SpecForge MCP server
2026년 11월 14일 커밋조직의 규칙과 도메인 전문 지식을 타입이 지정되고 검증된 그래프를 통해 AI agent가 반드시 준수해야 하는 결정론적 체크 항목으로 강제합니다.
다른 이름 leaderiop/SpecForge
- 스타
- 42
- Tools
- —
- 다운로드, 30일
- —
- 최신 버전
- 0.1.0-rc1
- 마지막 커밋
- 2026년 11월 14일
- 라이선스
- Apache-2.0
SpecForge MCP란?
조직의 규칙과 도메인 전문 지식을 타입이 지정되고 검증된 그래프를 통해 AI agent가 반드시 준수해야 하는 결정론적 체크 항목으로 강제합니다.
프로젝트 README에서 생성된 요약
SpecForge MCP server 정보
SpecForge는 조직의 지식을 AI agent가 따라야 하는 결정론적 규칙으로 변환하는 시스템을 제공합니다. agent가 무시할 수 있는 프롬프트 내의 서술형 지침에 의존하는 대신, 이 도구는 타입이 지정되고 검증된 그래프를 사용하여 하드 스킬을 강제합니다. 이는 도메인을 위한 컴파일러 역할을 하며, 사람이나 AI agent가 수행한 모든 변경 사항이 사전 정의된 제약 조건과 구조적 요구 사항을 준수하도록 보장합니다.
개발자는 단일 바이너리를 설치하고 @specforge/software 또는 @specforge/product와 같은 특정 확장을 사용하여 프로젝트를 초기화함으로써 로컬에서 SpecForge를 사용할 수 있습니다. 이 시스템은 MCP server를 통해 AI 클라이언트에 연결되어 Claude 또는 Cursor와 같은 agent가 그래프를 읽고, 쿼리하고, 편집할 수 있도록 합니다. agent가 규칙을 위반하는 편집을 시도하면 시스템은 변경을 거부하고 구체적인 오류를 제공합니다. 이를 통해 AI가 초안을 작성하고, 엔진이 이를 검증하며, 사람이 최종 승인을 하는 신뢰할 수 있는 루프가 생성됩니다.
활용 사례
- 1소프트웨어 사양 무결성 강제AI agent가 기술 사양 초안을 작성하고 소프트웨어 동작 및 인터페이스와 자동으로 대조하여 일관성을 검증할 수 있습니다.
- 2제품 및 마케팅 맵 관리개발자는 검증된 단일 구조 내에서 페르소나, 채널 및 여정을 매핑하도록 AI에게 작업을 맡길 수 있습니다.
- 3규제 산업의 컴플라이언스 유지제약 또는 의료 기기 분야의 조직은 절차와 승인이 엄격한 감사 기준을 따르도록 이 도구를 사용할 수 있습니다.
- 4요구 사항 추적성 자동화모든 요구 사항이 상응하는 테스트 또는 승인과 연결되도록 시스템을 사용할 수 있습니다.
프로젝트의 README를 바탕으로 작성되었습니다. 모든 활용 사례는 해당 내용의 인용문과 대조하여 확인합니다.
자동 검사
2026년 11월 12일에 실행됨전체 보고서 →아직 인증되지 않았습니다. 서버는 80점 이상의 점수, 심각한 결함 없음, 그리고 검사에 충분한 데이터를 갖추어야 합니다. 검사 방식 · 점수를 높이기 위해 수정할 항목
- 소스 저장소 연결 및 접근 가능통과
- 오픈 소스 라이선스 (OSI)통과
- 최근 1년 내 커밋 또는 릴리스통과
- 패키지 이름이 인기 패키지와 유사하지 않음검사되지 않음
- 원격 엔드포인트가 HTTPS 사용검사되지 않음
- 파괴적인 도구에 라벨 표시됨검사되지 않음
- 모델에 대한 숨겨진 지침 없음통과
- 패키지 및 해당 종속성에 중요한 보안 권고 없음검사되지 않음
README
GitHub에서 보기SpecForge turns what your organisation knows into rules your AI can't skip.
