io.github.keshrathPublished by GitHub account keshrathv2.1.0Updated Oct 25, 2026
Pipeline task management for AI agents - stages, dependencies, artifacts, claiming
Local MCP server that gives AI coding agents a shared, stage-gated task pipeline with dependencies, artifacts and claiming.
Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.
Follow the launch instructions in the repository.
[License: MIT] [Node.js] [Tests] [MCP Tools] [REST Endpoints]
Pipeline-driven task management for AI coding agents. An MCP server with stage-gated pipelines, multi-agent collaboration, and a native Claude Code /pipeline pane. Tasks flow through configurable stages — backlog, spec, plan, implement, test, review, done — with dependency tracking, stage gates, artifact versioning, and threaded comments.
Built for AI coding agents (Claude Code, Codex CLI, Gemini CLI, Aider) but works equally well with any MCP client or REST consumer.
[/pipeline opens the board beside a Claude Code conversation; Tab and Enter open a task]
The user manual shows every view and action of the pane, with screenshots and short clips from the real CLI.
2.0 replaced the web dashboard with the /pipeline pane inside Claude Code; there is no browser UI, WebSocket or agent-desk plugin any more.
/pipeline in Claude Code (install the plugin, below). The agent-desk Tasks tab is gone with it.GET /api/overview and PUT /api/tasks/:id/stage are gone (use GET /api/board and POST /api/tasks/:id/stage with {"action": "advance"}), and so are the routes nothing called; see the REST API.An older agent-tasks (1.10.13) holds the port) and in the status line (old server 1.10.13 on the port): end the Claude Code sessions still running it (or kill the old agent-tasks process) so a 2.x process takes the port, then Refresh.When you run multiple AI agents on the same codebase, they need a shared task pipeline — not just a flat todo list. They need stages, dependencies, stage gates, and visibility.
backlog > spec > plan > implement > test > review > done/pipeline pane — the board beside the conversation, keyboard-first: tasks by stage, task detail with artifacts and comments, advance, send back, complete, fail, cancel, comment and delete, a status line entryrequire_approval, but no MCP tool or REST route records an approval, so a stage with it set cannot be left; keep it off)task_artifact(type: "decision")task_artifact(type: "learning") captures insights (technique, pitfall, decision, pattern); auto-propagated to parent and sibling tasks on completiontask_list(next: true) prefers routing tasks to agents with related history (parent, dependency, project) as a tie-breakerAdd to your MCP client config (Claude Code, Cline, etc.):
The first MCP process to start also serves the REST API on http://localhost:3422; the others retry every 5 s and take over when it exits.
/pipeline pane)The plugin runs the MCP server and adds a Claude Code mod (function hooks, Claude Code 2.1.289+): /pipeline opens the board beside the conversation. The tutorial walks through it. Remove any hand-written agent-tasks entry from ~/.claude.json so tools do not appear twice.
Once configured (see Quick Start above), Claude Code can use all 8 MCP tools directly — creating tasks, advancing stages, adding artifacts, commenting, and more. With the plugin installed, /pipeline opens the board in a pane beside the conversation (Claude Code 2.1.289+). See the Setup Guide for detailed integration steps.
See full API reference for detailed descriptions of every tool and endpoint.
All endpoints return JSON. Loopback only: a foreign Host gets 403, so does any request carrying an Origin header (no browser calls this API), and request bodies must be application/json. Everything else goes through the MCP tools. See full API reference for details.
Required: Node.js >= 20.11, better-sqlite3 (bundled)
Optional (soft dependencies — fail-open, HTTP-only, no npm dep):
agent-comm — Heartbeat-based task cleanup and event notifications. agent-comm tracks heartbeats → agent-tasks checks heartbeats → auto-fails tasks from dead agents. Also sends direct messages on claim/advance and posts to a channel on comments. Without agent-comm, stale agent detection and notifications are skipped gracefully.
agent-knowledge — Knowledge persistence for task learnings and decisions. On task completion, the KnowledgeBridge pushes learning and decision artifacts to agent-knowledge via POST /api/knowledge. Entries are auto-indexed with embeddings, auto-linked to similar entries, and git-synced. Without agent-knowledge, artifacts stay in agent-tasks only.
