atlassian-browser-mcp

Overview Schema Source Related Servers Discussions Admin

How to sign in to Jira or Confluence

atlassian_login

Read-onlyIdempotent

Returns the terminal command to sign in to Jira or Confluence when authentication fails. Show it to the user, who runs it where a browser can open, then retry.

Instructions

Return the terminal command that signs the user in to Jira or Confluence.

(Async on purpose: upstream wraps every tool in an error handler that awaits it, so a plain function fails with "object can't be awaited".)

Sign-in is never done from inside the server (a browser login there used to hang it). Call this after a "Not authenticated" error and show the user the command; they run it in a terminal where a browser can open, then you retry. The server reuses the saved session automatically.

Input Schema

Name	Required	Description	Default
`target`	No	The service to sign in to: "jira" or "confluence".	jira

Output Schema

Name	Required	Description
`status`	Yes	Always action_required: sign-in happens in a terminal, not here.
`command`	Yes	The command to run in a terminal with a display.
`message`	Yes	What to tell the user.
`service`	Yes	The service to sign in to.

Schema Changelog

Changes observed during successful MCP inspections.

Changed7 schema fields changedv1.4.1Nov 2, 2026

addedInput schema / additionalProperties
```
Added value: +false
```

addedInput schema / properties / target / description

Added value: +"The service to sign in to: \"jira\" or \"confluence\"."

removedInput schema / properties / url

Removed value: -{
-  "default": null,
-  "type": "string"
-}

removedOutput schema / additionalProperties
```
Removed value: -true
```

addedOutput schema / description

Added value: +"How to sign in to one service."

addedOutput schema / properties

Added value: +{
+  "command": {
+    "description": "The command to run in a terminal with a display.",
+    "type": "string"
+  },
+  "message": {
+    "description": "What to tell the user.",
+    "type": "string"
+  },
+  "service": {
+    "description": "The service to sign in to.",
+    "enum": [
+      "jira",
+      "confluence"
+    ],
+    "type": "string"
+  },
+  "status": {
+    "const": "action_required",
+    "description": "Always action_required: sign-in happens in a terminal, not here.",
+    "type": "string"
+  }
+}

addedOutput schema / required

Added value: +[
+  "status",
+  "service",
+  "command",
+  "message"
+]

Addedv1.0.1Apr 14, 2026

TDQS

A3.9/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Goes well beyond the readOnly/idempotent annotations by disclosing that sign-in never happens server-side, that a browser login inside the server used to hang it, and that the saved session is reused on retry. The async-implementation parenthetical is internal plumbing an agent doesn't act on, which dilutes slightly.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with what the tool returns, then the workflow, then the rationale. The async parenthetical is a digression that costs more than it earns for an agent, though it does preempt confusion about why a login tool is async.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Output schema exists so return values need no explanation, and annotations cover the safety profile; the description supplies the missing piece — the human-in-the-loop workflow and the retry. Only gap is clarifying whether this precedes or replaces an atlassian_auth_status check.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The single `target` parameter is fully documented in the schema with an enum and default, so the schema carries the load. The description mentions "Jira or Confluence" but adds no formatting or selection guidance beyond that.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The first sentence states a specific, unusual verb+object: it returns a terminal command that signs the user in to Jira or Confluence. It never names its closest sibling (atlassian_auth_status), so the agent must infer the split itself, but the action and resource are unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives a concrete trigger (after a "Not authenticated" error), the follow-up action (show the user the command), and the next step (retry once they've run it). No explicit exclusion against atlassian_auth_status or guidance on calling this preemptively, which keeps it short of a 5.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server