You write down your things, how they link, and the rules they must obey. SpecForge compiles that into one typed, checked graph. People and AI agents read it and change it through standard protocols (CLI, MCP, LSP), and a change that breaks a rule is refused, whoever made it.
It works for software specs, product plans, quality procedures, or any field with rules worth checking. SpecForge doesn't know your field until you install an extension that teaches it.
The problem
AI can now do real work: write code, draft a launch plan, prepare a batch record. What it works from is the weak part.
The knowledge that should guide it sits in places nothing enforces:
- Documents and specs in prose (PRDs, Markdown specs, policies, brand guides). An agent can misread a rule or skip it, silently. Nothing checks that the document is complete or that its parts agree.
- Wikis and decks drift away from reality, and nothing breaks when they do.
- Traceability (which requirement has a test, which procedure has an approval, which campaign has a source for its claim) is a spreadsheet someone updates by hand, until they stop.
- Every session starts from zero. The agent re-reads dozens of files to rediscover what you meant, and still guesses.
The more work you give to AI, the worse this gets. It produces faster than anyone can review.
This isn't a problem with the model. It's a problem with where your rules live.
The idea: hard skills, not soft skills
There are two ways to teach an AI how your organisation works.
A soft skill is advice placed in the AI's context: a prompt, a Markdown spec, a policy PDF, a skill file. It helps, but it's prose. The AI may follow it, or not.
A hard skill is a rule a program enforces. The AI can't skip it, because the check fails and says why.
| Soft skillprompt, Markdown spec, policy, skill file | Hard skillSpecForge extension | |
|---|---|---|
| Lives in | The AI's context window, as prose | A compiler, as code |
| Can the AI ignore it? | Yes, silently | No: the check fails |
| Same verdict twice? | Not always | Always. There's no AI inside |
| Knows what's missing? | No | Yes: broken links, unenforced rules, unproven promises |
| Shared how? | Copied between files | Versioned and installed, like a library |
SpecForge is an engine for hard skills. Think of it as a type checker for what your organisation means.
The five parts
| Part | What it is | In plain words |
|---|---|---|
| Extensions | WASM packages that declare entity kinds, their fields and links, the rules that judge them, and commands | The "apps": they teach SpecForge a domain |
| The graph | Every entity and link, compiled from small .spec files in your repository |
The "memory": one source of truth |
| Validation | The extensions' rules plus structural checks, on every compile and every edit | The "referee": a change that breaks a rule is refused, whoever made it |
| Surfaces | CLI, MCP, LSP with a VS Code extension, and a package registry | The "doors" people and agents come in through |
| AI models | Claude or any other agent, driving SpecForge from outside, mostly over MCP | The "brain": bring your own |
The core grammar knows five structural words: spec, ref, use, define, defaults. Every other word in a
spec (behavior, persona, invariant, campaign, procedure) and every rule ("an invariant must be enforced
by a behavior", "a journey's persona must exist") exists only because an extension declares it.
These extensions ship inside the binary, as a starter set:
| Extension | What it declares |
|---|---|
@specforge/software |
Behaviors, events, types, and interfaces (ports) |
@specforge/product |
Features, personas, channels, journeys, deliverables, milestones, releases, modules, and your team's vocabulary (terms) |
@specforge/governance |
Rules that must always hold (invariants), decisions, constraints, and failure modes |
@specforge/formal |
Properties and axioms that an SMT solver proves or refutes |
@specforge/testing, @specforge/cargo-test, @specforge/vitest |
Which of your tests prove which entities |
Turn one on with specforge add @specforge/product. The full list is in the
extension inventory. To teach SpecForge your own field, see
Extending SpecForge and the extension SDK.
