Skip to main content
Glama

claude-task-graph

An MCP server + live graph viewer for Claude Code. Tasks, subtasks, ideas and discussion branches are stored as a graph and rendered live in your browser as a schematic-style diagram with connector lines — so you can skim the structure instead of reading walls of text, and tangents get parked as nodes instead of getting lost.

How it works

  • MCP server (stdio) exposes tools to Claude Code: create_node, update_node, link_nodes, get_graph, delete_node.

  • Viewer at http://localhost:7300 updates live over WebSocket while Claude works. Node border color = status, node shape = type (task / subtask / idea / discussion / note). Click a node for its full description and note log.

  • Storage is a plain JSON file (task-graph.json by default) — one graph per project directory, diffable, committable.

Related MCP server: visualize-chat-mcp

Install

git clone https://github.com/<you>/claude-task-graph.git
cd claude-task-graph
npm install

Hook into Claude Code

From the project directory where you want the graph:

claude mcp add task-graph -- node /path/to/claude-task-graph/src/server.js

Then copy the rules from CLAUDE.md.example into that project's CLAUDE.md. Those rules are what make Claude actually maintain the graph: register tasks before starting, park tangents as linked idea nodes, update status as it goes.

Open http://localhost:7300 and keep it on a second screen.

Configuration

Env var

Default

Purpose

TASK_GRAPH_FILE

./task-graph.json

Where the graph is stored

TASK_GRAPH_PORT

7300

Viewer HTTP/WebSocket port

Set them in the claude mcp add command with -e if needed, e.g. a fixed graph file shared across sessions:

claude mcp add task-graph -e TASK_GRAPH_FILE=$HOME/graphs/myproject.json -- node /path/to/claude-task-graph/src/server.js

Node types and relations

  • Types: task, subtask, idea, discussion, note, finding, decision, bug

  • Statuses: pending, in-progress, done, blocked, parked

  • Relations: subtask-of, depends-on (rendered dashed copper), spawned-from, discussion-of, related-to, found-in, decision-of

License

MIT

Available Tools

6 tools
create_nodeA

Create a node in the task graph. Use for every task, subtask, idea, discussion topic, note, finding (something learned), decision (with reasoning) or bug that comes up. If it grew out of another node, pass parent_id so the graph shows where it branched from.

Inputs: type (required), title (required), doc, status, +2 more.

delete_nodeA

Delete a node and all edges touching it. Only when the user explicitly asks.

Inputs: id (required).

get_graphA

Return the full current graph (all nodes and edges). Use to re-orient yourself at the start of a session.

Inputs: no named parameters.

import_graphA

Bulk-create many nodes and edges in one call. Use when reconstructing a graph from existing project history (e.g. context injected by a memory plugin such as claude-mem). Provide your own temporary ids in nodes[].ref and reference them in edges; real ids are assigned and returned as a ref->id map.

Inputs: nodes (required), edges.

update_nodeA

Update a node's title, description or status, and/or append a timestamped note. Notes are for the node's own status trail (why blocked, what the fix was); standalone information worth keeping should be its own note node via create_node so it is visible in the graph.

Inputs: id (required), doc, note, title, +2 more.

Tool Schema Changelog

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

Loading tool schema changelog…

    TDQS

    A4.2/5.0

    Scored across 6 tools

    Disambiguation5/5

    Each tool targets a distinct action: create, get, update, link, import, delete. Even create_node and import_graph are clearly separated by purpose (single vs bulk creation), with descriptions that prevent confusion.

    Naming Consistency5/5

    All tool names follow a consistent verb_noun snake_case pattern (create_node, get_graph, update_node, link_nodes, import_graph, delete_node). The plural in link_nodes is a minor variation but still fits the overall structure.

    Tool Count5/5

    Six tools is well-scoped for a task graph server. Each tool has a clear role, covering creation, retrieval, update, linking, bulk import, and deletion without unnecessary overlap or bloat.

    Completeness4/5

    The set covers core graph lifecycle operations (create, read, update, delete, link, import). Gaps include lack of explicit unlink and inability to change a node's parent_id via update_node, which may require workarounds like recreating nodes.

    Maintenance

    ActivityInactive
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      A
      quality
      D
      maintenance
      A read-only task graph visualizer for Beads projects, running as an MCP server in Claude Desktop or VS Code Copilot to display interactive DAGs, list views, and stats dashboards.
      3
      20 npm
      1
      MIT
    • F
      license
      B
      quality
      D
      maintenance
      Personal memory MCP server for Claude Code with an Obsidian-style graph. Enables persistent, queryable memories across sessions using Markdown files with bidirectional wiki-links and a D3.js force-directed graph UI.
      8
      -
    • A
      license
      B
      quality
      C
      maintenance
      An MCP server for AI-assisted project development and tracking. It exposes a typed graph of design nodes (concepts, decisions, requirements, etc.) and edges to Claude Code, enabling structured management of project knowledge and report generation.
      25
      3
      Apache 2.0