Skip to main content
Glama

Jira + Confluence MCP

A single MCP server that gives the Rapid7 SI Triage agent read/write access to Jira Cloud (tickets, attachments, comments, search) and Confluence Cloud (the historical knowledge base of runbooks and postmortems). Combining both Atlassian products in one server is natural: they share the same auth and host, and the triage workflow uses them together.

A key side effect lives here: when the agent fetches a ticket, this server auto-downloads log-like attachments into a shared directory that the companion Log Intelligence MCP then ingests.


Tools

Jira

Tool

Purpose

get_ticket(ticket_id, download_logs?)

Fetch + normalise a ticket (summary, description, comments, attachments, product/components, environment). Auto-downloads log attachments unless download_logs=false.

get_attachment(ticket_id, attachment_id)

Download a specific attachment by id into the ticket's log dir.

search_tickets(jql, max_results=25)

JQL search — used to find similar historical defects.

post_comment(ticket_id, body)

Post a comment (write; guarded).

update_ticket_field(ticket_id, field, value)

Update one field (write; guarded).

Confluence

Tool

Purpose

search_confluence(query, max_results=10, cql?)

CQL/text search of the KB. Returns ranked, normalised results (title, url, excerpt, relevance) — the same shape as Jira search so the agent handles both uniformly.

get_page(page_id)

Fetch a page as clean plain text (storage-format markup stripped) + metadata. Cached.

get_child_pages(page_id)

List direct child pages (walk a runbook space).


Related MCP server: inhouse_confluence_mcp

Auth & configuration

Atlassian Cloud uses HTTP Basic auth with email:api_token (base64). Secrets come from the environment only — never hardcoded. Copy .env.example to .env:

ATLASSIAN_BASE_URL=https://asgspratapsingh.atlassian.net
ATLASSIAN_EMAIL=asgspratapsingh@gmail.com
ATLASSIAN_API_TOKEN=<create at id.atlassian.com/manage-profile/security/api-tokens>
SI_DATA_DIR=./si_data

ATLASSIAN_BASE_URL may be any URL from your site — it's normalised to the site origin automatically (e.g. …atlassian.net/jira/for-you?tab=x → https://…atlassian.net).

Write safety. DRY_RUN=1 refuses all writes (read-only). ALLOW_WRITES=0 refuses writes even when not in dry-run. Both post_comment and update_ticket_field respect these guards.

Attachment download. AUTO_DOWNLOAD_LOGS=1 (default) downloads attachments whose name ends in LOG_ATTACHMENT_SUFFIXES (.log,.txt,.gz,.out,.err) or that are text/plain, up to MAX_ATTACHMENT_MB (50). Files land in SI_DATA_DIR/logs/<ticket_id>/.

The HTTP client retries 429/5xx with exponential backoff (honouring Retry-After), controlled by HTTP_MAX_RETRIES and HTTP_TIMEOUT.


Install & run

cd jira-confluence-mcp
python -m venv .venv && source .venv/bin/activate     # Windows: .venv\Scripts\activate
pip install -e .            # installs mcp, httpx, uvicorn
cp .env.example .env        # fill in ATLASSIAN_API_TOKEN

# stdio:
python -m jira_confluence_mcp --transport stdio

# HTTP (streamable-http at http://127.0.0.1:8080/mcp):
python -m jira_confluence_mcp --transport http

This server is one of four processes in the SI Triage POC (this + the Log Intelligence and Historical KB MCPs + the orchestrator). For the full multi-service manual startup sequence, .env layout across all four repos, and end-to-end test steps, see orchestrator-agent/si-triage-automation/README.md → "Running the full system manually".

Register with an MCP client (stdio example)

{
  "mcpServers": {
    "jira-confluence": {
      "command": "python",
      "args": ["-m", "jira_confluence_mcp", "--transport", "stdio"],
      "env": {
        "ATLASSIAN_BASE_URL": "https://asgspratapsingh.atlassian.net",
        "ATLASSIAN_EMAIL": "asgspratapsingh@gmail.com",
        "ATLASSIAN_API_TOKEN": "…",
        "SI_DATA_DIR": "/absolute/path/to/si_data"
      }
    }
  }
}

How it coordinates with the Log Intelligence MCP

Set SI_DATA_DIR to the same absolute path for both servers.

si_data/
  logs/<ticket_id>/…    # THIS server writes downloaded attachments here
                        # the Log Intelligence MCP reads + indexes them

Flow: get_ticket(EA-123) here → files appear in logs/EA-123/ → ingest_ticket_logs("EA-123") on the Log MCP → agent queries logs → delete_ticket_logs("EA-123") cleans up.


Ports

This server's HTTP transport defaults to 8080; the Log Intelligence MCP uses 8081, so both can run simultaneously.


Tests

pytest                      # in the POC environment
python tests/_runner.py     # offline harness when pytest isn't installed

Covers auth-header construction, base-URL normalisation, ADF→text flattening, ticket normalisation, log-attachment filtering, Confluence storage-format stripping, search-result normalisation, CQL escaping, and — via a stub HTTP transport (so no network is needed) — ticket fetch with auto-download, JQL search normalisation, write guards, Confluence search/get_page/caching, and child-page listing. 19 tests, all offline.

