Sootool MCP Server

전송별 단일 기동: ``` uv run python -m sootool --transport http --port 10535 uv run python -m sootool --transport sse-legacy --port 10536 uv run python -m

Local serverstdioPython

What is the Sootool MCP server?

전송별 단일 기동: ``` uv run python -m sootool --transport http --port 10535 uv run python -m sootool --transport sse-legacy --port 10536 uv run python -m sootool --transport websocket --port 10537 uv run python -m sootool --transport unix. The sootool mcp server wraps that behind the Model Context Protocol, so an assistant can use it through 14 defined tools rather than through you.

Adding it to your client

Setup follows the usual MCP pattern — install or clone the server, register it in your client's configuration file, restart the client.

Its toolset

Everything the assistant can do here goes through one of these:

  • core.batch — N개 독립 연산을 ThreadPoolExecutor로 병렬 실행. id 중복 거부, per-item 격리(ok|error|timeout|skipped), 최대 500 items, per-item 10s, batch 60s 제한. 결과는 입력 id 순으로 결정적
  • core.pipeline — graphlib.TopologicalSorter 기반 DAG 실행기. ${step_id.result.field} 참조 문법으로 단계 간 데이터 전달. max_steps=50, max_depth=10, step_timeout_s=2.0
  • core.pipeline_resume — 실패한 스텝을 TTL 10분 in-memory 캐시로부터 부분 재실행
  • Decimal — only 경계 · 명시적 rounding · 감사 트레이스 · 모듈 stateless / batch-safe
  • Provider — Model
  • SooTool — Decimal 커널
  • Google — gemini-2.5-pro
  • Anthropic — claude-sonnet-4-5
  • OpenAI — gpt-4o
  • Namespace — Count
  • core — 8
  • accounting — 11

Caveats

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • With 14 tools registered it takes up a noticeable share of the context window; turn it off in projects that never touch Sootool.
  • MCP clients confirm each tool call by default. Leave that on until you have watched what the sootool mcp server does with a few real requests.

When to reach for it

This sits in the AI and media services group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. Sootool's toolset — core.batch, core.pipeline, core.pipeline_resume and 11 more — is a fair guide to whether it matches your workflow. It is maintained by jinho-von-choi; worth a glance at recent repository activity before you build anything load-bearing on it.

We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.

Available tools

ToolWhat it does
core.batchN개 독립 연산을 ThreadPoolExecutor로 병렬 실행. id 중복 거부, per-item 격리(ok|error|timeout|skipped), 최대 500 items, per-item 10s, batch 60s 제한. 결과는 입력 id 순으로 결정적 재정렬된다(ADR-011).
core.pipelinegraphlib.TopologicalSorter 기반 DAG 실행기. ${step_id.result.field} 참조 문법으로 단계 간 데이터 전달. max_steps=50, max_depth=10, step_timeout_s=2.0, pipeline_timeout_s=30.0(ADR-006).
core.pipeline_resume실패한 스텝을 TTL 10분 in-memory 캐시로부터 부분 재실행.
Decimalonly 경계 · 명시적 rounding · 감사 트레이스 · 모듈 stateless / batch-safe
ProviderModel
SooToolDecimal 커널
Googlegemini-2.5-pro
Anthropicclaude-sonnet-4-5
OpenAIgpt-4o
NamespaceCount
core8
accounting11
finance15
tax10

Example prompts to try

  • Use Sootool to core.batch.
  • Use Sootool to core.pipeline.
  • Use Sootool to core.pipeline resume.

Frequently asked questions

It connects Sootool to MCP-compatible AI assistants such as Claude and Cursor, exposing 14 tools (core.batch, core.pipeline, core.pipeline_resume, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Sootool directly.