Ubersuggest MCP Server
Ubersuggest için projeler, sıralama takibi anahtar kelimeleri, rakipler ve anahtar kelime listeleri.
Barındırılan MCP Sunucusu
npx add-mcp 'https://cotlet.dev/mcp/v1/ubersuggest'Claude Code, Codex, Cursor ve daha fazlasına kurulur
Dokümantasyon
Cotlet · Integrations · How it works · Security · For developers · For automation agencies · Blog · API docs · Help center · Changelog · Contact · Pricing · Sign up
Ubersuggest API and MCP server
Ubersuggest has no public REST API and no webhooks (checked 23 Oct 2026). Its help center says so. The only official programmatic access is a read-only MCP server for research and project data, which cannot create projects, add keywords or add competitors.
Projects, rank-tracking keywords, competitors and keyword lists for Ubersuggest. Use it in ChatGPT, Claude or any AI agent over MCP, or in n8n, Make and scripts over REST.
Cotlet is an independent service. It is not affiliated with, endorsed by or sponsored by Ubersuggest. Ubersuggest is a trademark of its owner. If Ubersuggest's own integrations cover what you need, use them first.
SEO tool by Neil Patel with keyword research, Rank Tracking for projects, Site Audit, competitor tracking and Keyword Lists.
What is the Ubersuggest API?
Cotlet's Ubersuggest API exposes 13 endpoints for your own Ubersuggest account: list projects, get rank tracking, list competitors, get site audit, list keyword lists, get keyword list, create project, add tracked keywords, delete tracked keywords, add competitors, create keyword list, recrawl site audit and remove project. The list_projects endpoint returns projects on your Ubersuggest Dashboard with locations, tracked keywords and competitors. Each endpoint takes simple JSON inputs like project, location or keywords and works both as an operation of the ubersuggest_read or ubersuggest_write MCP tool for agents and as a REST call for scripts.
- Category: Marketing & SEO
- Endpoints: 13 (6 read, 7 write)
- Updated: 2026-11-15
Ubersuggest has no public REST API and no webhooks (checked 23 Oct 2026). Cotlet is a hosted MCP server and REST API for Ubersuggest with 13 endpoints (6 read, 7 write): you sign in once in your own cloud browser, your AI agent does the work.
Does Ubersuggest have an official API?
Ubersuggest has no public REST API and no webhooks (checked 23 Oct 2026). Its help center says so. The only official programmatic access is a read-only MCP server for research and project data, which cannot create projects, add keywords or add competitors.
| Task | Ubersuggest official | Cotlet |
|---|---|---|
| Read keyword, domain and backlink research | Yes: Official MCP, read-only, on any plan | Yes |
| Read Rank Tracking and project data | Yes: Official MCP has Projects tools for rank tracking results | Yes |
| Read Site Audit results | Yes: Official MCP has Site Audit tools | Yes |
| Recrawl a Site Audit | Partly: The MCP guide says "run and retrieve", but names no tool and calls the connection read-only | Yes |
| Create or remove a project | No | Yes |
| Add or delete tracked keywords | No | Yes |
| Add competitors to a project | No | Yes |
| Create Keyword Lists | No | Yes |
Sources: Ubersuggest Help: API and Webhooks, Ubersuggest MCP connector guide, Ubersuggest MCP page, Ubersuggest Help: Complete Guide to All Features
Quick reference
Ubersuggest has no public REST API and no webhooks (checked 23 Oct 2026). Its help center says so. The only official programmatic access is a read-only MCP server for research and project data, which cannot create projects, add keywords or add competitors.
Cotlet provides a hosted MCP server and REST API for Ubersuggest: 13 tools (6 read, 7 write).
