Skip to content
Agentmart
Submit a tool

subtask

Background sub-agents for Claude Code, Codex, Kimi and OpenCode, over MCP, with a spend cap.

Connector by tedin7 · GitHub account verified by the MCP Registry

IndexedMITLocal (stdio)
Write a review

Install

Works with Claude Code, Codex, VS Code, Cursor, Windsurf, Claude Desktop. Read the repository before you give any tool access to your data.

npx agentmarket install connector/tedin7-subtask

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Background sub-agents for Claude Code, Codex, Kimi and OpenCode, over MCP, with a spend cap.

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this server can do and what it asks for, from its tool list, install config and code. Checked Oct 25, 2026.

Tools
2 read · 5 write · 1 delete · 7 not yet classified
Secrets
None asked for
Install scripts
None found
Runs as
Python package

Tools by what they do 15

Read from the source code; the running server may list different tools.

Read 2 · Look things up without changing anything.

  • inspect
  • status

Write 5 · Create, change, send or run things.

  • bisect
  • reply
  • start
  • start_many
  • stop

Delete 1 · Delete, drop, revoke or wipe things.

  • cleanup

Not yet classified 7 · We could not tell from the name and description.

  • consensus
  • engines
  • integrate
  • map_reduce
  • result
  • steer
  • wait

Network hosts it talks to 4

  • api.kimi.ai · found in code
  • api.kimi.com · found in code
  • astral.sh · found in code
  • github.com · found in code

Files it touches

  • /proc/self/stat
  • /proc/sys/kernel/random/boot_id
  • /root/subtask-wt-base/.venv/bin/subtask-mcp
  • /root/subtask-wt/.venv/bin/subtask-mcp
  • Your home directory (~)
  • Any path the agent passes to its tools

Tools (15)

Read from the source code; the running server may differ. Descriptions are the server’s own words; hidden characters are shown as [U+…].

  • bisect

    First commit in good_ref..bad_ref that fails test_cmd, testing up to parallelism commits at once. auto_fix: start a fix job.

  • cleanup

    Remove a job's worktree, keep branch.

  • consensus

    2-4 engines solve prompt blind in worktrees, then one job merges the best (verify, invariants). Returns a group id for wait().

  • engines

    Free quota and API spend.

  • inspect

    Raw log lines of a job (last `tail`, filtered by `grep`). Only when the summary is not enough.

  • integrate

    Bring worktree jobs back. diff first to review; apply = uncommitted, all or nothing, Python files of symbol_scope jobs merged by symbol; discard removes worktree and branch. auto_resolve: a reconcile job on conflict.

  • map_reduce

    The same edit over many files: one job per batch of files matching glob ({{files}} in prompt_template), at most `concurrency` at once, each in a worktree with verify_cmd. Returns a group id for wait().

  • reply

    Continue a finished job.

  • result

    Job summary; full=True for all; evidence=True for the JSON envelope.

  • start

    Start one job; returns its id. kind: read|code|review|hard. Writes: repo= or isolation='worktree' (own branch). verify: shell check run by subtask after the job; max_retries (0-5) resumes with the failure. invariants: default ['no_test_deletion','no_suppression'] fail verify on deleted/skipped tests or new noqa; [] = off. allowed_paths: files outside are reverted. symbol_scope: ['f.py::func'] only those defs may change; integrate merges by symbol. oracle_cmd: after verify passes, run on base and result; reports output_match and speedup_pct. adversarial: a Breaker job writes the tests first. co…

  • start_many

    Start several jobs in one call. Items take start()'s arguments. With id + depends_on they form a group (grp-…) run as a DAG; subtask:<id>:summary in task/context_refs is replaced by the real job id. foreach=<parent id>: one copy per item of the JSON list the parent writes to .subtask/fanout.json ({{item}} in task), max 8; dependents wait for every copy. after='any': start when one parent succeeded.

  • status

    One line per job.

  • steer

    Correct a job: hint (instruction sent when the attempt ends) | abort | retry (fresh job with the instruction).

  • stop

    Stop a job.

  • wait

    Block until jobs or groups end and return their summaries. mode: all | any (first to end) | first_success (first done and verified; the rest are stopped). Returns early on a stalled job. since: cursor for clients without progress notifications. Call again only if it said 'still running'.

Compare and alternatives

    Featured in

    Signals

    Stars
    0
    Forks
    0
    Open issues
    0
    Weekly downloads
    533
    Last commit
    Oct 22, 2026 (6 days ago)
    Last release
    Oct 19, 2026 (10 days ago)
    Last package publish
    Oct 19, 2026 (10 days ago)

    From GitHub (fetched Oct 24, 2026) and the package registry.

    Details

    Registry name
    io.github.tedin7/subtask
    Version
    0.4.5
    Auth
    No auth
    Packages
    pypi subtask-mcp
    License
    MIT
    Repository
    github.com/tedin7/subtask
    First seen
    Oct 24, 2026
    Last checked
    Oct 24, 2026
    Source
    Official MCP Registrygithub-graphql
    Cite this page

    subtask MCP server. Agent Mart. https://agentmart.dev/connectors/tedin7-subtask (last updated 2026-10-24)