Atlassian Rovo MCP

Live

OAUTH 2.0

PRODUCTIVITY

Every page, decision, and team knowledge artifact across Atlassian lives in Rovo. Atlassian Rovo MCP gives your agent authenticated access to organizational knowledge scoped to the user who authorized it.

  • Acts as the user: Access and write actions stay tied to the Atlassian Rovo MCP account that authorized the agent.
  • Credentials stay vaulted: AES-256, resolved at request time, never in LLM context.
  • Scoped before every call: User permissions enforced. 90-day audit trail.
Atlassian Rovo MCP
agent · Acme Q3
Run
What decisions were made about the API rate limiting architecture in the last 30 days?
S
rovo_search
86ms
Knowledge agent
3 relevant decisions found. Oct 28: agreed on 1,000 req/min per tenant (Confluence RFC-412). Oct 22: burst allowance of 2x for 10s approved (Jira ARCH-88). Oct 15: Redis-based counter selected over Postgres (RFC-408 comments).
Sources: Confluence, Jira, last 30 days
atlassianrovomcpmcp
3 sources
18:29
Message Claude...

Tools your knowledge agent reaches for on Atlassian Rovo MCP, scoped per user.

CALL ANY TOOL
Search across Atlassian sources, get and create Confluence pages, and ask Rovo natural-language knowledge questions.
rovo_search
Search knowledge
Search across all connected Atlassian sources: Confluence, Jira, and third-party integrations.
Parameters
Name
Type
Required
Description
query
string
Required
Search query
limit
integer
Optional
Max results
sources
array
Optional
Source filters: confluence, jira, drive, slack
rovo_page_get
Get page
rovo_page_create
Create page
rovo_chat
Chat with Rovo
rovo_spaces_list
List spaces
Build your Agent
Drop the toolkit in, point it at the user, and your knowledge agent can use Atlassian Rovo MCP from the first run.
import { ScalekitClient } from "@scalekit-sdk/node";
import { DynamicStructuredTool } from "@langchain/core/tools";
import { createReactAgent } from "@langchain/langgraph/prebuilt";
import { z } from "zod";

const sk = new ScalekitClient(envUrl, clientId, clientSecret);

const { tools } = await sk.tools.listScopedTools("user_123", {
filter: { connectionNames: ["atlassianrovomcp"], toolNames: ["rovo_search", "rovo_page_get", "rovo_page_create"] },
pageSize: 100,
});

const lcTools = tools.map((t) => new DynamicStructuredTool({
name: t.tool.definition.name,
description: t.tool.definition.description,
schema: z.object({}).passthrough(),
func: async (args) => {
const { data } = await sk.tools.executeTool({
toolName: t.tool.definition.name,
identifier: "user_123",
params: args,
});
return JSON.stringify(data);
},
}));

const agent = createReactAgent({ llm, tools: lcTools });
import { ScalekitClient } from "@scalekit-sdk/node";
import OpenAI from "openai";

const sk = new ScalekitClient(envUrl, clientId, clientSecret);
const openai = new OpenAI();

const { tools } = await sk.tools.listScopedTools("user_123", {
filter: { connectionNames: ["atlassianrovomcp"], toolNames: ["rovo_search", "rovo_page_get", "rovo_page_create"] },
pageSize: 100,
});

const llmTools = tools.map((t) => ({
type: "function",
function: {
name: t.tool.definition.name,
description: t.tool.definition.description,
parameters: t.tool.definition.input_schema,
},
}));

const resp = await openai.responses.create({
model: "gpt-4o", input: prompt, tools: llmTools,
});
import { ScalekitClient } from "@scalekit-sdk/node";
import Anthropic from "@anthropic-ai/sdk";

const sk = new ScalekitClient(envUrl, clientId, clientSecret);
const anthropic = new Anthropic();

const { tools } = await sk.tools.listScopedTools("user_123", {
filter: { connectionNames: ["atlassianrovomcp"], toolNames: ["rovo_search", "rovo_page_get", "rovo_page_create"] },
pageSize: 100,
});

const llmTools = tools.map((t) => ({
name: t.tool.definition.name,
description: t.tool.definition.description,
input_schema: t.tool.definition.input_schema,
}));

const msg = await anthropic.messages.create({
model: "claude-sonnet-4-6", max_tokens: 1024,
tools: llmTools,
messages: [{ role: "user", content: prompt }],
});
import { Agent } from "@google/adk/agents";
import {
MCPToolset, StreamableHTTPConnectionParams,
} from "@google/adk/tools/mcp";

const toolset = new MCPToolset({
connectionParams: new StreamableHTTPConnectionParams({
url: "https://mcp.scalekit.com/atlassianrovomcp",
headers: { Authorization: `Bearer ${userScopedToken}` },
}),
});

