Is this an official Jira MCP server?

No. It is Memtro's MCP server with Memtro's Jira connector behind it: the connector reads Jira through its API with the credentials you connect on Dashboard → Connections, and Jira publishes nothing here. The same endpoint carries every other system you connect and Memtro's memory tools.

Nothing on top of Memtro. One price per organisation by its number of users, from $50 a month for up to 10 users after a 7-day free trial, with every connector, the MCP server, jobs and memory included. You bring your own model keys.

Can it change anything in Jira?

Only when you ask, and only what it has been granted: create an issue in a project; comment on an issue; move an issue through its workflow (and change its assignee or labels); change an issue's summary, description, priority, labels, assignee, due date, parent or story points; link two issues (blocks, duplicates, relates to…); log work against an issue. Every other tool reads, searches or lists. An administrator grants each acting tool by name per team, and a personal connection acts only after its owner allows it.

Any MCP client that speaks Streamable HTTP: Claude Code, Cursor, Claude Desktop, OpenCode, Codex, Zed, Windsurf, Cline and the Anthropic and OpenAI SDKs. There is no local process to run; the server is remote and authenticated with your key.

MCP server · Work management

Jira MCP server

Jira in any MCP client, through Memtro: Jira does not publish this server. Memtro's Jira connector reads Jira through its API with the credentials you connect, and one endpoint hands those tools, every other system you connect and Memtro's memory tools to Claude Code, Cursor, Claude Desktop or anything else that speaks Streamable HTTP, as you.

What the model can do

Search issues with JQL, read issue details and comments, list projects and find people by name (Jira Cloud); can also create an issue, comment on one, move it through its workflow, change its fields, link it to another issue and log work against it when you ask.

Reads

jira_searchSearch Jira issues with JQL (e.g. 'project = PAY AND status != Done ORDER BY updated DESC', 'assignee = currentUser()', 'text ~ "webhook"').
jira_get_issueGet one issue by key with description and comments.
jira_usersFind people by name or email and get their Atlassian account id, which is what assigning an issue takes.
jira_projectsList projects (key, name, lead).

Acts, when you ask

These change something in Jira. The model is told to use them only when you ask for exactly that, and each one is granted by name: per team on a shared connection, by the owner on a personal one.

jira_create_issueCreates an issue in a Jira project.
jira_commentComments on a Jira issue, by key.
jira_transitionMoves a Jira issue through its workflow — "In Progress", "Done", "Won't Do" — by the transition's name or the status it leads to…
jira_update_issueChanges an existing Jira issue — its summary, description, priority, labels, assignee, due date, parent or story points.
jira_link_issuesLinks two Jira issues — blocks, is blocked by, duplicates, relates to, causes — so the relationship shows on both.
jira_log_workLogs time against a Jira issue, under the connected account's name.

Connect it

First connect Jira on Dashboard → Connections, then add Memtro to your client once. The Jira tools appear alongside the tools of everything else you have connected; nothing is configured per connector.

Claude Code

One command registers the server; the tools are then available in every session.

claude mcp add --transport http memtro https://platform.memtro.com/api/mcp \
  --header "Authorization: Bearer sk-memtro-..."

Cursor

Add the server to .cursor/mcp.json in the project, or to the global file under ~/.cursor/.

{
  "mcpServers": {
    "memtro": {
      "url": "https://platform.memtro.com/api/mcp",
      "headers": {
        "Authorization": "Bearer sk-memtro-..."
      }
    }
  }
}

Claude Desktop

Create a personal API key on Dashboard → Profile → API keys. In Claude Desktop add an MCP server of type HTTP with URL https://platform.memtro.com/api/mcp and the header Authorization: Bearer sk-memtro-…

OpenCode

A remote server in opencode.json.

{
  "mcp": {
    "memtro": {
      "type": "remote",
      "url": "https://platform.memtro.com/api/mcp",
      "headers": {
        "Authorization": "Bearer sk-memtro-..."
      }
    }
  }
}

Any other client

Add an MCP server of type HTTP (Streamable HTTP, stateless) at https://platform.memtro.com/api/mcp with the header Authorization: Bearer sk-memtro-.... Codex, Zed, Windsurf, Cline and the SDKs all take a remote server this way.

Who may use it

The key identifies the person, and the server offers that person the tools they may use everywhere else in Memtro. A shared Jira connection is used by the teams an administrator granted it to, tool by tool, on the Permissions page; a personal connection is used by its owner alone, and its tools that act stay off until the owner allows them. See Teams and permissions and Connectors.

Ask it like this

› What blocked PAY-114?
› List bugs opened this week in the payments project

Questions

Is this an official Jira MCP server?: No. It is Memtro's MCP server with Memtro's Jira connector behind it: the connector reads Jira through its API with the credentials you connect on Dashboard → Connections, and Jira publishes nothing here. The same endpoint carries every other system you connect and Memtro's memory tools.
What does it cost?: Nothing on top of Memtro. One price per organisation by its number of users, from $50 a month for up to 10 users after a 7-day free trial, with every connector, the MCP server, jobs and memory included. You bring your own model keys.
Can it change anything in Jira?: Only when you ask, and only what it has been granted: create an issue in a project; comment on an issue; move an issue through its workflow (and change its assignee or labels); change an issue's summary, description, priority, labels, assignee, due date, parent or story points; link two issues (blocks, duplicates, relates to…); log work against an issue. Every other tool reads, searches or lists. An administrator grants each acting tool by name per team, and a personal connection acts only after its owner allows it.
Which clients work?: Any MCP client that speaks Streamable HTTP: Claude Code, Cursor, Claude Desktop, OpenCode, Codex, Zed, Windsurf, Cline and the Anthropic and OpenAI SDKs. There is no local process to run; the server is remote and authenticated with your key.