release-doc-mcp
Finds version and image tag from latest successful GitHub Actions workflow run and creates a Confluence release page documenting that information.
README
release-doc-mcp
MCP server that:
- Given a repo name, finds the image tag + version from the latest successful GitHub Actions workflow run.
- Creates a Confluence page documenting that version, image tag, and a link to the workflow run.
How version/image tag extraction works
The GitHub client fetches the latest successful run of a workflow (optionally filtered by workflow file and branch), then scans each job's logs for lines matching two regexes (defaults below), returning the first job where both match:
- Version:
Version:\s*(\S+) - Image tag:
Image tag:\s*(\S+)
These defaults match workflows that print lines like Image tag: myapp:1.2.3
and Version: 1.2.3 to the job log (e.g. via echo or $GITHUB_STEP_SUMMARY
plus a plain echo). If your workflow logs a different format, override
RELEASE_VERSION_REGEX / RELEASE_IMAGE_TAG_REGEX in your environment.
Setup
python -m venv .venv
./.venv/Scripts/pip install -e ".[dev]" # Windows
# source .venv/bin/activate && pip install -e ".[dev]" # macOS/Linux
cp .env.example .env
Fill in .env:
GITHUB_TOKEN— a PAT withactions:readon the target repos.CONFLUENCE_BASE_URL— e.g.https://your-domain.atlassian.net/wiki.CONFLUENCE_EMAIL/CONFLUENCE_API_TOKEN— Confluence Cloud API token auth.CONFLUENCE_SPACE_KEY— default space for created pages.CONFLUENCE_PARENT_PAGE_ID— optional parent page to nest pages under.
Running the server
./.venv/Scripts/release-doc-mcp # Windows
# .venv/bin/release-doc-mcp # macOS/Linux
It speaks MCP over stdio. To use it from Claude Code / Claude Desktop, add it as an MCP server, e.g. in Claude Code:
claude mcp add release-doc -- /full/path/to/.venv/Scripts/release-doc-mcp.exe
(Configure GITHUB_TOKEN/CONFLUENCE_* in your shell/user environment, or as
env entries in the MCP server config, so they're available to the process.)
Tools
get_image_version(repo, workflow_file="", branch="")— returns version, image tag, and workflow run info for a repo.create_confluence_release_page(repo, version, image_tag, workflow_run_url, workflow_name="", job_name="", space_key="", parent_page_id="")— creates a Confluence page for an already-known version/tag.document_release(repo, workflow_file="", branch="", space_key="", parent_page_id="")— does both steps in one call.
Tests
./.venv/Scripts/python -m pytest
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.