What you can build with it
- Software spec frameworks. The builtin software extensions already give agents a checked spec to build
against, with tests that name the promise they prove. Methods like GSD, BMAD, OpenSpec and SpecKit are a
vocabulary plus rules, so each can become an extension, with its state in checked entities instead of
Markdown files. A GSD family (
@gsd/*) is being designed; the others are not started. - Product and marketing. Personas, channels, journeys, features and releases in one checked map that an agent can report from ("which channels does this persona use?", "what is unscheduled?"). Campaigns, audiences and claims can be added with your own extension.
- Regulated industries. Pharma (GxP), medical devices, safety cases: procedures, deviations and approvals with the rules an auditor expects, in version control and checked in CI. The AI drafts, the rules check, a qualified person signs. You write this extension yourself today; none ships yet.
- Your own domain. Any business with entities and rules worth checking. SpecForge can be the product you use, or the harness the business runs on: extensions as its domain, the graph as its memory, AI models as its workers.
The use cases say what works today and what is roadmap for each, and examples has projects you can run.
See it in 60 seconds
No agent needed. Install, create a product plan, then try to break it:
curl -fsSL https://raw.githubusercontent.com/leaderiop/SpecForge/main/install.sh | sh
mkdir launch-plan && cd launch-plan
specforge init --extensions @specforge/product # a persona, a channel, a journey, a milestone
specforge link onboarding channels email # point the journey at a channel that doesn't exist
error[E080]: the edit would leave the project with 1 error it does not have; nothing was written
error[E003]: unresolved reference 'email' in entity 'onboarding'
The edit is refused and nothing is written. Declare the channel first, and the same edit goes through:
specforge new channel email "Email newsletter" --in spec/hello.spec --description "The monthly newsletter" --status active
specforge link onboarding channels email
specforge product persona-channels developer # cli, email
An agent makes the same edits over MCP, and gets the same refusals. Hand-written files get the same check:
mkdir ../sf-demo && cd ../sf-demo
specforge init --extensions @specforge/software # spec/hello.spec, which checks clean
sed -i.bak 's/\[user_logged_in\]/[user_loged_in]/' spec/hello.spec # drop one letter
specforge check
[E003] Error: unresolved reference 'user_loged_in' in entity 'authenticate_user'
20 │ produces [user_loged_in]
│ Help: did you mean 'user_logged_in'?
[W007] Warning: event 'user_logged_in' is not produced by any behavior
1 error, 1 warning, 0 infos
A reviewer reads. A check resolves. Errors always fail the check; warnings fail it too with
specforge check --strict, which is what you run in CI.
Use it with your agent
1. Install. SpecForge is a single binary with no dependencies.
curl -fsSL https://raw.githubusercontent.com/leaderiop/SpecForge/main/install.sh | sh
# Homebrew (once the tap is published)
brew install leaderiop/tap/specforge
# Prebuilt binary via cargo-binstall
cargo binstall --git https://github.com/leaderiop/SpecForge specforge-cli
# From source (stable Rust toolchain)
git clone https://github.com/leaderiop/SpecForge && cd SpecForge
cargo install --path crates/surfaces/cli
Prebuilt archives for macOS, Linux and Windows are on the Releases page. Formal proofs (@specforge/formal) also need the z3 solver on your PATH; everything else works without it.
2. Create a project with the extensions your work needs:
specforge init --extensions @specforge/software,@specforge/product
This writes a specforge.json and a first file in spec/. In a Cargo or vitest project, it also turns on the
matching test runner.
3. Connect your agent. SpecForge speaks MCP, so any MCP client can read, query and edit the graph. Use an absolute path:
claude mcp add specforge -- specforge mcp /path/to/your/project
In Cursor, one click adds it for the open project (${workspaceFolder}):
{
"mcpServers": {
"specforge": { "command": "specforge", "args": ["mcp", "/path/to/your/project"] }
}
}
4. Ask your agent. For example:
Write a spec in
spec/for the feature I described: the behavior, the rules it must never break, the events it emits, and what proves each one. Validate it with the SpecForge tools and fix every error before you show it to me.
5. Read the result yourself.
specforge check # is the graph consistent?
specforge review # what is still unproven?