const agent = new Agent({
name: "agent", model: "gemini-2.0-flash",
tools: await toolset.getTools(),
});
Try these prompts
Paste any prompt into your agent to start using Atlassian Rovo MCP.
Search & knowledge
Copy the prompt
Copied
Search for decisions about [topic] in the last 30 days.
Copy the prompt
Copied
Find all RFCs mentioning [component].
Copy the prompt
Copied
What Jira tickets are related to [feature]?
Copy the prompt
Copied
Find runbooks tagged [label].
Pages & creation
Copy the prompt
Copied
Get the latest version of [page name].
Copy the prompt
Copied
Create a page in [space]: [title].
Copy the prompt
Copied
List all pages in [space] updated this week.
Copy the prompt
Copied
Find pages with [keyword] in the body.
Rovo chat
Copy the prompt
Copied
What did we decide about [topic] last quarter?
Copy the prompt
Copied
Summarize all architecture decisions in [project].
Copy the prompt
Copied
Who owns the [component] according to our docs?
Copy the prompt
Copied
What is our policy on [topic]?
SEE HOW AUTH WORKS
Users authorize Atlassian Rovo MCP once. Their credentials stay vaulted, every call is checked, and every action is logged.
1
Authorize
Your user connects
Atlassian Rovo MCP
once. We tie it to their identity and the meetings they approved — no shared bot account, no org-wide access
Who:
user ‘A’
when:
Once per user
access:
Limited to user
2
Store
Their
Atlassian Rovo MCP
token lives in a vault scoped to them. User A's meetings are never reachable by an agent acting for user B, even on the same connection
vault:
encrypted
scope:
per-user
tokens:
auto-refreshed
3
Resolve
When your agent calls a
Atlassian Rovo MCP
tool, we fetch the right token server-side. It never touches your agent, never appears in the LLM context, never shows up in your logs
speed:
~40ms
check:
before every call
seen by:
nobody
4
Audit
Every
Atlassian Rovo MCP
tool call is logged — who triggered it, which meeting was fetched, what came back. 90 days of history, tied to the user who authorized it
history:
90 days
export:
SIEM-ready
logged:
every call
Test other agents
Same per-user auth pattern across other knowledge agents and MCP connectors. Working code, live demos, fork what fits.
ENGINEERING
Engineering standup agent
Aggregate GitHub and GitLab activity, link to Jira, and post a daily standup digest to Slack. No async updates.
SUPPORT
Support triage agent
Read Zendesk tickets, fetch runbooks from Notion, and route to the right Slack channel with a drafted response.
Why Scalekit
Secure your agent's access. Connectors ship in minutes
Other connector libraries treat auth as a demo afterthought. Scalekit starts with user identity, scope enforcement, and audit.
01.
Shared tokens break per-user analytics
A shared token looks fine in a demo. In production every call looks like a service account. Scalekit resolves the real user credential so attribution, audit, and scope stay accurate.
// shared token
 audit → bot_service_account
 user_filter → broken

 // scalekit
 audit → user_abc
 scope → enforced ✓
02.
Authentication is not authorization
03.
Multi-tenancy is architectural
04.
Atlassian Rovo MCP today. Others tomorrow.
“Our agents act across Salesforce, Gong, Google Drive, and more, on behalf of every customer. Scalekit behind the scenes meant we can keep adding tools without ever rebuilding how credentials or tool calling work.”
Venu Madhav Kattagoni
Head of Engineering / Von
FAQs
Frequently Asked Questions
Does the agent access Atlassian Rovo MCP as the user or as a shared key?
As the user. Each workspace member authorizes once and Scalekit resolves their credential at request time. Audit logs attribute every action to that user, not a shared service account.
Where is the Atlassian Rovo MCP oauth 2.0 stored?
In Scalekit's managed AES-256 token vault, namespaced per tenant. Refresh is automatic. Revocation is a single dashboard action. Tokens never appear in prompts, logs, or LLM context.
Can I limit what the agent is allowed to do in Atlassian Rovo MCP?
Yes. Pass a tool name filter to listScopedTools so the knowledge agent only sees the subset you authorize. Pre-API-call scope checks block out-of-policy actions before the request reaches Atlassian Rovo MCP.
What happens when a user revokes Atlassian Rovo MCP access?
The connection is invalidated on the next tool call. Subsequent requests for that user fail closed with a clear error. Other users in the tenant remain unaffected. The event is logged for audit.
Can the agent search Confluence spaces the user doesn't have access to?
No. Rovo searches run under the authorizing user's Atlassian OAuth scope. Space permissions, page restrictions, and Jira project visibility all apply. Out-of-scope content is never returned.
Start in your coding agent
Up and running in one command
Install the Scalekit skill in your editor of choice. Connector, auth, tools, prompt, all wired up
Claude Code REPL
/plugin marketplace add scalekit-inc/claude-code-authstack
/plugin install agentkit@scalekit-auth-stack
Cursor Code REPL
# ~/.cursor/mcp.json
{
""mcpServers"": {
""atlassianrovomcp"": {
""url"": ""https://mcp.scalekit.com/atlassianrovomcp"",
""headers"": { ""Authorization"": ""Bearer $SCALEKIT_TOKEN"" }
}
}
}
Codex Code REPL
# ~/.codex/config.toml
[mcp_servers.atlassianrovomcp]
url = ""https://mcp.scalekit.com/atlassianrovomcp""
auth_env = ""SCALEKIT_TOKEN""
Copilot Code REPL
# .vscode/mcp.json
{
""servers"": {
""atlassianrovomcp"": {
""url"": ""https://mcp.scalekit.com/atlassianrovomcp"",
""type"": ""http""
}
}
}