Productboard MCP Server
Comentarios, información, funciones y estados en tu Productboard, gestionados por tu agente.
Servidor MCP alojado
npx add-mcp 'https://cotlet.dev/mcp/v1/productboard'Se instala en Claude Code, Codex, Cursor y más
Documentación
Cotlet · Integrations · How it works · Security · For developers · For automation agencies · Blog · API docs · Help center · Changelog · Contact · Pricing · Sign up
Productboard API and MCP server
Productboard has a full REST API v2 for notes, entities, teams, members, webhooks and analytics, and a beta MCP server at mcp.productboard.com that works on specs (checked 22 Oct 2026). API tokens need a workspace admin on the Pro plan or higher, and the API reference lists no endpoints for boards.
Feedback, insights, features and statuses in your Productboard, worked by your agent. 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 Productboard. Productboard is a trademark of its owner. If Productboard's own integrations cover what you need, use them first.
Product management platform: customer feedback collected in insights boards, linked to features in a product hierarchy, then planned on roadmap boards with objectives and statuses.
What is the Productboard API?
Cotlet's Productboard API exposes 12 endpoints for your own Productboard account: list feedback, get feedback, search features, get feature, list feature insights, list feature statuses, list objectives, add feedback, link feedback to a feature, unlink an insight, mark feedback processed and update feature status. The list_feedback endpoint returns feedback items from your insights boards, with company, user, tags, owner, processed flag and insight count. Each endpoint takes simple JSON inputs like feature_id, cursor or feedback_id and works both as an operation of the productboard_read or productboard_write MCP tool for agents and as a REST call for scripts.
- Category: Productivity & teams
- Endpoints: 12 (7 read, 5 write)
- Updated: 2026-11-18
Productboard has a full REST API v2 for notes, entities, teams, members, webhooks and analytics, and a beta MCP server at mcp.productboard.com that works on specs (checked 22 Oct 2026). Cotlet is a hosted MCP server and REST API for Productboard with 12 endpoints (7 read, 5 write): you sign in once in your own cloud browser, your AI agent does the work.
Does Productboard have an official API?
Productboard has a full REST API v2 for notes, entities, teams, members, webhooks and analytics, and a beta MCP server at mcp.productboard.com that works on specs (checked 22 Oct 2026). API tokens need a workspace admin on the Pro plan or higher, and the API reference lists no endpoints for boards.
| Task | Productboard official | Cotlet |
|---|---|---|
| Search features and read one | Yes: Entities API; needs an admin token | Yes |
| Read feedback items | Yes: Notes API; needs an admin token | Yes |
| Add a feedback item | Yes: Notes API, POST /v2/notes; needs an admin token | Yes |
| Link a quote to a feature with an importance score | Partly: Relationship endpoints link a note to a feature; a note with highlights linked to features cannot have its content updated | Yes |
| Change a feature status | Yes: Entities API update, or a Jira rule for connected issues | Yes |
| List objectives and key results | Yes: Entities API | Yes |
| Work on feedback and features through an MCP server | Partly: Beta; the page describes finding, reading, refining and commenting on specs and updating an item status, not notes or insights | Yes |
Sources: Productboard developers: API v2 overview, Productboard developers: MCP server (beta), Productboard developers: Connecting your agent, Productboard developers: API token authentication
Quick reference
Productboard has a full REST API v2 for notes, entities, teams, members, webhooks and analytics, and a beta MCP server at mcp.productboard.com that works on specs (checked 22 Oct 2026). API tokens need a workspace admin on the Pro plan or higher, and the API reference lists no endpoints for boards.
Cotlet provides a hosted MCP server and REST API for Productboard: 12 tools (7 read, 5 write).
Access Sign up at https://cotlet.dev/app/signup?app=productboard 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 productboard_read, productboard_write, reads and writes apart; call one with {"operation": "<operation>", "arguments": {...}}
REST base https://cotlet.dev/api/v1/productboard, each operation at its own route, e.g. POST /api/v1/productboard/feedbacks
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_feedback, get_feedback, search_features, get_feature, list_feature_insights, list_feature_statuses, list_objectives, create_feedback, link_feedback_to_feature, unlink_insight, mark_feedback_processed, update_feature_status
Confirm update_feature_status (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/productboard-api-mcp-server.md
How access works:
1. The user signs up at https://cotlet.dev/app/signup?app=productboard and requests Productboard in the Cotlet console.
2. The user signs in to Productboard once in their Cotlet Cloud Browser (their own Chrome in the cloud, opened from the console) and enables Productboard 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 Productboard 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 Productboard 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 Productboard 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 Productboard 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 Productboard 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 Productboard's terms; Cotlet is not affiliated with Productboard.
