LABSCO SUMMARY

A wide surface with a single tool that can do anything, and the guardrail on that tool is a sentence.

The bulk-first design is the strength — issue_ids plurals across close, reopen, move, assignee, label and milestone edits mean a board reshuffle is a single request rather than a loop, and zenhub_get_workspace_overview is the entry point the rest of the list assumes you called first. The thing to weigh is zenhub_query_potentially_dangerous: it executes arbitrary GraphQL including mutations, and its only protection is an instruction in its own description telling the caller to obtain explicit approval, which is guidance to a model rather than a check. One documented dead end is worth noting too — zenhub_get_repository_collaborators states that repository collaborators are not available through the ZenHub API and points at zenhub_get_workspace_users instead.

What it is

A ZenHub workspace client with 51 tools covering issue creation and editing, bulk assignee, label, estimate and milestone changes, epics and sub-issues, workspaces and repositories, sprints, pipelines, blocking dependencies, label creation on both the GitHub and ZenHub side, user lookup, search, and a raw GraphQL escape hatch.

What you get

Bulk editing as the default shape: zenhub_close_issues, zenhub_reopen_issues, zenhub_move_issue, zenhub_add_assignees_to_issues, zenhub_remove_assignees_from_issues, zenhub_add_labels_to_issues, zenhub_remove_labels_from_issues and zenhub_add_milestone_to_issues all take issue_ids rather than a single issue, and zenhub_set_multiple_estimates takes an estimates list.
Board position as a parameter: zenhub_move_issue takes pipeline_id and position, and zenhub_reopen_issues takes the same pair, so reopening an issue lands it somewhere chosen rather than wherever it was.
Epics with children and dates: zenhub_create_epic can take epic_child_ids at creation time, zenhub_add_subissues_to_epic attaches existing issues to a parent_epic_id afterwards, and zenhub_update_epic_dates sets start_date and end_date.
A single call that orients you in a workspace: zenhub_get_workspace_overview returns pipelines with issue counts, repositories with issue counts, the default repository and its issue types, epic summaries and workspace users — and zenhub_search_issues_in_repository says outright to call it first for the repository and pipeline IDs it needs.
Sprints and milestones kept apart: zenhub_create_sprint takes start_date, end_date, timezone and settings, zenhub_update_sprint can change state, and zenhub_add_issues_to_sprints maps issue_ids onto sprint_ids, while zenhub_create_milestone and zenhub_update_milestone carry due_date and start_date on the repository side.
Blocking relationships as data: zenhub_create_issue_dependency and zenhub_delete_issue_dependency take the blocking and blocked issue numbers with their repository GitHub IDs, so a dependency can span repositories.
Labels on both sides of the integration: zenhub_create_github_label writes to a repository_id and zenhub_create_zenhub_label writes to a workspace_id, with zenhub_get_repository_labels and zenhub_get_workspace_labels reading each side back.
Search scoped to wherever you are looking: zenhub_search_issues filters inside one pipeline_id by title, labels or assignees, zenhub_search_issues_in_repository spans repo_ids and pipeline_ids within a workspace, and zenhub_get_workspace_issues pages the whole workspace with after.
A fallback for everything the list does not cover: zenhub_query_potentially_dangerous runs a custom GraphQL query with variables.

Requirements

ZENHUB_API_KEY. Past that, identifiers are the real prerequisite: the write tools address a workspace_id, repository_id, pipeline_id or issue_ids, and zenhub_get_user_organizations, zenhub_get_user_workspaces and zenhub_get_workspace_overview are how you come by them. zenhub_get_viewer confirms which ZenHub and GitHub identity the key resolves to.

