OpenCurrent
● Activeai.opencurrent/opencurrent
Dated, step-by-step AI workflows and agent setups your agent can search and follow (Korean).
Connect this server
One click to install, or copy the config below. Suits: Cursor · HTTP clients.
Or add it manually — claude_desktop_config.json (Claude Desktop) or .cursor/mcp.json (Cursor):
{
"mcpServers": {
"opencurrent": {
"url": "https://opencurrent.ai/mcp"
}
}
}claude mcp add --transport http opencurrent https://opencurrent.ai/mcpcode --add-mcp '{"name":"opencurrent","type":"http","url":"https://opencurrent.ai/mcp"}'Syntax from each client's docs (Claude Code: claude mcp add; Codex: codex mcp add; VS Code: code --add-mcp). Placeholders in angle brackets are values you fill in. Codex takes hosted servers in config.toml ([mcp_servers.<name>] url = …) rather than on the command line.
A starting point — check the repository for exact arguments and setup. Restart your client after editing the config.
- Category
- Other
- Version
- 0.1.0
- Registry
- active
- Published
- 11/21/2026
Is it safe? Is it maintained?
Serverdex check: Nov 22, 2026Looks healthy: OpenCurrent is maintained, open source, hosted endpoint answering without a key.
- Maintained
- Active
- Last commit 12 days ago (Nov 10, 2026), 0 open issues.
- Official registry
- Active
- Published as ai.opencurrent/opencurrent in the official MCP registry, version 0.1.0.
- Source
- Open source, MIT
- Public repository under the MIT licence, 0 stars, 0 forks.
- Runs
- Hosted by the publisher
- Your client talks to opencurrent.ai: prompts and tool arguments leave your machine for that host.
- Credentials
- None needed to connect
- The hosted endpoint completed the Serverdex initialize + tools/list handshake with no key (checked Nov 22, 2026); individual tools may still ask for one.
- Owner
- Unclaimed
- Nobody has claimed this page yet; the data above comes from the registry, GitHub and the live check.
Facts only: last commit and licence from GitHub, the entry's status from the official registry, credentials from the live check. Not a code audit — run the security scan on the endpoint yourself and see the status history.
Live check
checked Nov 22, 2026, 07:07 UTCStatus history & uptime →The endpoint answered the MCP handshake as "OpenCurrent — 에이전트에 바로 연결하는 최신 AI 활용법" and listed 8 tools. Answering since Nov 21, 2026.
Context cost ≈ 7.6k tokens of tool definitions a client loads per conversation (estimate: characters ÷ 4) across 8 tools.
Tools (8)
search_workflows11 params사용자의 작업을 시작하기 전에, 사람들이 검증한 AI 활용 방법이 있는지 찾을 때 사용. 상황을 문장이나 키워드로 넣으면(한국어 가능) 맞는 워크플로를 관련도순으로 반환. 각 결과의 status로 얼마나 믿을지 판단할 것. 단계 전체는 get_workflow로 받을 것.
Show parametersHide parameters
querystringrequired하려는 일이나 상황. 예: '회의록 정리', 'onboard to a new codebase'kindstring종류로 좁히기: prompt(바로 쓰는 프롬프트, 결과 예시 포함), workflow(여러 단계)categorystring용도로 좁히기: dev, research, writing, data, ops, productdomainstring업무 분야로 좁히기 (D100): dev(개발), vibe(바이브 코딩), marketing(마케팅), design(디자인), content(콘텐츠·미디어), education(교육), research(연구·리서치), sales(영업·고객 지원), ops(운영·사무), finance(재capabilitystring필요한 기능으로 좁히기 (D100): writing(글쓰기·요약), translate(번역), image(이미지 생성), video(영상 생성), audio(음성·전사), code(코드 작성), data(데이터 분석), search(웹 검색), documents(문서 읽기 (PDF·파일topicstring주제로 좁히기 (주 용도 포함): dev(개발), research(리서치·학습), writing(글쓰기), data(데이터 분석), ops(업무 자동화), product(기획·디자인), video(영상 제작), image(이미지·그래픽), audio(음악·오디오), marketing(마statusstring검증 상태로 좁히기: verified(검증됨), pending(검수 대기), check(확인 필요)limitinteger최대 개수, 기본 5minScoreinteger평가 점수(0~100)가 이 값 이상인 것만toolstring이 도구를 쓰는 것만 (예: 'Claude Code'). 표기가 조금 달라도 맞춤cursorstring앞 응답의 nextCursor를 넣으면 다음 결과
- list_workflows12 params
검색어 없이 용도·주제·도구·상태·점수로 워크플로 목록을 훑을 때 사용(예: 'Claude Code를 쓰는 검증된 워크플로를 점수순으로'). 축별 개수(facets)도 함께 와서 어떤 조건으로 더 좁힐지 선택 가능. 결과가 많으면 nextCursor로 이어 받을 것.
