jira-mcp-bridge
A local-only MCP server providing safe, typed Jira tools for AI agents via Atlassian ACLI, enabling search, get issue, add comment, and transition issues with policy guardrails.
README
jira-mcp-bridge
jira-mcp-bridge is a local-only MCP server that gives AI coding agents a safe, typed Jira tool interface while using Atlassian ACLI internally.
Why this exists
- Public contract: MCP tools (
jira_search,jira_get_issue,jira_add_comment,jira_transition_issue) - Internal implementation: ACLI subprocess calls
- Security objective: AI agents do not receive Jira tokens; ACLI owns auth state
Architecture
AI Agent -> MCP Client -> jira-mcp-bridge (stdio MCP server) -> Atlassian ACLI -> Jira Cloud
See architecture.md for details.
Repository layout
/server
/adapters/acli
/policies
/tests
/docs
README.md
LICENSE
.gitignore
Features in v0.1
- Local stdio MCP server
- Typed and constrained Jira tools
- Input validation and policy guardrails
- ACLI adapter with timeout, output capture, error mapping
- Structured JSON logging
- Unit tests for validation, parsing, builders, and failure scenarios
Configuration
Configuration is loaded from environment variables and optional JSON config file:
ACLI_PATH(default:acli)JIRA_PROJECT_ALLOWLIST(csv; optional)MAX_RESULTS(default:50)COMMENT_MAX_LENGTH(default:4000)COMMAND_TIMEOUT(seconds; default:30)TRANSITION_ALLOWLIST(csv; optional)JIRA_MCP_CONFIG(path to JSON config; default:jira-mcp-bridge.jsonif present)LOG_LEVEL(default:INFO)
Example config file (jira-mcp-bridge.json):
{
"acli_path": "acli",
"jira_project_allowlist": "ABC,PLAT",
"max_results": 50,
"comment_max_length": 4000,
"command_timeout": 30,
"transition_allowlist": "In Progress,Done",
"log_level": "INFO"
}
Run locally
python -m venv .venv
. .venv/bin/activate # Windows PowerShell: .venv\\Scripts\\Activate.ps1
pip install -e ".[dev]"
python -m server
Configure MCP client (example)
{
"mcpServers": {
"jira-mcp-bridge": {
"command": "python",
"args": ["-m", "server"],
"env": {
"ACLI_PATH": "acli",
"JIRA_PROJECT_ALLOWLIST": "ABC,PLAT"
}
}
}
}
Tests
pytest
Important notes
- ACLI command syntax can vary by ACLI version/distribution. If needed, update command builders in
adapters/acli/commands.py. - No direct Jira REST API calls are used in this version.
- No raw shell passthrough is exposed to MCP clients.
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.