What can an AI agent do in Productboard?
Cotlet is best for product managers and makers who want their AI agent to triage feedback, log calls and update feature statuses without running or fixing a server.
- Triage new customer feedback (runs: daily): "Go through unprocessed feedback in Productboard. For each item, find the feature it is about, link the most relevant quote with an importance, and mark it processed. Leave the ones you are unsure about for me." →
list_feedback,get_feedback,search_features,link_feedback_to_feature,mark_feedback_processed - Log customer calls as feedback (runs: daily): "Take the notes from today's customer calls and add each one to Productboard as feedback with the company, the person and the tags "interview" and "q4"." →
create_feedback,list_feedback - Update feature statuses after a release (runs: weekly): "Here is the list of features we shipped this week. Set each one to Launched in Productboard. Skip any that are not in Delivery or Testing and tell me why." →
list_feature_statuses,search_features,get_feature,update_feature_status - Weekly feedback digest per feature (runs: weekly): "Every Monday, take the five features with the most linked insights, read the newest insights on each and send me one line per feature on what customers are asking for." →
search_features,list_feature_insights,get_feature - Check objectives and key results (runs: weekly): "List our objectives with their key results and statuses, and tell me which ones have no key result yet." →
list_objectives
Can Productboard automations run on a schedule in n8n, Make or Zapier?
Yes. Cotlet does not replace your automation platform: it gives it a Productboard 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 triage new customer feedback, 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/productboard/feedbacks. | 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/productboard/feedbacks with your API key. | cron or GitHub Actions. |
Tools
For AI agents: Every endpoint and its schema is public. The 12 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 Productboard.
list_feedback
Feedback items from your insights boards, with company, user, tags, owner, processed flag and insight count. Access: read. REST: GET /api/v1/productboard/feedbacks. MCP: productboard_read → list_feedback.
| Parameter | Type | Required | Description |
|---|---|---|---|
processed | boolean | no | true for processed items, false for unprocessed. Leave out for both. |
query | string | no | Words from the title. |
cursor | string | no | Next page cursor from the previous call. |
Lists feedback items in your workspace as the Library feedback list shows them. Each row gives the title, the company and user, tags, the owner, whether it is processed and how many insights link it to features. processed true returns processed items, false the unprocessed ones, and leaving it out returns both. query matches the title. Pass id to get_feedback for the full text. Pass next_cursor back as cursor for the next page.
Example response:
{
"feedback": [
{
"id": "fb_81c2a9",
"title": "Export to CSV is too slow",
"company": "Northwind",
"user": "Dana Ruiz",
"tags": [
"interview"
],
"owner": "Priya Nair",
"processed": false,
"insights": 0,
"created_at": "2026-10-21T09:12:00Z"
},
{
"id": "fb_81c2b4",
"title": "Call with Bluepeak, 20 Oct",
"company": "Bluepeak",
"user": "Sam Ito",
"tags": [
"q4"
],
"owner": "Priya Nair",
"processed": false,
"insights": 2,
"created_at": "2026-10-20T16:40:00Z"
}
],
"next_cursor": "eyJwIjoyfQ"
}
get_feedback
One feedback item with its full text, company, user, tags and the insights that link it to features. Access: read. REST: GET /api/v1/productboard/feedbacks/{feedback_id}. MCP: productboard_read → get_feedback.
| Parameter | Type | Required | Description |
|---|---|---|---|
feedback_id | string | yes | Feedback item ID from list_feedback. |
Returns the whole text of one feedback item, not a preview, with the company, the user, the tags, the owner and the processed flag. links lists each insight: the feature it points to, the highlighted quote and the importance. ai_summary is filled only in workspaces where Productboard Spark has written one, otherwise it is null. Images and attachments are not returned.
