TaskChampion MCP server
io.github.GabiUp2/taskchampion-mcp·v1.0.4·3 starsMCP server for Taskwarrior 3.x, TaskChampion, and Timewarrior task management.
3 stars
Reviews
Write oneNobody has reviewed TaskChampion MCP yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
TaskChampion MCP tools (35, 6 write)
write = sends, deletes, buys or postsRead from the package source without running it. The installed server may list more.
analyze_existing_tasks_for_schemaAnalyse existing Taskwarrior tasks for field/schema inference.
analyze_taxonomy_fileParse a taxonomy Markdown file and return extracted semantics.
annotate_taskAppend a timestamped annotation to a task.
batch_create_taskswrite actionCreate multiple tasks in a single call with per-task result reporting.
bulk_modifyModify all tasks matching a filter expression in a single call.
complete_taskMark a task as done (completed).
create_subtaskwrite actionCreate a subtask with depends: linking to a parent task.
create_taskwrite actionCreate a new Taskwarrior task with schema validation.
delete_taskwrite actionDelete a task from Taskwarrior.
generate_initial_schema_previewGenerate a reviewable schema TOML preview without writing any files.
get_active_contextShow the currently active Taskwarrior context filter. Read-only.
get_initialization_statusInspect first-run onboarding state without mutating tasks or config.
get_projectsList all project names in the Taskwarrior database. Read-only.
get_runtime_capabilitiesReturn the server's current mode, role, schema, and callable tool groups.
get_schema_infoGet the active task schema definition.
get_tagsList all tags used across the Taskwarrior database. Read-only.
get_taskGet a single task by UUID and return all its fields. Read-only.
get_task_reportwrite actionRun a named Taskwarrior report and return its output. Read-only.
get_time_statusCheck whether Timewarrior is currently tracking time. Read-only.
get_time_summaryGet a Timewarrior time-tracking summary for a period. Read-only.
list_preset_schemasList bundled preset schemas (minimal, gtd, kanban, scrum, ...).
list_tasksList and filter Taskwarrior tasks. Read-only.
modify_taskModify fields on an existing task.
propose_initialization_optionsReturn structured onboarding choices for the user/model to discuss.
reload_configurationRe-read config.toml from disk and refresh all runtime state.
save_initial_schemaPersist an approved generated schema and optionally update config.toml.
search_tasksSearch tasks by matching a query against a specific field. Read-only.
set_active_schemaSwitch the active task schema.
set_roleChange the persisted MCP role — DOWNGRADE ONLY.
set_taxonomy_pathwrite actionUpdate the taxonomy file path persisted in config.toml.
start_taskMark a task as active by setting its start timestamp.
stop_taskDeactivate a task by clearing its start timestamp.
sync_tasksTrigger a sync with the configured TaskChampion sync server.
undo_last_actionUndo the most recent Taskwarrior operation.
use_preset_schemaWire a bundled preset schema into the user's config.toml.
Public scan report
scanner v0.1.9 · 2026-09-27 · same rubric, same numbers if you re-run it
- Code scan18 source files scanned20/25
- –Live reliabilityno gateway calls yet and no remote to proben/a
- –Tool poisoningtools not inspected (local package is not executed); not countedn/a
- Auth qualitylocal package, no credentials required12/15
- Maintenancelast push 88 days ago12/15
- Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
Findings (1)
- mediumsubprocess with shell=True
exec.shell-truetaskchampion_mcp-1.0.4/src/taskchampion_mcp/cli.py: … a subprocess with argument list (never shell=True). This is the ONLY place subproces…
How TaskChampion MCP compares
Against every graded Productivity MCP server, from our own scans and uptime checks. Updated after each scan run.
- Safety score
- 80/100
- higher than 53% of 1,299 Productivity servers
- Tools
- 35
- the typical Productivity server has 7
- Tools that change things
- 17%
- typical: 0%. Fewer write tools means less an agent can break
- GitHub stars
- 3
- more than 65% of 854 Productivity servers
What its tools let an agent do: 21 read · 4 create · 7 change · 1 delete · 2 run or deploy
Install TaskChampion MCP in Claude Code, Cursor or VS Code
claude mcp add taskchampion-mcp -- uvx taskchampion-mcp
What the publisher says
From the TaskChampion MCP repository's README, as published. We do not edit it. Read it on GitHub
TaskChampion MCP
A Model Context Protocol server for Taskwarrior 3.x, TaskChampion, and Timewarrior.
For the bearded Unix jockeys and keyboard cowboys who manage their life from the terminal — and now want their LLM to lend a hand. 🧔⌨️
<!-- mcp-name: io.github.GabiUp2/taskchampion-mcp -->
Latest release: v1.0.4 — pip install taskchampion-mcp / uvx taskchampion-mcp
What Is This?
TaskChampion MCP is a Model Context Protocol server that lets LLMs read, create, modify, and manage your Taskwarrior tasks and Timewarrior time entries. It wraps the task and timew CLI tools and exposes them as structured MCP tools that any compatible AI assistant can call.
Why? The author self-hosts TaskChampion on a home server and wanted a clean way for LLMs to cooperate on project planning, task decomposition, and time tracking — without giving up control of the task database.
Supported Platforms
Requirements:
- Python 3.10+
- Taskwarrior 3.x (TaskChampion sync)
- Timewarrior (optional, for time tracking features)
Quick Install
# With uv (recommended)
uv tool install taskchampion-mcp
# With pip
pip install taskchampion-mcpThen configure your IDE's MCP settings to use:
{
"mcpServers": {
"taskchampion": {
"command": "taskchampion-mcp-server",
"args": []
}
}
}Per-target install guides: Claude Desktop | Windsurf | Cursor | Neovim
First Run
On a fresh install with no config.toml, the server boots in onboarding mode. All tools are visible in tools/list, but operational tools return structured schema_unset errors until onboarding completes (ADR 19). You finish onboarding by persisting two keys in ~/.config/taskchampion-mcp/config.toml:
- role — what the LLM can do (CONTRIBUTOR / GENERATOR / MANAGER)
- schema or schema_path — which task schema the server validates against
Three ways to get there:
Shortened. The full README is on GitHub.
Nothing above is checked by us. What we check is on the safety report.
TaskChampion MCP: common questions
- Is TaskChampion MCP server safe?
- Mostly: it is graded B (80/100). Read the TaskChampion MCP safety report
- How do I install TaskChampion MCP?
- It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
- Does TaskChampion MCP need an API key?
- Not as far as the registry entry and our scan can tell: no credentials are declared or required.
- Is TaskChampion MCP maintained?
- The last commit was 126 days ago (2026-07-01). The latest release is v1.0.4.
- How does TaskChampion MCP compare with other Productivity MCP servers?
- safety score 80/100 (higher than 53% of 1,299 Productivity servers); tools 35 (the typical Productivity server has 7); tools that change things 17% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.