Setup effort

One command plus a key — npx zenhub-mcp-server, then supply credentials

See installation options

USE CASES

01

Reshuffling a board before a sprint starts

Read the workspace to get its pipelines and their issue counts, move the tickets that belong elsewhere into position, and set estimates across the batch in one go.

zenhub_get_workspace_overviewzenhub_get_workspace_pipelineszenhub_move_issuezenhub_set_multiple_estimates

02

Filing an epic with the work already known

Create the epic with its existing issues attached as children, add any that turn up later, and put start and end dates on it.

zenhub_create_epiczenhub_add_subissues_to_epiczenhub_update_epic_dates

03

Closing out a batch of finished tickets

Find the issues sitting in the done pipeline, close them all in one call, and tag the batch so the release notes can find it later.

zenhub_search_issueszenhub_close_issueszenhub_add_labels_to_issues

04

Recording what is blocking what

Look the issues up by repository and number, declare the blocking relationship between them, and remove it once the dependency clears.

zenhub_get_issue_by_infozenhub_create_issue_dependencyzenhub_delete_issue_dependency

05

Setting up a sprint and filling it

Create the sprint with its dates and timezone, check what sprints the workspace already has, then map the chosen issues onto it.

zenhub_create_sprintzenhub_get_workspace_sprintszenhub_add_issues_to_sprints

06

Finding out who can be assigned in a new repository

List the repositories the workspace covers, ask which users a repository will accept as assignees, and fall back to the workspace roster when it will not answer.

zenhub_get_workspace_repositorieszenhub_get_repository_assignable_userszenhub_get_workspace_users

51 tools

Counted once with only startup setup. Other versions, modes or optional credentials may expose a different list.

`zenhub_add_assignees_to_issues`

Add assignees to multiple issues

BEFORE YOU INSTALL

What to know first

Tools you get

51 tools when we connected.

Requires

npx on PATH
ZENHUB_API_KEY in your environment
GITHUB_PAT (a GitHub personal access token) in your environment, for the tools that create issues and epics

CONTEXT COST

Moderate Standing cost

Rated by the size of the 51 tool definitions that ride along on every turn, not by how many there are

INSTALLATION

Connect your client

Server setup

TERMINAL

npx zenhub-mcp-server

MCP Clients

Claude Desktop

CLAUDE DESKTOP · JSON

{
  "mcpServers": {
    "zenhub": {
      "command": "npx",
      "args": [
        "zenhub-mcp-server"
      ],
      "env": {
        "ZENHUB_API_KEY": "<YOUR_ZENHUB_API_KEY>",
        "GITHUB_PAT": "github_pat_"
      }
    }
  }
}

<YOUR_ZENHUB_API_KEY> is your ZenHub API key (from https://app.zenhub.com/settings/tokens). github_pat_ is only how a GitHub token starts; GITHUB_PAT is a full GitHub personal access token (from https://github.com/settings/tokens, e.g. with repo scope). Creating an issue or an epic fails with an error when GITHUB_PAT is not set.

Cursor

Clone and build the server

This block runs dist/index.js from your own clone, which exists only after the build.

CURSOR · TERMINAL

git clone https://github.com/derekbar90/zenhub-mcp.git
cd zenhub-mcp
npm install
npm run build

In Cursor, go to Settings > MCP Servers and add:

<YOUR_PATH_TO_ZENHUB_MCP> is the folder you cloned. zh_ and github_pat_ are only the start of each value: paste your full ZenHub API key (from https://app.zenhub.com/settings/tokens) and a full GitHub personal access token (from https://github.com/settings/tokens, e.g. with repo scope). Creating an issue or an epic fails with an error when GITHUB_PAT is not set.

CURSOR · JSON

{
  "mcpServers": {
    "zenhub": {
      "command": "node",
      "args": [
        "<YOUR_PATH_TO_ZENHUB_MCP>/dist/index.js"
      ],
      "env": {
        "ZENHUB_API_KEY": "zh_",
        "GITHUB_PAT": "github_pat_"
      }
    }
  }
}

ZenHub

A wide surface with a single tool that can do anything, and the guardrail on that tool is a sentence.