Example response:
{
"id": "fb_81c2a9",
"title": "Export to CSV is too slow",
"content": "Exporting 50,000 rows to CSV takes over ten minutes and then times out. We now split the export by month.",
"company": "Northwind",
"user": "Dana Ruiz",
"tags": [
"interview"
],
"owner": "Priya Nair",
"processed": false,
"ai_summary": null,
"links": [],
"created_at": "2026-10-21T09:12:00Z"
}
search_features
Features in your product hierarchy by name, with status, owner and parent. Access: read. REST: GET /api/v1/productboard/features/search. MCP: productboard_read → search_features.
| Parameter | Type | Required | Description |
|---|---|---|---|
query | string | no | Words from the feature name. |
status | string | no | A status name from list_feature_statuses. |
cursor | string | no | Next page cursor from the previous call. |
Searches the features of your hierarchy by name and returns the id, name, status, owner and parent component of each match. status narrows the result to one status name from list_feature_statuses. Subfeatures are included, with their parent feature. Pass next_cursor back as cursor for the next page.
Example response:
{
"features": [
{
"id": "ft_4d7e10",
"name": "CSV export",
"status": "Delivery",
"owner": "Lena Brandt",
"parent": "Reporting"
},
{
"id": "ft_4d7e33",
"name": "Scheduled export",
"status": "Discovery",
"owner": "Lena Brandt",
"parent": "Reporting"
}
],
"next_cursor": null
}
get_feature
One feature with its description, status, owner, parent and the number of linked insights. Access: read. REST: GET /api/v1/productboard/features/{feature_id}. MCP: productboard_read → get_feature.
| Parameter | Type | Required | Description |
|---|---|---|---|
feature_id | string | yes | Feature ID from search_features. |
Returns one feature or subfeature: name, description, status, owner, parent and how many insights are linked to it. Use list_feature_insights for the insights themselves.
Example response:
{
"id": "ft_4d7e10",
"name": "CSV export",
"description": "Export any report to CSV from the reports page.",
"status": "Delivery",
"owner": "Lena Brandt",
"parent": "Reporting",
"insights": 6
}
list_feature_insights
Insights linked to a feature: the feedback title, the highlighted quote and the importance. Access: read. REST: GET /api/v1/productboard/feature-insights. MCP: productboard_read → list_feature_insights.
| Parameter | Type | Required | Description |
|---|---|---|---|
feature_id | string | yes | Feature ID from search_features. |
cursor | string | no | Next page cursor from the previous call. |
Lists the insights on the Insights tab of one feature. Each has the feedback id and title, the quote that was highlighted, the importance (unknown, nice_to_have, important or critical) and the link type: manual, AI to verify or AI verified. Pass next_cursor back as cursor for the next page.
Example response:
{
"insights": [
{
"feedback_id": "fb_81a7c0",
"feedback_title": "Reports are hard to share",
"quote": "I cannot get the CSV out for my CFO without a developer.",
"importance": "important",
"link_type": "manual"
},
{
"feedback_id": "fb_81b002",
"feedback_title": "Call with Acme, 14 Oct",
"quote": "CSV with a date range is the first thing we would use.",
"importance": "nice_to_have",
"link_type": "manual"
}
],
"next_cursor": null
}
list_feature_statuses
The status names your workspace uses for features and subfeatures. Access: read. REST: GET /api/v1/productboard/feature-statuses. MCP: productboard_read → list_feature_statuses.
No parameters.
Returns the statuses of your workspace in the order Productboard shows them. Features and subfeatures share one list. Custom statuses exist on the Business and Enterprise plans, so use the names from this call, not the ones from another workspace, in update_feature_status.
Example response:
{
"statuses": [
"New idea",
"Discovery",
"Design",
"Planned for delivery",
"Delivery",
"Testing",
"Launched",
"Won't do"
]
}
list_objectives
Objectives with their status and key results. Access: read. REST: GET /api/v1/productboard/objectives. MCP: productboard_read → list_objectives.
| Parameter | Type | Required | Description |
|---|---|---|---|
query | string | no | Words from the objective name. |
cursor | string | no | Next page cursor from the previous call. |
Lists the objectives of your workspace with their status, owner and key results. Each key result has its own status. An objective with no key results comes back with an empty list, so you can find the ones that still need one. Pass next_cursor back as cursor for the next page.
