MCP Server

Jira MCP server with scoped API tokens via api.atlassian.com gateway

Local serverstdioGo

What is the MCP MCP server?

MCP MCP server exists for a simple reason — assistants are far more useful when they can act on MCP directly instead of describing what you should do. Jira MCP server with scoped API tokens via api.atlassian.com gateway.

What you get

Every other Jira MCP server uses classic (unscoped) API tokens with basic auth against yoursite.atlassian.net. Atlassian is deprecating those. This server uses scoped tokens with the modern api.atlassian.com gateway — the way Atlassian intends these tokens to be used.

What the assistant can call

Once MCP is connected, these are the calls the assistant has available:

  • read — jira-work — read issues, search, comments, projects
  • write — jira-work — create/update/delete issues, add comments
  • jira_get_issue — Get issue by key. Pass includeCustomFields: true to return all custom fields
  • jira_search — Search issues via JQL with pagination
  • jira_list_comments — List comments on an issue
  • jira_list_projects — List accessible projects
  • jira_get_project — Get project details by key
  • jira_list_link_types — List available issue link types
  • jira_list_fields — List all fields (system + custom) — discover customfield_* IDs
  • jira_list_attachments — List attachments on an issue with filename, size, MIME type, and download URL
  • jira_get_transitions — Get available transitions for an issue with required screen fields expanded
  • jira_create_issue — Create an issue (task, bug, story, epic). Supports custom fields

Configuration and credentials

You will need 5 environment variables: JIRA_INSTANCE, JIRA_USER_EMAIL, JIRA_API_TOKEN, JIRA_SCOPES, JIRA_CLOUD_ID. The server will not start without them, which is usually why the tools fail to appear on a first run. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.

Setting it up

mcp-jira-scoped on npm is all you need. Most clients run it directly, so configuration is a few lines and a restart.

Choosing this one

Plenty of planning and project tracking servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. MCP's toolset — read, write, jira_get_issue and 11 more — is a fair guide to whether it matches your workflow. It is maintained by deepwired; worth a glance at recent repository activity before you build anything load-bearing on it.

We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.

Before you rely on it

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • With 14 tools registered it takes up a noticeable share of the context window; turn it off in projects that never touch MCP.
  • Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
  • MCP clients confirm each tool call by default. Leave that on until you have watched what the mcp mcp server does with a few real requests.

Available tools

ToolWhat it does
readjira-work — read issues, search, comments, projects
writejira-work — create/update/delete issues, add comments
jira_get_issueGet issue by key. Pass includeCustomFields: true to return all custom fields
jira_searchSearch issues via JQL with pagination
jira_list_commentsList comments on an issue
jira_list_projectsList accessible projects
jira_get_projectGet project details by key
jira_list_link_typesList available issue link types
jira_list_fieldsList all fields (system + custom) — discover customfield_* IDs
jira_list_attachmentsList attachments on an issue with filename, size, MIME type, and download URL
jira_get_transitionsGet available transitions for an issue with required screen fields expanded
jira_create_issueCreate an issue (task, bug, story, epic). Supports custom fields
jira_update_issueUpdate fields on an issue. Supports custom fields
jira_add_commentAdd a comment (plain text auto-converted to ADF)

How to install the MCP MCP server

{
  "mcpServers": {
    "jira": {
      "command": "npx",
      "args": ["-y", "mcp-jira-scoped"],
      "env": {
        "JIRA_INSTANCE": "yourcompany",
        "JIRA_USER_EMAIL": "you@yourcompany.com",
        "JIRA_API_TOKEN": "<your-scoped-token>",
        "JIRA_SCOPES": "read:jira-work,write:jira-work"
      }
    }
  }
}

Configuration as documented by the project. Restart the client after saving.

Configuration

VariableDescriptionRequired
JIRA_INSTANCEConfiguration value read at startup.Optional
JIRA_USER_EMAILConfiguration value read at startup.Optional
JIRA_API_TOKENCredential the server authenticates with.Yes
JIRA_SCOPESConfiguration value read at startup.Optional
JIRA_CLOUD_IDConfiguration value read at startup.Optional

Example prompts to try

  • Use MCP to read.
  • Use MCP to write.
  • Use MCP to jira get issue.

Frequently asked questions

It connects MCP to MCP-compatible AI assistants such as Claude and Cursor, exposing 14 tools (read, write, jira_get_issue, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with MCP directly.