What it is

What you get

Requirements

Setup effort

Reshuffling a board before a sprint starts

Filing an epic with the work already known

Closing out a batch of finished tickets

Recording what is blocking what

Setting up a sprint and filling it

Finding out who can be assigned in a new repository

51 tools

zenhub_add_assignees_to_issues

zenhub_add_issues_to_sprints

zenhub_add_labels_to_issues

zenhub_add_milestone_to_issues

zenhub_add_repository_to_workspace

zenhub_add_subissues_to_epic

zenhub_close_issues

zenhub_create_epic

zenhub_create_github_label

zenhub_create_issue

zenhub_create_issue_dependency

zenhub_create_milestone

zenhub_create_sprint

zenhub_create_workspace

zenhub_create_zenhub_label

zenhub_delete_issue_dependency

zenhub_get_epic

zenhub_get_issue_by_info

zenhub_get_organization_workspaces

zenhub_get_owner_by_gh_id

zenhub_get_owner_by_login

zenhub_get_repositories

zenhub_get_repositories_by_github_ids

zenhub_get_repository_assignable_users

zenhub_get_repository_collaborators

zenhub_get_repository_details

zenhub_get_repository_labels

zenhub_get_user_organizations

zenhub_get_user_workspaces

zenhub_get_viewer

zenhub_get_workspace_issues

zenhub_get_workspace_labels

zenhub_get_workspace_overview

zenhub_get_workspace_pipelines

zenhub_get_workspace_repositories

zenhub_get_workspace_sprints

zenhub_get_workspace_users

zenhub_move_issue

zenhub_query_potentially_dangerous

zenhub_remove_assignees_from_issues

zenhub_remove_labels_from_issues

zenhub_reopen_issues

zenhub_search_issues

zenhub_search_issues_in_repository

zenhub_set_estimate

zenhub_set_multiple_estimates

zenhub_update_epic

zenhub_update_epic_dates

zenhub_update_issue

zenhub_update_milestone

zenhub_update_sprint

What to know first

Tools you get

Requires

Moderate Standing cost

Connect your client

Server setup

MCP Clients

Claude Desktop

Cursor

Same category

Linear MCP Server by emmett-deen

Redmine MCP

ClickUp Task Context MCP

Productive.io MCP Server

`zenhub_add_assignees_to_issues`

`zenhub_add_issues_to_sprints`

`zenhub_add_labels_to_issues`

`zenhub_add_milestone_to_issues`

`zenhub_add_repository_to_workspace`

`zenhub_add_subissues_to_epic`

`zenhub_close_issues`

`zenhub_create_epic`

`zenhub_create_github_label`

`zenhub_create_issue`

`zenhub_create_issue_dependency`

`zenhub_create_milestone`

`zenhub_create_sprint`

`zenhub_create_workspace`

`zenhub_create_zenhub_label`

`zenhub_delete_issue_dependency`

`zenhub_get_epic`

`zenhub_get_issue_by_info`

`zenhub_get_organization_workspaces`

`zenhub_get_owner_by_gh_id`

`zenhub_get_owner_by_login`

`zenhub_get_repositories`

`zenhub_get_repositories_by_github_ids`

`zenhub_get_repository_assignable_users`

`zenhub_get_repository_collaborators`

`zenhub_get_repository_details`

`zenhub_get_repository_labels`

`zenhub_get_user_organizations`

`zenhub_get_user_workspaces`

`zenhub_get_viewer`

`zenhub_get_workspace_issues`

`zenhub_get_workspace_labels`

`zenhub_get_workspace_overview`

`zenhub_get_workspace_pipelines`

`zenhub_get_workspace_repositories`

`zenhub_get_workspace_sprints`

`zenhub_get_workspace_users`

`zenhub_move_issue`

`zenhub_query_potentially_dangerous`

`zenhub_remove_assignees_from_issues`

`zenhub_remove_labels_from_issues`

`zenhub_reopen_issues`

`zenhub_search_issues`

`zenhub_search_issues_in_repository`

`zenhub_set_estimate`

`zenhub_set_multiple_estimates`

`zenhub_update_epic`

`zenhub_update_epic_dates`

`zenhub_update_issue`

`zenhub_update_milestone`

`zenhub_update_sprint`