field as the blog parameter of the other endpoints.
Posts is the count Tumblr shows on the blog.
Keep the same selection when continuing a list. Compare changed record values as well as identifiers when refreshing your destination.
Tumblr workflows for agents and automations
| Tool | Connect through | Example workflow |
|---|---|---|
| n8n | HTTP Request | Posts on a blog or under a tag, newest first. Use list_posts in your configured content report. |
| Make | HTTP > Make a request | Posts waiting in the queue, in publishing order, with their Queue settings. Use list_queue in your configured content report. |
| Python or Node.js | REST API | Asks waiting in the blog inbox, oldest first. Use list_asks in your configured content report. |
Send Authorization: Bearer <your Cotlet API key> in request headers. You configure the schedule, destination and record comparisons.
Cotlet reads Tumblr; your workflow steps write to your chosen destination. These HTTP workflows do not require a native Cotlet connector or a prebuilt template.
Python and Node.js can use the same HTTP requests without an AI agent. Keep access keys in credentials, outside shared workflow exports.
The API and MCP reference lists operations and inputs. The REST API guide explains authentication, errors and approvals.
Why use Cotlet for Tumblr?
Built for agents
- One MCP server for every app you connect.
- The same tools as a REST API for scripts and cron jobs.
- Works with ChatGPT, Claude, Claude Code, Codex and Cursor.
Your login stays yours
- You sign in to Tumblr yourself, in your own Cloud Browser. We never save your password; the profile is encrypted with AES-256-GCM, the cipher 1Password uses.
- A+ on Qualys SSL Labs, securityheaders.com and Mozilla Observatory.
- The model never sees a login.
- No stored passwords, no MFA bypass.
You stay in control
- Scope each API key: its apps, its tools, read only or read and write.
- Anything that reaches other people waits for your OK, so a leaked key cannot post or message as you.
- Every background request listed in your Background activity. Disable for agents in one click.
Kept working for you
- We test every integration every 6 hours.
- When Tumblr changes, the tool pauses until we fix it.
- Failed calls cost nothing.
Is it safe to connect Tumblr to Cotlet?
Yes. You sign in to Tumblr yourself, in your own Cloud Browser, and we never save your password. Your agents only get Tumblr once you enable it, and every background request is listed. The browser profile is stored encrypted with AES-256-GCM, the same cipher 1Password uses for its vaults and Apple for iCloud Keychain. Independent public scanners grade cotlet.dev A+ and find it clean; click a result to rerun it yourself.
- A+ on Qualys SSL Labs: Encryption in transit: TLS setup and certificates, on all four server addresses. Live result
- A+ on securityheaders.com: Browser protections sent with every page, all six headers present. Live result
- A+ on Mozilla Observatory: Mozilla's web security baseline: score 120 of 100, 12 of 12 tests passed. Live result
- Clean on Sucuri SiteCheck: No malware, spam or defacement, and not on any of 9 blocklists, Google Safe Browsing included. Live result
How Cotlet protects your access
Common concerns
Who runs Cotlet?
Cotlet is run by Take Group, a Polish software company working since 2019. Take Group runs about 3,200 websites on its own systems and has its own DevOps team for infrastructure security. We built and used integrations like this inside the company for years before opening them as Cotlet.
Is this an official Tumblr integration?
No, Cotlet is independent of Tumblr. Tumblr's own API is too limited for this work. Cotlet works through your own Tumblr account, the way you use Tumblr in the browser, so you need no partner approval and no developer setup.
What about client data and GDPR?
Cotlet is run from the EU and follows the GDPR. Cloud Browsers run in Finland, a Tier 1 country in the ITU Global Cybersecurity Index 2024. Data passes through a call and is not kept after it.
Can I start with read only?
Yes. Enable the app for agents as read only, or make the API key read only, and anything that reaches other people waits for your OK unless you switch that off per tool.
Is it reliable?
Every Cotlet service is checked every 3 minutes from Europe, North America, Asia and Australia. The live results and any outage are public at status.cotlet.dev.
How do I stop?
Press Disable for agents next to Tumblr in your console: your agents lose access at once and you stay signed in. Signing out of Tumblr in the browser works too, and Reset browser deletes the whole profile.
Is there a Tumblr MCP server on GitHub?