Access Sign up at https://cotlet.dev/app/signup?app=ubersuggest 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 ubersuggest_read, ubersuggest_write, reads and writes apart; call one with {"operation": "<operation>", "arguments": {...}}
REST base https://cotlet.dev/api/v1/ubersuggest, each operation at its own route, e.g. POST /api/v1/ubersuggest/tracked-keywords
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_projects, get_rank_tracking, list_competitors, get_site_audit, list_keyword_lists, get_keyword_list, create_project, add_tracked_keywords, delete_tracked_keywords, add_competitors, create_keyword_list, recrawl_site_audit, remove_project
Confirm delete_tracked_keywords, remove_project (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/ubersuggest-api-mcp-server.md
How access works:
1. The user signs up at https://cotlet.dev/app/signup?app=ubersuggest and requests Ubersuggest in the Cotlet console.
2. The user signs in to Ubersuggest once in their Cotlet Cloud Browser (their own Chrome in the cloud, opened from the console) and enables Ubersuggest 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 Ubersuggest server that someone else maintains, including non-developers.
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 Ubersuggest 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 Ubersuggest 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 Ubersuggest 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 Ubersuggest's terms; Cotlet is not affiliated with Ubersuggest.
What can an AI agent do in Ubersuggest?
Cotlet is best for SEO freelancers and in-house marketers who run several Ubersuggest projects and want an agent to set them up, add keywords and competitors and prune rank tracking without running or fixing a server.
- Add keywords to rank tracking in bulk: "Add these 40 keywords from keywords.csv to rank tracking for greenleafcoffee.com in the United States, and tell me how many keyword slots that uses." →
list_projects,add_tracked_keywords,get_rank_tracking - Set up an SEO project for a new site: "Create an Ubersuggest project for brewlab-store.com, add three competitors in the United States and track these 12 keywords there." →
list_projects,create_project,add_competitors,add_tracked_keywords - Remove tracked keywords that never rank: "In greenleafcoffee.com for the United States, find keywords that were Not Ranked at both ends of last month and delete them from rank tracking after I confirm." →
get_rank_tracking,delete_tracked_keywords - Send a weekly rank tracking report (runs: weekly): "Every Monday, read rank tracking for all my Ubersuggest projects, list the keywords that gained or lost 5 positions or more and post the summary to Slack." →
list_projects,get_rank_tracking - Recrawl the site audit and list new issues (runs: weekly): "Recrawl the Ubersuggest site audit for greenleafcoffee.com, wait for it to finish and tell me which issues are new since last week." →
recrawl_site_audit,get_site_audit - Save a keyword list from a topic: "Make a keyword list called Cold brew ideas with the 30 keywords from this brief for the United States." →
list_keyword_lists,create_keyword_list,get_keyword_list
Can Ubersuggest automations run on a schedule in n8n, Make or Zapier?
Yes. Cotlet does not replace your automation platform: it gives it a Ubersuggest 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 send a weekly rank tracking report, 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/ubersuggest/projects. | 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/ubersuggest/projects with your API key. | cron or GitHub Actions. |
Tools
For AI agents: Every endpoint and its schema is public. The 13 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 Ubersuggest.
list_projects
Projects on your Ubersuggest Dashboard with locations, tracked keywords and competitors. Access: read. REST: GET /api/v1/ubersuggest/projects. MCP: ubersuggest_read → list_projects.
No parameters.
Returns every project of the account, with its domain, the locations it tracks, the number of tracked keywords (one per keyword and location) and of tracked competitors, and whether notifications are on. Use domain as the project parameter of the other tools. The number of projects depends on your plan.
