favro-mcp
Provides read-only access to Favro project management data, including collections, boards, cards, comments, and checklists.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@favro-mcp find cards about deployment issues in the engineering board"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
favro-mcp
An MCP server that gives your AI assistant read access to Favro — collections, boards, cards, comments and checklists.
Read-only by design. Every one of the 14 tools issues a GET and nothing else. There is no code path in this package that can create, change, archive or delete anything in your Favro account — a test asserts it on every commit. You are handing over an API token, so that guarantee is the point.
Install
Nothing to install. Point your MCP client at npx:
{
"mcpServers": {
"favro": {
"command": "npx",
"args": ["-y", "favro-mcp"],
"env": {
"FAVRO_EMAIL": "you@example.com",
"FAVRO_API_TOKEN": "your-api-token",
"FAVRO_ORGANIZATION_ID": ""
}
}
}
}Requires Node 18 or newer.
Getting a Favro API token
In Favro: profile menu → My profile → API tokens → Create new token. The token pairs with the email address you sign in with; both are needed.
FAVRO_ORGANIZATION_ID is optional. Leave it empty and ask your assistant to run list-organizations — it will return the ids you have access to, and you can either paste one into the config or let the assistant pass it per call.
Per-client setup
claude mcp add favro --env FAVRO_EMAIL=you@example.com --env FAVRO_API_TOKEN=your-api-token -- npx -y favro-mcpOr add the JSON block above to .mcp.json in your project root.
Edit claude_desktop_config.json:
macOS —
~/Library/Application Support/Claude/claude_desktop_config.jsonWindows —
%APPDATA%\Claude\claude_desktop_config.json
Paste the JSON block above, then fully quit and reopen Claude Desktop — reloading the window is not enough.
Edit ~/.cursor/mcp.json (global) or .cursor/mcp.json (per project) and paste the JSON block above.
Add to .vscode/mcp.json, using servers rather than mcpServers:
{
"servers": {
"favro": {
"command": "npx",
"args": ["-y", "favro-mcp"],
"env": {
"FAVRO_EMAIL": "you@example.com",
"FAVRO_API_TOKEN": "your-api-token"
}
}
}
}Related MCP server: linear-mcp
Tools
Tool | Purpose | Required arguments |
| Organizations the account belongs to | — |
| Collections shared with the account | — |
| One collection |
|
| Boards and backlogs, optionally by collection | — |
| One board, with its columns and lanes |
|
| A board's columns |
|
| Cards on a board, in a collection, or in your todo list | one of |
| Full detail on one card |
|
| Find cards by text in their name or description |
|
| A card's comments |
|
| A card's checklists |
|
| Checklist items |
|
| Users in the organization | — |
| One user |
|
Every tool also accepts an optional organizationId to override the configured default.
Configuration
Variable | Required | Default | Purpose |
| yes | — | The email you sign in to Favro with |
| yes | — | An API token from your Favro profile |
| no | — | Default organization; otherwise pass |
| no |
| Seconds to cache slow-changing entities. |
Things worth knowing
The API's vocabulary differs from the UI
API term | What you see in Favro |
widget | A board or backlog |
tasklist | A checklist on a card |
task | A single checklist item |
Cards have two ids
cardIdidentifies one card on one board.get-cardtakes this.cardCommonIdidentifies the card across every board it appears on. The comment and checklist tools take this.
Both come back from list-cards and get-card.
A typical path through the hierarchy
list-organizations (only when FAVRO_ORGANIZATION_ID is unset)
→ list-collections find the collection
→ list-boards boards in that collection
→ get-board its columns and lanes, in one call
→ list-cards cards on the board or in a column
→ get-card full detail on one card
→ list-card-comments / list-card-tasklists / list-card-tasksPagination
Listings return up to 100 entities. When more remain, the response carries a cursor:
"pagination": {
"page": 0,
"pages": 3,
"requestId": "...",
"backendId": "...",
"next_page": { "page": 1, "requestId": "...", "backendId": "..." }
}Call the same tool again passing page, requestId and backendId exactly as given. All three are required — Favro routes follow-up pages to the same backend server, and the backendId is what gets them there.
search-cards is a local filter, not a search endpoint
Favro's API has no card search. search-cards reads cards from a board or collection and filters them by case-insensitive substring on name and description. It reads up to maxPages pages (default 3, maximum 10), each costing one API call, and reports what it covered:
"scan": {
"cards_scanned": 250,
"matches_found": 4,
"pages_read": 3,
"pages_available": 5,
"complete": false,
"note": "Only 3 of 5 pages were searched. Raise maxPages..."
}When complete is false, narrow the scope or raise maxPages rather than treating the result as exhaustive.
Rate limits and caching
Favro's hourly budget is low and plan-dependent — 100/hour on Trial up to 10,000/hour on Enterprise, with list-organizations and the user tools sharing a separate 50/hour budget. Every response carries a rate_limit block showing what is left.
To conserve calls, organizations, users, collections, boards and columns are cached for FAVRO_CACHE_TTL seconds. Cached responses are marked "cached": true. Cards, comments and checklists are never cached, so they are always current.
Not covered
Tags, custom field definitions, groups and webhooks are not exposed, and nothing writes to Favro. Open an issue if you need something added.