Example response:
{
"objectives": [
{
"id": "ob_21f0",
"name": "Make reporting self-serve",
"status": "On track",
"owner": "Priya Nair",
"key_results": [
{
"id": "kr_90a1",
"name": "Share of reports exported without help",
"status": "On track"
}
]
},
{
"id": "ob_21f4",
"name": "Cut onboarding time",
"status": "At risk",
"owner": "Lena Brandt",
"key_results": []
}
],
"next_cursor": null
}
create_feedback
Adds a feedback item with a title, text, company, user and tags. Access: write. REST: POST /api/v1/productboard/feedbacks. MCP: productboard_write → create_feedback.
| Parameter | Type | Required | Description |
|---|---|---|---|
title | string | yes | A short line naming the source, such as an email or a meeting. |
content | string | yes | The feedback text. |
company | string | no | Company the feedback came from. |
user | string | no | Person the feedback came from. |
tags | array | no | Tag names to apply. |
Creates one feedback item the way Submit feedback does: title, text, and the company and user it came from. The company and user feed the Customer Importance Score, so give them when you know them. tags are applied only if your workspace uses tags. The item arrives unprocessed with no owner. The text is plain text; images and attachments are not uploaded. It reaches no one and you can edit it in Productboard, so it does not wait for your OK. You need the admin, maker or contributor role; a viewer gets APP_PERMISSION_DENIED.
Example response:
{
"id": "fb_81c2c7",
"title": "Call with Northwind, 21 Oct",
"company": "Northwind",
"user": "Dana Ruiz",
"tags": [
"interview",
"q4"
],
"processed": false,
"url": "https://yourteam.productboard.com/feedback/fb_81c2c7"
}
link_feedback_to_feature
Highlights a quote in a feedback item and links it to a feature with an importance. Access: write. REST: POST /api/v1/productboard/features/{feature_id}/feedbacks/{feedback_id}/to-feature/link. MCP: productboard_write → link_feedback_to_feature.
| Parameter | Type | Required | Description |
|---|---|---|---|
feedback_id | string | yes | Feedback item ID from list_feedback. |
feature_id | string | yes | Feature ID from search_features. |
quote | string | yes | Text copied from the feedback body to highlight. |
importance | enum | yes | unknown, nice_to_have, important or critical. |
Creates an insight: the quote you give is highlighted in the feedback item and linked to the feature with an importance. importance is one of unknown, nice_to_have, important or critical, which add +1, +1, +2 and +3 to the feature. quote must be text from the feedback. Linking the same item to another feature is a second call. It reaches no one and unlink_insight undoes it, so it does not wait for your OK.
Example response:
{
"feedback_id": "fb_81c2a9",
"feature": {
"id": "ft_4d7e10",
"name": "CSV export"
},
"quote": "Exporting 50,000 rows to CSV takes over ten minutes and then times out.",
"importance": "important",
"linked": true
}
unlink_insight
Removes the link between a feedback item and a feature. Access: write. REST: POST /api/v1/productboard/feedbacks/{feedback_id}/insight/unlink. MCP: productboard_write → unlink_insight.
| Parameter | Type | Required | Description |
|---|---|---|---|
feedback_id | string | yes | Feedback item ID from list_feedback. |
feature_id | string | yes | Feature ID from search_features. |
Removes the insight that links one feedback item to one feature, like the small x next to a link. The feedback item stays, and so do its other links. It reaches no one and link_feedback_to_feature puts it back, so it does not wait for your OK.
Example response:
{
"feedback_id": "fb_81c2a9",
"feature_id": "ft_4d7e10",
"unlinked": true
}
mark_feedback_processed
Marks a feedback item processed, or takes it back to unprocessed. Access: write. REST: POST /api/v1/productboard/feedbacks/{feedback_id}/processed/mark. MCP: productboard_write → mark_feedback_processed.
| Parameter | Type | Required | Description |
|---|---|---|---|
feedback_id | string | yes | Feedback item ID from list_feedback. |
processed | boolean | yes | true to mark processed, false to mark unprocessed. |
Sets the processed flag of one feedback item, the same as Mark processed in the item sidebar. processed false takes it back to the queue. It reaches no one and one more call undoes it, so it does not wait for your OK.