Example response:
{
"projects": [
{
"domain": "greenleafcoffee.com",
"locations": [
"United States"
],
"tracked_keywords": 42,
"competitors": 3,
"notifications": true
},
{
"domain": "northpeak-gear.com",
"locations": [
"United States",
"Canada"
],
"tracked_keywords": 60,
"competitors": 5,
"notifications": false
}
]
}
get_rank_tracking
Positions of the tracked keywords of a project by location, device and timeframe. Access: read. REST: GET /api/v1/ubersuggest/rank-tracking. MCP: ubersuggest_read → get_rank_tracking.
| Parameter | Type | Required | Description |
|---|---|---|---|
project | string | yes | Project domain, e.g. greenleafcoffee.com. |
location | string | no | A tracked location such as United States. Default: all locations. |
device | enum | no | desktop or mobile. Mobile only has data when it is enabled in the project settings. Default: desktop. |
timeframe | enum | no | last_2_weeks or last_month. Default: last_2_weeks. |
cursor | string | no | Next page cursor from the previous call. |
Returns the Average Position and each tracked keyword with its position at the end and at the start of the timeframe. A null position is Not Ranked, outside the top 100. Rankings update weekly, so a new keyword has no position until the next update. Returns up to 50 keywords a page; pass next_cursor back as cursor.
Example response:
{
"project": "greenleafcoffee.com",
"location": "United States",
"device": "desktop",
"timeframe": "last_month",
"average_position": 31,
"previous_average_position": 34,
"keywords": [
{
"keyword": "cold brew coffee beans",
"position": 7,
"previous_position": 9
},
{
"keyword": "single origin coffee beans",
"position": 18,
"previous_position": 18
},
{
"keyword": "coffee gift box",
"position": 52,
"previous_position": 61
},
{
"keyword": "coffee subscription box uk",
"position": null,
"previous_position": null
},
{
"keyword": "arabica bean wholesale",
"position": null,
"previous_position": null
}
],
"total": 46,
"next_cursor": "1"
}
list_competitors
Competitors tracked in a project, by country. Access: read. REST: GET /api/v1/ubersuggest/competitors. MCP: ubersuggest_read → list_competitors.
| Parameter | Type | Required | Description |
|---|---|---|---|
project | string | yes | Project domain. |
Returns the competitors in the Competitor Tracking section of the project with their country. slots_used is competitors times locations, the number Ubersuggest checks against your plan limit.
Example response:
{
"project": "greenleafcoffee.com",
"competitors": [
{
"domain": "northbeanco.com",
"location": "United States"
},
{
"domain": "tidalroast.com",
"location": "United States"
},
{
"domain": "emberandoak.coffee",
"location": "United States"
}
],
"slots_used": 3
}
get_site_audit
Latest Site Audit of a project: health score, pages by status and the issues found. Access: read. REST: GET /api/v1/ubersuggest/site-audit. MCP: ubersuggest_read → get_site_audit.
| Parameter | Type | Required | Description |
|---|---|---|---|
project | string | yes | Project domain. |
Returns the SEO Health Score, the pages crawled split into successful, redirected, broken and blocked, and the issues grouped as critical errors, warnings and recommendations with the number of pages each affects. status is crawling while a recrawl runs. It does not start a crawl; use recrawl_site_audit.
Example response:
{
"project": "greenleafcoffee.com",
"status": "complete",
"crawled_at": "2026-10-19T06:12:00Z",
"health_score": 78,
"pages_crawled": 112,
"pages": {
"successful": 98,
"redirected": 9,
"broken": 3,
"blocked": 2
},
"issues": [
{
"issue": "Broken links",
"level": "critical error",
"pages": 3
},
{
"issue": "Missing meta description",
"level": "warning",
"pages": 7
},
{
"issue": "Low word count",
"level": "recommendation",
"pages": 12
}
]
}
list_keyword_lists
Your Keyword Lists with keyword counts and combined metrics. Access: read. REST: GET /api/v1/ubersuggest/keyword-lists. MCP: ubersuggest_read → list_keyword_lists.
No parameters.
Returns each list with the number of keywords, the total monthly search volume, the average CPC and the average paid and SEO difficulty, as the Keyword Lists dashboard shows them. Free accounts have up to three lists.
