Markdown Pipeline runs on your own machine — the client starts it, so there is no endpoint to ping. 736 installs a week from pypi. Last commit 1 Nov 2026.
Your team's Jira as clean Markdown files, kept current for your AI agent. Local and read-only.
Today is the operative word: we check Markdown Pipeline every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add mdpipeline -- uvx mdpipeline
{
"mcpServers": {
"mdpipeline": {
"command": "uvx",
"args": [
"mdpipeline"
]
}
}
}
[mcp_servers.mdpipeline]
command = "uvx"
args = ["mdpipeline"]
{
"mcpServers": {
"mdpipeline": {
"command": "uvx",
"args": [
"mdpipeline"
]
}
}
}
{
"servers": {
"mdpipeline": {
"type": "stdio",
"command": "uvx",
"args": [
"mdpipeline"
]
}
}
}
Your team's design feedback from Figma, Jira and Notion: ask, search, read, reply, mark done.
Assign Linear, Jira or GitHub issues to an AI coding agent team that plans, builds, reviews, tests.
Ask a local SQLite mirror of your Jira and Confluence: SQL, full-text search, issue detail.
Read and manage your own Taiga projects: items, statuses, assignees, sprints, comments
Kanban boards your AI agent can use: add, complete, move and recall tasks with your team.
eGile kanban board for AI agents: a card per task, take teammates' tasks, move cards as you work.
Kanban boards, sprints, tickets and a team wiki, with versioned writes for concurrent agents.
Shared memory + orchestration for your coding agents. Local-first MCP, vector RAG.
Answers built from our own checks of this server.