Example response:
{
"feedback_id": "fb_81c2a9",
"processed": true
}
update_feature_status
Changes the status of a feature or subfeature. Access: write, asks the user first. REST: PATCH /api/v1/productboard/features/{feature_id}/status. MCP: productboard_write → update_feature_status.
| Parameter | Type | Required | Description |
|---|---|---|---|
feature_id | string | yes | Feature ID from search_features. |
status | string | yes | A status name from list_feature_statuses. |
Sets the status of one feature to a name from list_feature_statuses; an unknown name fails and lists the valid ones. Teammates see the new status on the feature and on boards. On the Enterprise plan a lifecycle rule can require fields before a status, so fill those in Productboard first. The response gives the old and the new status. By default you confirm each call; you can switch that off for this tool.
Example response:
{
"feature_id": "ft_4d7e10",
"name": "CSV export",
"status": {
"previous": "Delivery",
"current": "Launched"
}
}
How do I connect Productboard to ChatGPT, Claude, Cursor or Codex?
Connecting Productboard takes three steps: sign up, sign in to Productboard 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 Productboard to your agent.
-
Create an account Sign up and add Productboard 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 Productboard in your Cloud Browser Open your Cloud Browser in the console: your own Chrome in the cloud. Sign in to Productboard 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 Productboard 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.
Go through unprocessed feedback in Productboard. For each item, find the feature it is about, link the most relevant quote with an importance, and mark it processed. Leave the ones you are unsure about for me.
Call Productboard 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/productboard 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/productboard/feedbacks \
-H "Authorization: Bearer $COTLET_API_KEY" \
-H "Content-Type: application/json" \
-d '{"title":"Call with Northwind, 21 Oct","content":"Dana said the weekly export fails for her largest workspace and her team now copies the numbers by hand.","company":"Northwind","user":"Dana Ruiz","tags":["interview","q4"]}'
- Read the result You get plain JSON back, ready for your script. A failed call costs nothing.
{
"id": "fb_81c2c7",
"title": "Call with Northwind, 21 Oct",
"company": "Northwind",
"user": "Dana Ruiz",
"tags": [
"interview",
"q4"
],
"processed": false,
"url": "https://yourteam.productboard.com/feedback/fb_81c2c7"
}
How to use the Productboard REST API
Create your Cotlet API key
Create a Cotlet API key with access to Productboard and its read operations. Store it as COTLET_API_KEY in your environment or automation platform's credential store.
Connect Productboard in Cotlet and enable it for agents. Account access: Your own Productboard login (admin, maker or contributor; viewers cannot add feedback). What your agent can do follows your role. You sign in in your own browser and keep your SSO or 2-step verification.
Make your first Productboard API request
REST:
curl https://cotlet.dev/api/v1/productboard/feedbacks \
-H "Authorization: Bearer $COTLET_API_KEY"
Read feedback 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": "productboard",
"tool": "list_feedback",
"result": {
"feedback": [
{
"id": "fb_81c2a9",
"title": "Export to CSV is too slow",
"company": "Northwind",
"user": "Dana Ruiz",
"tags": [
"interview"
],
"owner": "Priya Nair",
"processed": false,
"insights": 0,
"created_at": "2026-10-21T09:12:00Z"
},
{
"id": "fb_81c2b4",
"title": "Call with Bluepeak, 20 Oct",
"company": "Bluepeak",
"user": "Sam Ito",
"tags": [
"q4"
],
"owner": "Priya Nair",
"processed": false,
"insights": 2,
"created_at": "2026-10-20T16:40:00Z"
}
],
"next_cursor": "eyJwIjoyfQ"
}
}
Lists feedback items in your workspace as the Library feedback list shows them. Each row gives the title, the company and user, tags, the owner, whether it is processed and how many insights link it to features. processed true returns processed items, false the unprocessed ones, and leaving it out returns both. query matches the title.
Pass id to get_feedback for the full text. Pass next_cursor back as cursor for the next page.
cursor: Next page cursor from the previous call.
Keep the same selection when continuing a list. Compare changed record values as well as identifiers when refreshing your destination.
Productboard workflows for agents and automations
| Tool | Connect through | Example workflow |
|---|---|---|
| n8n | HTTP Request | One feedback item with its full text, company, user, tags and the insights that link it to features. Use get_feedback in your configured workspace report. |
| Make | HTTP > Make a request | One feature with its description, status, owner, parent and the number of linked insights. Use get_feature in your configured workspace report. |
| Python or Node.js | REST API | Insights linked to a feature: the feedback title, the highlighted quote and the importance. Use list_feature_insights in your configured workspace report. |
Send Authorization: Bearer <your Cotlet API key> in request headers. You configure the schedule, destination and record comparisons.