Example response:
{
"lists": [
{
"list_id": "kl_5f2a",
"name": "Cold brew ideas",
"keywords": 18,
"total_monthly_volume": 12400,
"avg_cpc": 0.85,
"avg_paid_difficulty": 52,
"avg_seo_difficulty": 41
},
{
"list_id": "kl_8c1d",
"name": "Gift boxes",
"keywords": 9,
"total_monthly_volume": 6100,
"avg_cpc": 1.12,
"avg_paid_difficulty": 60,
"avg_seo_difficulty": 47
}
]
}
get_keyword_list
Keywords of one list with volume, SEO difficulty and CPC. Access: read. REST: GET /api/v1/ubersuggest/lists/{list_id}/keyword-list. MCP: ubersuggest_read → get_keyword_list.
| Parameter | Type | Required | Description |
|---|---|---|---|
list_id | string | yes | List id from list_keyword_lists. |
cursor | string | no | Next page cursor from the previous call. |
Returns the keywords of one list with the location each was added for, monthly search volume, SEO difficulty and CPC. Up to 100 keywords a page; pass next_cursor back as cursor.
Example response:
{
"list_id": "kl_5f2a",
"name": "Cold brew ideas",
"keywords": [
{
"keyword": "cold brew coffee beans",
"location": "United States",
"monthly_volume": 2900,
"seo_difficulty": 38,
"cpc": 0.92
},
{
"keyword": "cold brew subscription",
"location": "United States",
"monthly_volume": 480,
"seo_difficulty": 29,
"cpc": 1.4
}
],
"next_cursor": null
}
create_project
Add a domain as a new project on the Dashboard. Access: write. REST: POST /api/v1/ubersuggest/projects. MCP: ubersuggest_write → create_project.
| Parameter | Type | Required | Description |
|---|---|---|---|
domain | string | yes | Domain to track, e.g. brewlab-store.com. |
Does what Add Project does: enters the domain, starts the analysis and creates the project from the Business Summary. It skips the competitor, prompt and keyword screens like Do It Later; add those with add_competitors and add_tracked_keywords. Fails if the domain already has a project or your plan has no free project slot, and never buys an add-on. It reaches no one and remove_project undoes it, so it does not ask for your OK.
Example response:
{
"project": "brewlab-store.com",
"status": "created",
"business_summary": "Online store selling home coffee brewing equipment.",
"next": "Add competitors and keywords"
}
add_tracked_keywords
Add keywords to Rank Tracking of a project for one location. Access: write. REST: POST /api/v1/ubersuggest/tracked-keywords. MCP: ubersuggest_write → add_tracked_keywords.
| Parameter | Type | Required | Description |
|---|---|---|---|
project | string | yes | Project domain. |
keywords | string[] | yes | Keywords to track, up to 200 per call. |
location | string | yes | Location name as in the Rank Tracking locations menu, e.g. United States. |
Adds the keywords to the Tracked Keywords list for the location you name. Each keyword and location counts as one keyword of your plan, and a keyword added without a location is tracked in all the available locations, so location is required here. Fails above your keyword limit. New keywords show a position after the next weekly update. It reaches no one and delete_tracked_keywords undoes it, so it does not ask for your OK.
Example response:
{
"project": "greenleafcoffee.com",
"location": "United States",
"added": [
"single origin coffee beans",
"cold brew subscription",
"coffee gift box",
"organic espresso beans"
],
"counted_as_keywords": 4,
"tracked_keywords_now": 46,
"first_ranking_data": "next weekly update"
}
delete_tracked_keywords
Remove keywords from Rank Tracking of a project in one location. Access: write, asks the user first. REST: DELETE /api/v1/ubersuggest/tracked-keywords. MCP: ubersuggest_write → delete_tracked_keywords.
| Parameter | Type | Required | Description |
|---|---|---|---|
project | string | yes | Project domain. |
keywords | string[] | yes | Keywords exactly as tracked. |
location | string | yes | Location the keywords are tracked in. |
Deletes the keywords from the Tracked Keywords list of one location, as the Delete button in Rank Tracking does. Ubersuggest cannot restore a deleted keyword and drops its ranking data. A keyword tracked in other locations stays there. Returns the deleted keywords and the tracked count after. By default you confirm each call; you can switch that off for this tool.