Yes. Community Tumblr MCP servers exist on GitHub, usually maintained by one person. You register a Tumblr app, install one yourself, and fix it when Tumblr changes. Zapier has Tumblr actions that only create posts. Cotlet hosts the same kind of MCP server for you, with no app to register, and our team keeps it working.
| GitHub MCP server | Cotlet | |
|---|---|---|
| Setup | Register a Tumblr app, clone the repo, run the OAuth flow, add it to each MCP client | Sign up, sign in to Tumblr once, add one MCP server or API key |
| When Tumblr changes | It breaks until you or the maintainer fix it | Our team tests it daily and fixes it for you; failed calls are free |
| Your Tumblr access | Consumer key and OAuth tokens in a file on your computer, readable by any program you run | Signed in inside your own Cloud Browser in the EU, profile encrypted, only for the apps you enable, disabled for agents in one click |
| When access expires | Tools fail until you renew the token by hand | Your Cloud Browser keeps you signed in; if Tumblr logs you out, your agent gets a link to sign in again |
| Upkeep | You update, monitor and debug it yourself | Nothing to host or update |
| Where it runs | Your computer, while it is on | Hosted: Claude Code, Codex, Cursor, n8n and scripts, also on a schedule |
| Price | Free, paid for with your time | Free 7-day trial, then pay-as-you-go credit packs, no subscription |
Which one fits you
Pick Cotlet if
- you are not a developer, or you do not want to maintain a server
- you need it to keep working when Tumblr changes, without checking it yourself
- your agent or a script should run it on a schedule, also while your computer is off
Pick an open-source server if
- you are comfortable installing, updating and fixing it yourself
- you want your sign-in to stay on your own computer
- you only need it now and then, from one MCP client
How much does the Tumblr API cost?
Free 7-day trial with 2,000 credits, no card needed. After that, the Tumblr API is pay as you go with no limit on apps: Credit packs from $29 for 5,000 credits, one-time, no subscription. A successful call uses 10 to 100 credits (10 for most tools, about $0.04 to $0.06), your Cloud Browser uses 50 credits a day while it has an app enabled for agents, however many apps that is, and an agent driving the browser itself uses 5 credits a minute. Credit packs stay valid for 12 months and stack, so unused credits carry over.
| Credits | Price, one time | Calls at 10 credits | Per 1,000 credits |
|---|---|---|---|
| 5,000 | $29 | 500 | $5.80 |
| 15,000 | $79 | 1,500 | $5.27 |
| 32,000 | $149 | 3,200 | $4.66 |
| 60,000 | $249 | 6,000 | $4.15 |
Only successful calls use credits; failed calls and timeouts cost nothing. At a balance of 0 calls pause, never a surprise charge. Authenticate with the Authorization: Bearer header. See full pricing
How Cotlet holds your access
Cotlet hosts MCP servers and REST APIs for apps with no usable API. Your agent works in your own Tumblr account.
- Company details: Cotlet is run by Take Group sp. z o.o., a company registered in Poland. Its full address and registration numbers are in the Terms of service. Terms of service
- Your sign-in: You sign in to Tumblr yourself, in your own Cloud Browser: a Chrome we run for you in the EU, one per app. We never save your password (password saving is off), the profile is stored encrypted with AES-256-GCM, and your agents get Tumblr only after you enable it. When Tumblr signs you out, your agent gives you a link to sign in again. Security
- Revoking access: Press Disable for agents next to Tumblr, sign out of Tumblr in your Cloud Browser, or reset the browser. Every background request is listed in your Background activity. Actions that reach other people wait for your OK unless you switch that off per tool.
- What we never do: Store passwords or bypass MFA.
- Tumblr's terms: You use your own Tumblr account and stay responsible for following Tumblr's terms. Cotlet is independent and not affiliated with Tumblr. Terms
- Contact: Questions about the company, security or an app: contact@cotlet.dev
Tumblr API and MCP: questions
How do I get access?
Sign up free, open Tumblr in the console and press Activate. Then you create your API key and connect Tumblr there.
Do I need to be technical?
No. You sign in to Tumblr once in your Cloud Browser, a normal Chrome you open from the console, and paste one command into your agent, or one URL into n8n. Your agent can walk you through it. There is no server to install, update or fix.
Is it safe to connect Tumblr to Cotlet?
Yes. You sign in to Tumblr yourself, in your own Cloud Browser in the EU, and we never save your password. Your agents only get Tumblr once you enable it, every background request is listed, and the browser profile is stored encrypted with AES-256-GCM, the cipher 1Password uses for its vaults. The AI model never sees a login, posts and messages wait for your OK, and Disable for agents cuts access in one click. Independent scanners grade cotlet.dev A+ on Qualys SSL Labs, securityheaders.com and Mozilla Observatory; live results are on https://cotlet.dev/security.