6. Link your proof. For software, each test names the entity and obligation it proves. Follow the
Rust or vitest guide, then run
specforge collect. It asks once before running your test command, and records what each test proves.
Do I have to learn a new language?
You'll want to read it, because the graph is what you approve. You rarely need to write it: your agent
writes and fixes the files, or edits them through specforge new, set and link, and the check tells it when
it's wrong.
It's built to be easy to read. Each block is one thing, with a kind, a name, a title, and fields, like a filled-in form:
channel email "Email newsletter" {
description "The monthly newsletter"
status active
}
To write specs by hand, start with the authoring tutorial, the worked example and product getting started.
Surfaces
| Surface | Status | What it's for |
|---|---|---|
CLI (specforge) |
Shipped | Check, query, export, typed edits, CI |
MCP server (specforge mcp) |
Shipped | AI agents read, query and edit the graph |
| LSP + VS Code extension | Shipped | Diagnostics, completion, navigation and formatting while you type |
Package registry (add, search, publish) |
Shipped | Install and share extensions (trust model) |
| AG-UI | Planned | Agent-driven screens for people who don't use an editor |
| HTTP | Planned | Other applications reading and changing the graph |
Not built yet, so not claimed: connections to outside systems (a CRM, an issue tracker, a quality system), and proof beyond test results. Extensions are pure WASM today: no files, no network.
How is this different from…
| You already use | It's good at | What SpecForge adds |
|---|---|---|
| Specs, PRDs and policies in Markdown | Describing intent for people and agents | The same intent as .spec files whose structure is checked. Broken references, missing pieces and unproven promises fail the check |
CLAUDE.md, AGENTS.md |
Working rules for the agent: conventions, commands, style | Nothing to replace. Keep those rules there; what must be true lives in SpecForge |
| Tests | Proving the code does something | Saying which promise each test proves, and which promises have no test at all |
| Issue trackers, roadmap tools | Tracking work in progress | A checked model of what must exist and how it links, that an agent can query |
| Requirements and quality tools (DOORS, Polarion, eQMS) | Traceability for regulated teams | Plain text in your repository, checked in CI, readable by agents, extensible by you |
| Generators | Producing code or documents from a model | Nothing. SpecForge never writes your code or your documents. Your agent does, from knowledge SpecForge has checked |
What SpecForge is not
- Not an AI. It makes no model calls. It's a deterministic compiler, written in Rust. The AI is yours.
- Not a generator. It checks knowledge. Your agent produces the work.
- Not a test framework. Your tests stay in
cargo testor vitest. SpecForge runs them only after you approve the command, and records what they prove. - Not only for software. Software is one of its biggest uses, not its definition.
Learn more
- Vision: why SpecForge exists, its principles, the north star and the use cases.
- Authoring tutorial: writing
.specfiles from zero, with a cookbook, best practices and troubleshooting. - Extending SpecForge: teach it your field, with the extension SDK.
- Test tracing for Rust and for vitest: link tests to the entities they prove.
- Formal verification: specs an SMT solver checks, with counterexamples at exact locations.
- Quick reference: every command, entity kind and diagnostic code on one page.
- Architecture, the crate map and Contributing: how SpecForge is built, what each crate owns, and how to work on it.
- Documentation hub: everything else.
License
Licensed under either of Apache License, Version 2.0 or MIT license at your option.
SpecForge MCP 질문
사용을 위해 새로운 사양 언어를 배워야 하나요?
사양을 승인하기 위해 내용을 읽을 수 있어야 하지만, SpecForge 도구의 피드백을 바탕으로 AI agent가 파일을 작성하고 수정하는 작업을 처리할 수 있습니다.
어떤 종류의 도메인을 처리할 수 있나요?
도메인에 구애받지 않으며, WASM 기반 확장을 사용하여 소프트웨어, 제품 관리, 거버넌스 또는 제약 산업과 같은 특정 분야를 학습할 수 있습니다.