Live Jira/Confluence calls and running the MCP over a real transport need network access and the mcp/httpx packages installed, which the build sandbox blocks. The tests validate all request-building and response-handling logic against real payloads through the stubbed transport.

Available Tools

8 tools
get_attachmentA

Download a specific Jira attachment by id into the ticket's log directory.

Inputs: ticket_id (required), attachment_id (required).

get_child_pagesB

List the direct child pages of a Confluence page.

Inputs: page_id (required).

get_pageA

Fetch a Confluence page as clean plain text plus metadata (cached).

Inputs: page_id (required).

get_ticketA

Fetch a Jira ticket (summary, description, comments, attachments, metadata).

Automatically downloads log-like attachments into the shared data directory so the Log Intelligence MCP can ingest them. Set download_logs=false to skip.

Inputs: ticket_id (required), download_logs.

post_commentA

Post a comment on a Jira ticket. Guarded by DRY_RUN / ALLOW_WRITES env vars.

Inputs: body (required), ticket_id (required).

search_confluenceA

Search the Confluence knowledge base; returns ranked, normalised results.

Uses CQL full-text search. Results include title, url, excerpt, and relevance score in the same shape as Jira search results. When mechanism_signal (an exception/error class or quoted error string) is supplied, hits with no token overlap against it are dropped, since a broad site search can match an unrelated write-up on topical vocabulary alone.

Inputs: query (required), cql, max_results, mechanism_signal.

search_ticketsA

Search Jira issues with JQL (e.g. to find similar historical defects).

Inputs: jql (required), max_results.

update_ticket_fieldB

Update a single Jira field value. Guarded by DRY_RUN / ALLOW_WRITES env vars.

Inputs: field (required), value (required), ticket_id (required).

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A3.9/5.0

    Scored across 8 tools

    Disambiguation5/5

    Each tool has a clearly distinct purpose: Jira actions target tickets, comments, fields, and attachments, while Confluence actions target pages, child pages, and search. Overlap is minor and resolved by descriptions, such as get_ticket for whole-ticket data and get_attachment for one specific attachment.

    Naming Consistency5/5

    All tools follow a consistent snake_case verb_noun pattern: get_*, search_*, post_*, update_*. There are no one-word verbs, version suffixes, or mixed conventions, making the tool set predictable.

    Tool Count5/5

    Eight tools is well-scoped for a server spanning Jira and Confluence. Each tool serves a distinct purpose and none are redundant, keeping the surface compact while covering meaningful retrieval and update workflows.

    Completeness4/5

    The set supports the core investigation workflow: search and read Jira tickets, download attachments, add comments, update fields, and search/read Confluence pages. Missing issue creation, issue deletion, and Confluence write operations are notable as general CRUD gaps, but they appear to be intentionally outside the workflow described by this server.

    Maintenance

    ActivityInactive
    ResponsivenessNo recent community issues

    Related MCP Connectors

    • One MCP server for all your work accounts: Slack, Teams, Google Chat, Jira, ClickUp, digest, tasks.

      https://app.goptin.com/mcp
    • Unified MCP Server is a remote MCP connector for AI agents and vertical AI products that provides access to 22,000+ authorized SaaS tools across 400+ integrations and 24 categories directly inside LLMs (Claude, GPT, Gemini, Cohere). Tools operate only on explicitly authorized customer connections, enabling agents to safely read and write against live third-party systems.

      https://mcp-api.unified.to/mcp
    • ClearFeed turns customer conversations in Slack, Microsoft Teams and email into trackable support requests. The ClearFeed MCP server lets AI assistants work with that data directly, so support, success and ops teams can get answers and take action without switching tabs. What you can do - Find and summarize requests: "Summarize the open requests assigned to me" - Update requests: change status, priority and assignee - Reply to customers: post a message on any request - Look up customers: request history and account details - Link tickets: connect Jira and other tickets to a request - Pull support metrics: response times, SLA performance and team workload - Manage collections: list collections, add channels or clone a setup Getting started 1. Add https://mcp.clearfeed.app/mcp as a custom connector in Claude, Cursor or Codex. 2. Sign in with your ClearFeed account. No API keys needed. 3. Start asking. The assistant can only see and do what your ClearFeed role allows. Requirements: a ClearFeed account. To self-host instead, run npx -y @clearfeed-ai/mcp with a ClearFeed API token.

      https://mcp.clearfeed.app/mcp
    • MCP server for AI access to SmartBear tools, including BugSnag, Reflect, Swagger, PactFlow, QTM4J.

    Related MCP Servers

    • A
      license
      Not graded
      quality
      D
      maintenance
      A read-only MCP server that enables querying and searching Atlassian Confluence pages and Jira issues through their REST APIs. Supports retrieving content by ID or URL, searching using CQL/JQL, and listing spaces and projects.
      1
      MIT
    • A
      license
      Not graded
      quality
      B
      maintenance
      MCP server for interacting with Jira Cloud instances. Enables issue management, JQL queries, project and sprint management, and batch operations via natural language interfaces.
      141 npm
      4
      MIT
    • A
      license
      Not graded
      quality
      C
      maintenance
      This MCP server enables interaction with Atlassian products (Jira and Confluence), with additional tools for uploading attachments, embedding images, and commenting with images. It supports both Cloud and Server/Data Center deployments.
      MIT