/pipeline pane step by step, recorded from the real CLI/pipeline pane view by view (screenshots and GIFs), every tool, the pipeline, gates, cleanupscripts/setup.js installsMIT — see LICENSE
Source: README.md at commit 13a69dd
Create a pipeline task. Tasks start in "backlog" and move through stages: backlog → spec → plan → implement → test → review → done. Use parent_id to create subtasks under an existing task.
tagsstagetitlerequiredprojectpriorityassign_toparent_iddescriptionGet a single task by ID. By default returns task with artifacts, comment count, dependencies (blockers/blocking = `blocks` edges; links = `related`/`duplicate`, with direction), claim status and collaborators. Use "include" to inline full subtasks, artifacts (filterable by stage), comments (with limit), or transitive_deps (full upstream + downstream closure of the dependency graph in one call — answers questions like "what depends on this task transitively?" and "what is its critical path depth?" without forcing the caller to BFS the graph).
limitstageincludetask_idrequiredList, search, or pick tasks. Without params: returns all tasks. With filters: narrow by status/stage/project/assignee. With "query": full-text search across titles and descriptions. With "next": true: returns the single highest-priority unassigned task with all dependencies met (uses affinity scoring when agent is provided).
nexttagsagentlimitquerystageoffsetstatusprojectassign_toparent_idroot_only+1 moreUpdate task metadata — title, description, priority, tags, project, assignment, or dependencies. Does not change stage or status (use task_stage for that).
tagstitleprojecttask_idrequiredpriorityassign_todependencydescriptionDelete a task and all its artifacts, comments, and dependencies (cascading delete). Cannot be undone.
task_idrequiredMove a task through its lifecycle. Actions: "claim" → assign to you and advance from backlog to spec, "assign" → assign to you WITHOUT advancing the stage (use for custom pipelines where the first stage is itself a do-work stage), "advance" → next stage (or jump to a specific one), "regress" → earlier stage (requires reason), "complete" → marks done with result, "fail" → marks failed with error, "cancel" → cancels with reason.
stageactionrequiredreasonresultclaimercommenttask_idrequiredAttach artifacts or comments to a task. Types: "general" → document (spec, test-results, review-notes), "decision" → structured decision record (chose/over/because), "learning" → insight that auto-propagates to parent and sibling tasks on completion, "comment" → discussion comment (supports threading via parent_comment_id, satisfies stage-gate require_comment checks).
nameovertyperequiredchosestagebecausecontenttask_idrequiredcategoryparent_comment_idConfiguration and admin. Actions: "session" → set agent identity (call this first), "pipeline" → get/set pipeline stages and gate config for a project, "cleanup" → purge old completed tasks, "rules" → generate IDE rule files (.mdc or CLAUDE.md).
idmodenameactionrequiredformatstagesprojectgate_configtimeout_minutes90% of the applicable checks met
How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.
Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.
npm install -g agent-tasksgit clone https://github.com/keshrath/agent-tasks.gitcd agent-tasksnpm installnpm run build{ "mcpServers": { "agent-tasks": { "command": "npx", "args": ["agent-tasks"] } }}claude plugin marketplace add keshrath/agent-tasksclaude plugin install agent-tasks@agent-tasksnode dist/server.js --port 3422GET /health Health check with version + uptimeGET /api/tasks/:id One task, as task_get (?include=subtasks,comments,transitive_deps)GET /api/pipeline Pipeline stage configurationGET /api/board Open and recently closed tasks (what the pane polls)
POST /api/tasks Create a taskPOST /api/tasks/:id/stage Lifecycle action (claim, assign, advance, regress, complete, fail, cancel)POST /api/tasks/:id/comments Add a commentDELETE /api/tasks/:id Delete a tasknpm test # vitest: 472 tests across 25 filesnpm run test:watch # Watch modenpm run test:coverage # Coverage reportnpm run check # Full CI: typecheck + lint + format + testnpm run plugin:check # the /pipeline pane: claude plugin validate + its tests (needs the claude CLI)npm run e2e:claude # the pane in the real Claude Code CLI (see CONTRIBUTING.md)