Example response:
{
"project": "greenleafcoffee.com",
"location": "United States",
"deleted": [
"coffee subscription box uk",
"arabica bean wholesale"
],
"deleted_count": 2,
"tracked_keywords_now": 44
}
add_competitors
Add competitor domains to Competitor Tracking of a project for one country. Access: write. REST: POST /api/v1/ubersuggest/competitors. MCP: ubersuggest_write → add_competitors.
| Parameter | Type | Required | Description |
|---|---|---|---|
project | string | yes | Project domain. |
competitors | string[] | yes | Competitor domains or URLs. |
location | string | yes | Country to track them in, e.g. United States. |
Does what Add Competitors to Track does: adds the domains for the location you name. Ubersuggest tracks competitors at country level only, so a city becomes its country. Competitors times locations must fit your plan limit, otherwise the call fails and adds nothing. It reaches no one and does not buy the add-on for more slots. It is not confirmed by default because you undo it by removing the competitor in the app.
Example response:
{
"project": "brewlab-store.com",
"location": "United States",
"added": [
"northbeanco.com",
"tidalroast.com",
"emberandoak.coffee"
],
"slots_used": 3
}
create_keyword_list
Create a Keyword List and add keywords to it. Access: write. REST: POST /api/v1/ubersuggest/keyword-lists. MCP: ubersuggest_write → create_keyword_list.
| Parameter | Type | Required | Description |
|---|---|---|---|
name | string | yes | List name that reflects its purpose. |
keywords | string[] | yes | Keywords to add. |
location | string | yes | Location for the metrics, e.g. United States. |
Creates a list in Keyword Lists and adds the keywords for the location you name. Free accounts can have up to three lists, and paid accounts have unlimited lists with up to 1,000 keywords per list. It reaches no one and you can delete the list in the app, so it does not ask for your OK.
Example response:
{
"list_id": "kl_5f2a",
"name": "Cold brew ideas",
"location": "United States",
"keywords_added": 3
}
recrawl_site_audit
Start a new Site Audit crawl of a project. Access: write. REST: POST /api/v1/ubersuggest/site-audit/recrawl. MCP: ubersuggest_write → recrawl_site_audit.
| Parameter | Type | Required | Description |
|---|---|---|---|
project | string | yes | Project domain. |
Clicks Recrawl Website on the Site Audit page of the project and returns at once with status crawling. Read the result with get_site_audit when status is complete. It crawls only your own site and reaches no one, so it does not ask for your OK.
Example response:
{
"project": "greenleafcoffee.com",
"status": "crawling",
"previous_crawl": "2026-10-19T06:12:00Z"
}
remove_project
Remove a project and all its tracking data from the Dashboard. Access: write, asks the user first. REST: DELETE /api/v1/ubersuggest/projects. MCP: ubersuggest_write → remove_project.
| Parameter | Type | Required | Description |
|---|---|---|---|
project | string | yes | Project domain. |
Does what Remove Project in Project Settings does. It deletes the project history for good, and a project created again starts tracking from the new date. Returns the removed domain. By default you confirm each call; you can switch that off for this tool.
Example response:
{
"project": "old-client-site.com",
"removed": true
}
How do I connect Ubersuggest to ChatGPT, Claude, Cursor or Codex?
Connecting Ubersuggest takes three steps: sign up, sign in to Ubersuggest 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 Ubersuggest to your agent.
-
Create an account Sign up and add Ubersuggest 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 Ubersuggest in your Cloud Browser Open your Cloud Browser in the console: your own Chrome in the cloud. Sign in to Ubersuggest 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 Ubersuggest 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 40 keywords from keywords.csv to rank tracking for greenleafcoffee.com in the United States, and tell me how many keyword slots that uses.