Cotlet reads Productboard; 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 Productboard?
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 Productboard 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 Productboard changes, the tool pauses until we fix it.
- Failed calls cost nothing.
Is it safe to connect Productboard to Cotlet?
Yes. You sign in to Productboard yourself, in your own Cloud Browser, and we never save your password. Your agents only get Productboard 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 Productboard integration?
No, Cotlet is independent of Productboard. Productboard's own API is too limited for this work. Cotlet works through your own Productboard account, the way you use Productboard 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 Productboard in your console: your agents lose access at once and you stay signed in. Signing out of Productboard in the browser works too, and Reset browser deletes the whole profile.
Is there a Productboard MCP server on GitHub?
Yes. Community Productboard MCP servers exist on GitHub, usually maintained by one person. You install one yourself, give it an API token from a workspace admin, and fix it when Productboard changes. Cotlet hosts the same kind of server for you, works in your own login, and our team keeps it working.
| GitHub MCP server | Cotlet | |
|---|---|---|
| Setup | Clone the repo, get an API token from a workspace admin on the Pro plan or higher, add the server to each MCP client | Sign up, sign in to Productboard once, add one MCP server or API key |
| When Productboard changes | It breaks until you or the maintainer fix it; API v1 was scheduled for sunset on 8 July 2026, so servers built on v1 need a rewrite | Our team tests it daily and fixes it for you; failed calls are free |
| Your Productboard access | An admin API token 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 replace the token by hand | Your Cloud Browser keeps you signed in; if Productboard 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 Productboard 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 Productboard API cost?
Free 7-day trial with 2,000 credits, no card needed. After that, the Productboard 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 Productboard 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 Productboard 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 Productboard only after you enable it. When Productboard signs you out, your agent gives you a link to sign in again. Security
- Revoking access: Press Disable for agents next to Productboard, sign out of Productboard 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.
- Productboard's terms: You use your own Productboard account and stay responsible for following Productboard's terms. Cotlet is independent and not affiliated with Productboard. Terms
- Contact: Questions about the company, security or an app: contact@cotlet.dev
Productboard API and MCP: questions
How do I get access?
Sign up free, open Productboard in the console and press Activate. Then you create your API key and connect Productboard there.
Do I need to be technical?
No. You sign in to Productboard 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 Productboard to Cotlet?
Yes. You sign in to Productboard yourself, in your own Cloud Browser in the EU, and we never save your password. Your agents only get Productboard 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 Productboard 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 Productboard 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 Productboard's pages. It sends the same requests your browser would, from your browser's IP with its cookies, without opening a window. Productboard 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 Productboard 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?
Productboard 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 Productboard to ChatGPT or Claude?
Sign up at cotlet.dev, log in to Productboard 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 Productboard account through Cotlet, in their phone apps too.
What can ChatGPT do in Productboard?
With Cotlet, ChatGPT, Claude and other AI agents handle jobs like these in Productboard: triage new customer feedback; log customer calls as feedback; update feature statuses after a release. You ask in plain words, and anything that reaches other people waits for your OK first.
Do I need to be a workspace admin?
No. Cotlet works in your own Productboard login, so your role decides what your agent can do. Productboard's API tokens need a workspace admin on the Pro plan or higher, which is why many makers cannot use the API at all. Viewers cannot add feedback, and create_feedback fails with APP_PERMISSION_DENIED for them.
How is this different from Productboard's own MCP server?
Productboard's MCP server is in beta. An admin turns it on under Settings > MCP Server and picks the roles that may use it, and you sign in with OAuth. Its documentation describes finding, reading, refining and commenting on specs and updating an item status. Cotlet's tools work on feedback, insight links, features, statuses and objectives.
Can it change roadmaps and boards?
No. The tools cover feedback, features, statuses and objectives. Timeline and columns boards stay in Productboard, and so do milestones, board filters and customer-specific roadmaps.
Can my agent post or send messages in Productboard without asking me?
No. Every call to update_feature_status 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_feedback, link_feedback_to_feature, unlink_insight and mark_feedback_processed run without asking, because they send nothing to anyone and one call undoes it.
Can I use the Productboard 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/productboard from the HTTP Request node.
Can I use the Productboard 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.