jira-mcp
Self-hosted MCP server for Jira Cloud that mirrors the Atlassian Rovo MCP Server, enabling Jira issue management, JQL search, and workflow transitions via natural language.
README
jira-mcp
A self-hosted MCP server for Jira Cloud, built with FastMCP in Python.
Tool names and signatures mirror the official Atlassian Rovo MCP Server, so prompts and skills written for the official server work here too. One intentional difference: there is no cloudId parameter — this server is bound to a single Jira site via configuration.
Tools
| Tool | Description |
|---|---|
atlassianUserInfo |
Info about the authenticated user |
getAccessibleAtlassianResources |
The connected Jira site |
lookupJiraAccountId |
Resolve a user's accountId by name/email |
getVisibleJiraProjects |
List/search visible projects |
getJiraProjectIssueTypesMetadata |
Issue types available in a project |
getJiraIssueTypeMetaWithFields |
Fields (incl. required/custom) for an issue type |
getJiraIssue |
Get one issue with description and comments |
searchJiraIssuesUsingJql |
JQL search with pagination |
getJiraIssueRemoteIssueLinks |
Remote (web) links on an issue |
createJiraIssue |
Create an issue (supports additional_fields) |
editJiraIssue |
Update issue fields |
addCommentToJiraIssue |
Comment on an issue |
getTransitionsForJiraIssue |
Available workflow transitions |
transitionJiraIssue |
Move an issue through a transition |
Descriptions and comments are accepted as plain text and converted to Atlassian Document Format automatically; ADF in responses is flattened back to plain text.
Setup
-
Create an API token at https://id.atlassian.com/manage-profile/security/api-tokens
-
Copy the env template and fill it in:
cp .env.example .env
Run with Docker (recommended)
docker build -t jira-mcp .
As a stdio server (Docker Desktop / MCP clients that spawn a container)
Add to your MCP client config (e.g. Claude Desktop / Claude Code):
{
"mcpServers": {
"jira": {
"command": "docker",
"args": ["run", "-i", "--rm", "--env-file", "/absolute/path/to/jira-mcp/.env", "jira-mcp"]
}
}
}
As a long-running HTTP server
docker run --rm --env-file .env -e MCP_TRANSPORT=http -p 8000:8000 jira-mcp
Then point your MCP client at http://localhost:8000/mcp.
Run locally (without Docker)
pip install -e .
jira-mcp
Configuration
| Variable | Required | Description |
|---|---|---|
JIRA_URL |
✅ | Your site, e.g. https://your-company.atlassian.net |
JIRA_EMAIL |
✅ | Email of the account the token belongs to |
JIRA_API_TOKEN |
✅ | Atlassian API token |
JIRA_TIMEOUT |
— | HTTP timeout in seconds (default 30) |
MCP_TRANSPORT |
— | stdio (default) or http |
MCP_HOST / MCP_PORT |
— | HTTP bind address (default 0.0.0.0:8000) |
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.