Development
npm install
npm test
npm run buildInspect the server interactively against your real account:
FAVRO_EMAIL=you@example.com FAVRO_API_TOKEN=your-token npx @modelcontextprotocol/inspector node dist/index.jsLicense
MIT
Available Tools
14 toolsget-boardARead-only
Get a single Favro board (widget) by its widgetCommonId, including its lanes and columns. This is the cheapest way to learn a board's column layout before listing cards. Results are cached.
Inputs: widgetCommonId (required), organizationId.
get-cardARead-only
Get one Favro card by its cardId, with the full untruncated description plus custom fields, dependencies, attachments, and time-on-board data. Use the cardCommonId from the result to fetch the card's comments and checklists. Not cached, so results are always current.
Inputs: cardId (required), organizationId, descriptionFormat.
get-collectionARead-only
Get a single Favro collection by id, including its sharing level and archived state. Results are cached.
Inputs: collectionId (required), organizationId.
get-userARead-only
Look up a single Favro user by id. Results are cached.
Inputs: userId (required), organizationId.
list-boardsARead-only
List Favro boards and backlogs, optionally filtered to one collection. The Favro API calls these "widgets", and each is identified by a widgetCommonId that other tools take. Type "board" is a Kanban board, type "backlog" is a card list. Results are cached.
Inputs: page, archived, backendId, requestId, +2 more.
list-card-commentsARead-only
Read the comments on a Favro card. Takes the card's cardCommonId, not its cardId, because comments are shared across every instance of the card. Use list-users to turn the returned userIds into names. Not cached, so results are always current.
Inputs: cardCommonId (required), page, backendId, requestId, +1 more.
list-cardsARead-only
List Favro cards on a board, in a collection, or in the account's todo list. You must scope the call with one of widgetCommonId, collectionId, cardCommonId, cardSequentialId, or todoList. columnId narrows the results further but cannot be used on its own. Card descriptions are truncated here; use get-card for the full text. Not cached, so results are always current.
Inputs: page, unique, archived, columnId, +9 more.
list-card-tasklistsARead-only
List the checklists on a Favro card. The Favro API calls these "tasklists". Takes the card's cardCommonId. Pass a returned taskListId to list-card-tasks to read the items in one checklist. Not cached, so results are always current.
Inputs: cardCommonId (required), page, backendId, requestId, +1 more.
list-card-tasksARead-only
List the checklist items on a Favro card, with their completed state. The Favro API calls these "tasks". Takes the card's cardCommonId, and optionally a taskListId to read a single checklist. Not cached, so results are always current.
Inputs: cardCommonId (required), page, backendId, requestId, +2 more.
list-collectionsARead-only
List the Favro collections shared with the account. A collection groups related boards and backlogs, so this is the usual entry point for exploring an organization. Results are cached.
Inputs: page, archived, backendId, requestId, +1 more.
list-columnsARead-only
List the columns on a Favro board, with each column's position and card count. Use the returned columnId to narrow list-cards to a single column. Results are cached.
Inputs: widgetCommonId (required), page, backendId, requestId, +1 more.
list-organizationsARead-only
List the Favro organizations the configured account belongs to. Start here when no organization is configured, then pass the organizationId to other tools. This route is limited to 50 calls per hour, so results are cached.
Inputs: page, backendId, requestId.
list-usersARead-only
List the users in a Favro organization, with their id, name, email, and role. Use this to resolve the userIds returned on card assignments and comments. Results are cached.
Inputs: page, backendId, requestId, organizationId.
search-cardsARead-only
Find Favro cards whose name or description contains a piece of text. The Favro API has no card search, so this reads the cards on a board or in a collection and filters them here. Scope it with widgetCommonId or collectionId. Each 100 cards scanned costs one API call, so the scan stops after maxPages pages and reports whether it was cut short.
Inputs: query (required), archived, columnId, maxPages, +3 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 14 tools
Every tool targets a distinct resource and action, with clear boundaries between listing, getting, and searching. Even tools like list-cards and search-cards are differentiated by scoping and behavior.
All tools follow a consistent verb_noun pattern using either 'list-' for collections or 'get-' for single entities, making the naming predictable and easy to understand.
14 tools is a well-scoped set for a project management API, covering all major resource types without being bloated or sparse.
The tool set is entirely read-only, lacking any create, update, or delete operations for cards, boards, comments, etc. This is a significant gap for typical workflow automation, severely limiting the server's utility.
Maintenance
Related MCP Connectors
Unofficial remote MCP server for Less Annoying CRM: OAuth 2.1, read-only grants, 10 tools.
Official Todoist MCP server. Manage tasks and projects. Hosted, no API key needed.
OAuth-protected, read-only-by-default MCP server for provenance-labeled QuillCaddie project memory.
Read-only MCP server for ClassQuill, a tutoring-business-management platform.
Related MCP Servers
- AlicenseBqualityBmaintenanceAn MCP server for interacting with the Favro project management platform. It enables users to manage organizations, boards, columns, and cards through actions like task creation, assignment, and status updates.285MIT
- AlicenseAqualityDmaintenanceA read-only MCP server for Linear that enables listing teams, cycles, and issues, and searching issues via the Linear API.5578 npmMIT
- FlicenseNot gradedqualityDmaintenanceA read-only MCP server for accessing Mobilize public API data, including organizations, events, and enums.-
- AlicenseAqualityDmaintenanceA read-only MCP server that gives LLM agents deterministic operational facts about Trello boards, including structural history, card movement, workflow flow, staleness, and due-date information.14MIT