Call Ubersuggest 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/ubersuggest 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/ubersuggest/tracked-keywords \
-H "Authorization: Bearer $COTLET_API_KEY" \
-H "Content-Type: application/json" \
-d '{"project":"greenleafcoffee.com","keywords":["single origin coffee beans","cold brew subscription","coffee gift box","organic espresso beans"],"location":"United States"}'
- Read the result You get plain JSON back, ready for your script. A failed call costs nothing.
{
"project": "greenleafcoffee.com",
"location": "United States",
"added": [
"single origin coffee beans",
"cold brew subscription",
"coffee gift box",
"organic espresso beans"
],
"counted_as_keywords": 4,
"tracked_keywords_now": 46,
"first_ranking_data": "next weekly update"
}
How to use the Ubersuggest REST API
Create your Cotlet API key
Create a Cotlet API key with access to Ubersuggest and its read operations. Store it as COTLET_API_KEY in your environment or automation platform's credential store.
Connect Ubersuggest in Cotlet and enable it for agents. Account access: Your own Ubersuggest account (email and password, or Continue with Google); your plan sets project, keyword and competitor limits.
Make your first Ubersuggest API request
REST:
curl https://cotlet.dev/api/v1/ubersuggest/projects \
-H "Authorization: Bearer $COTLET_API_KEY"
Read projects 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": "ubersuggest",
"tool": "list_projects",
"result": {
"projects": [
{
"domain": "greenleafcoffee.com",
"locations": [
"United States"
],
"tracked_keywords": 42,
"competitors": 3,
"notifications": true
},
{
"domain": "northpeak-gear.com",
"locations": [
"United States",
"Canada"
],
"tracked_keywords": 60,
"competitors": 5,
"notifications": false
}
]
}
}
Returns every project of the account, with its domain, the locations it tracks, the number of tracked keywords (one per keyword and location) and of tracked competitors, and whether notifications are on. Use domain as the project parameter of the other tools.
The number of projects depends on your plan.
Keep the same selection when continuing a list. Compare changed record values as well as identifiers when refreshing your destination.
Ubersuggest workflows for agents and automations
| Tool | Connect through | Example workflow |
|---|---|---|
| n8n | HTTP Request | Positions of the tracked keywords of a project by location, device and timeframe. Use get_rank_tracking in your configured marketing report. |
| Make | HTTP > Make a request | Latest Site Audit of a project: health score, pages by status and the issues found. Use get_site_audit in your configured marketing report. |
| Python or Node.js | REST API | Competitors tracked in a project, by country. Use list_competitors in your configured marketing report. |
Send Authorization: Bearer <your Cotlet API key> in request headers. You configure the schedule, destination and record comparisons.
Cotlet reads Ubersuggest; 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 Ubersuggest?
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 Ubersuggest 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 Ubersuggest changes, the tool pauses until we fix it.
- Failed calls cost nothing.
Is it safe to connect Ubersuggest to Cotlet?
Yes. You sign in to Ubersuggest yourself, in your own Cloud Browser, and we never save your password. Your agents only get Ubersuggest 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 Ubersuggest integration?
No, Cotlet is independent of Ubersuggest. Ubersuggest's own API is too limited for this work. Cotlet works through your own Ubersuggest account, the way you use Ubersuggest in the browser.
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 Ubersuggest in your console: your agents lose access at once and you stay signed in. Signing out of Ubersuggest in the browser works too, and Reset browser deletes the whole profile.
Is there a Ubersuggest MCP server on GitHub?