Is a hosted server safer than a local one? My Tumblr sign-in would leave my computer.
On Cotlet you sign in inside your own Cloud Browser, which only you open, and its profile is stored encrypted with AES-256-GCM in the EU. Agents get only the apps you enable, and every background request is listed. A local server keeps your Tumblr cookie in a plain file on your computer, readable by any program you run, and stops when your computer is off.
Why does Cotlet send requests instead of clicking in my browser?
To be fast, Cotlet doesn't click through Tumblr's pages. It sends the same requests your browser would, from your browser's IP with its cookies, without opening a window. Tumblr sees the same browser and IP you signed in with, and every request is listed in your Background activity.
What if someone gets my Cotlet API key?
The key holds no Tumblr login or cookies, it only asks Cotlet to run a tool. It can call only the apps and tools you gave it, and a read-only key changes nothing. Anything that reaches other people, like posts, comments or messages, waits for your OK in the dashboard by default, so a leaked key cannot post or message as you. When you switch approval off for a scheduled job, give that job its own key limited to that one tool. Every call is in your activity log, and deleting the key ends access at once.
Why a signed-in browser and not OAuth, like other integration platforms?
Tumblr offers no OAuth token you can simply grant for these tools: its official API leaves them out or needs a developer app, a plan or an approval first (see the official API section above). That is why Cotlet sets the limits itself: per key, per tool, with your approval before anything reaches other people. Cotlet is run by Take Group sp. z o.o., an EU company (VAT PL6342984273).
How do I connect Tumblr to ChatGPT or Claude?
Sign up at cotlet.dev, log in to Tumblr once in its Cloud Browser and add Cotlet to ChatGPT or Claude, following the steps in your console. No API key is needed. ChatGPT and Claude then work in your Tumblr account through Cotlet, in their phone apps too.
What can ChatGPT do in Tumblr?
With Cotlet, ChatGPT, Claude and other AI agents handle jobs like these in Tumblr: fill the post queue; answer asks in your inbox; queue reblogs from a tag. You ask in plain words, and anything that reaches other people waits for your OK first.
Do I need to register a Tumblr app or get an API key?
No. Cotlet works in your own signed-in Tumblr account. The official API needs a registered app and an OAuth consumer key, and each key is capped at 1,000 calls an hour and 5,000 a day.
Does the queue limit apply to my agent?
Yes. Tumblr holds at most 1,000 queued posts and publishes at most 50 queued posts a day, so your agent queues up to that and reports when the queue is full.
Can my agent post or send messages in Tumblr without asking me?
No. Every call to create_post, edit_post, reblog_post, answer_ask, delete_ask, delete_post or follow_blog waits for your OK by default. For scheduled automations you can switch confirmation off per tool in your dashboard, for example only for approvals.
Can I use the Tumblr API in n8n?
Yes. Add https://cotlet.dev/mcp/v1 with your API key in n8n's MCP Client node, or call its endpoints under https://cotlet.dev/api/v1/tumblr from the HTTP Request node.
Can I use the Tumblr API without an AI agent?
Yes. Call Cotlet's REST API from a script or an HTTP step in n8n, Make or Zapier with your Cotlet key. MCP is the alternative for AI agents; you do not need to connect an agent to use REST.
Give your AI agents your signed-in browser.
Product: Integrations · How it works · Pricing · Security
Resources: Blog · API docs · Help center · Changelog · GitHub
Solutions: For developers · For automation agencies
Company: About · AI info: company facts · Contact
Legal: Terms of service · Privacy policy · Refund policy · Acceptable use · Cookie policy · DPA · Subprocessors
Elsewhere: Status page · Cotlet on GitHub · Cotlet on X · Cotlet on LinkedIn · Cotlet on Product Hunt · Cotlet on Crunchbase · Cotlet on SaaSHub
Cotlet.dev is built by Bart Krawczyk and Jake Slugocki, the founders of Take Group sp. z o.o., ul. Wincentego Janasa 4, 40-855 Katowice, Poland. KRS 0000871398, NIP 6342984273, VAT EU: PL6342984273. About us
Cotlet is an independent service. It is not affiliated with, endorsed by or sponsored by any of the products listed on this site. Product names are trademarks of their respective owners.