Ubersuggest offers its own read-only MCP server on any plan. For research, rankings and audit data it is the right choice. It cannot create projects, add keywords or add competitors. Cotlet does those in your signed-in account, reads the same screens, and adds a REST API for scripts.
| Official MCP | Cotlet | |
|---|---|---|
| Setup | Add the connector in your MCP client and sign in with OAuth | Sign up, sign in to Ubersuggest once, add one MCP server or API key |
| What it does | Reads research, domain, backlink, audit and project data | Reads rank tracking, audits, competitors and lists; creates projects, adds keywords and competitors, creates lists, recrawls audits |
| Your Ubersuggest login | A scoped OAuth token, no password shared | In your own Cloud Browser in the EU, profile encrypted, only for the apps you enable, disabled for agents in one click |
| When Ubersuggest changes | Ubersuggest maintains it | Our team tests it daily and fixes it for you; failed calls are free |
| Where it runs | MCP clients such as Claude, Cursor and Windsurf; no public REST API | Hosted: MCP clients, n8n and scripts, also on a schedule |
| Upkeep | None | Nothing to host or update |
| Price | Free on any plan, within your plan limits | 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 Ubersuggest 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 Ubersuggest API cost?
Free 7-day trial with 2,000 credits, no card needed. After that, the Ubersuggest 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 Ubersuggest 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 Ubersuggest 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 Ubersuggest only after you enable it. When Ubersuggest signs you out, your agent gives you a link to sign in again. Security
- Revoking access: Press Disable for agents next to Ubersuggest, sign out of Ubersuggest 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.
- Ubersuggest's terms: You use your own Ubersuggest account and stay responsible for following Ubersuggest's terms. Cotlet is independent and not affiliated with Ubersuggest. Terms
- Contact: Questions about the company, security or an app: contact@cotlet.dev
Ubersuggest API and MCP: questions
How do I get access?
Sign up free, open Ubersuggest in the console and press Activate. Then you create your API key and connect Ubersuggest there.
Do I need to be technical?
No. You sign in to Ubersuggest 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 Ubersuggest to Cotlet?
Yes. You sign in to Ubersuggest yourself, in your own Cloud Browser in the EU, and we never save your password. Your agents only get Ubersuggest 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 Ubersuggest 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 Ubersuggest 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 Ubersuggest's pages. It sends the same requests your browser would, from your browser's IP with its cookies, without opening a window. Ubersuggest 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 Ubersuggest 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?
Ubersuggest 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 Ubersuggest to ChatGPT or Claude?
Sign up at cotlet.dev, log in to Ubersuggest 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 Ubersuggest account through Cotlet, in their phone apps too.
What can ChatGPT do in Ubersuggest?
With Cotlet, ChatGPT, Claude and other AI agents handle jobs like these in Ubersuggest: add keywords to rank tracking in bulk; set up an SEO project for a new site; remove tracked keywords that never rank. You ask in plain words, and anything that reaches other people waits for your OK first.
Which Ubersuggest plan do I need?
Cotlet works in your own account on any plan, and your plan sets the limits. Ubersuggest's help center caps tracked competitors at 5 on Individual, 10 on Business and 15 on Agency/Enterprise, counted per location. Free accounts can create up to three Keyword Lists, paid accounts unlimited lists with 1,000 keywords each. Project slots per plan are on Ubersuggest's pricing page, and a call over a limit fails without buying an add-on.
Why does a keyword I just added show no position?
Ubersuggest updates Rank Tracking weekly, and its help center says that adding a keyword does not guarantee immediate data. The keyword gets a position with the next scheduled update. Not Ranked means it sits outside the top 100.
Can my agent post or send messages in Ubersuggest without asking me?
No. Every call to delete_tracked_keywords or remove_project waits for your OK by default. For scheduled automations you can switch confirmation off per tool in your dashboard, for example only for approvals. create_project, add_tracked_keywords, add_competitors, create_keyword_list and recrawl_site_audit run without asking, because they send nothing to anyone and one call undoes it.
Can I use the Ubersuggest 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/ubersuggest from the HTTP Request node.
Can I use the Ubersuggest 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.