Show parametersHide parameters
kindstring종류로 좁히기: prompt(바로 쓰는 프롬프트, 결과 예시 포함), workflow(여러 단계)categorystringdomainstring업무 분야로 좁히기 (D100)capabilitystring필요한 기능으로 좁히기 (D100)topicstring주제로 좁히기 (주 용도 포함): dev(개발), research(리서치·학습), writing(글쓰기), data(데이터 분석), ops(업무 자동화), product(기획·디자인), video(영상 제작), image(이미지·그래픽), audio(음악·오디오), marketing(마statusstringtoolstring이 도구를 쓰는 것만minScoreintegersortstring기본 popular(인기순: 근거 있는 점수 → 쓰인 횟수 → 최근)goalstring하려는 일 id로 좁히기 (list_goals의 id = category). 모르는 값이면 좁히지 않음limitinteger기본 20, 최대 50cursorstring
list_goals1 param사용자가 하려는 일에 맞는 방법을 고를 때 먼저 사용. 묶음은 하려는 일 여섯(개발·리서치·학습·글쓰기·데이터 분석·업무 자동화·기획·디자인) 가운데 글이 있는 것, 묶음마다 이름(title)과 그 안의 워크플로가 인기순으로 옴(근거 있는 점수 → 쓰인 횟수 → 최근). 워크플로마다 근거 한 줄(proof)이 있어 본문을 받기 전에 고를 수 있음. 고른 것은 get_workflow로 받을 것.
Show parametersHide parameters
topinteger묶음마다 받을 워크플로 수, 기본 5
- get_workflow1 param
search_workflows로 찾은 워크플로의 전체 내용을 받을 때 사용: 준비물, 사용자에게 받을 입력값, 단계(종류, 그대로 쓸 수 있는 프롬프트, 기대 결과, 확인 방법), 주의할 점, 출처, 검증 상태. 따라 하기 전에 verification을 확인할 것.
Show parametersHide parameters
idstringrequired워크플로 id (search_workflows 결과의 id, 웹 주소 /w/<id>의 id)
list_signals2 params최근 AI 모델·도구·기법 소식과 그 소식 때문에 다시 확인해야 할 워크플로를 받을 때 사용. 워크플로를 따라 하기 전에 그사이 바뀐 점이 있는지 볼 때 유용.
Show parametersHide parameters
sincestring이 날짜(YYYY-MM-DD) 이후 소식만workflow_idstring이 워크플로와 관련된 소식만
- report_outcome4 params
get_workflow로 받은 워크플로를 실제로 따라 한 뒤 결과를 알릴 때 사용. success(목표대로 됨), partial(일부만 됨), failure(안 됨)와 짧은 이유, 쓴 모델을 남기면 이 워크플로의 평가 점수에 반영. OpenCurrent 무료 키 필요. 내용은 바뀌지 않음. 같은 키는 워크플로마다 하루 한 번(다시 보내면 그날 보고를 바꿈).
Show parametersHide parameters
idstringrequired워크플로 id (get_workflow의 id)outcomestringrequiredreasonstring무엇이 잘 됐거나 막혔는지 한두 문장. 사용자 개인정보는 넣지 말 것modelstring따라 할 때 쓴 모델 이름
- search_catalog4 params
모델의 능력·가격·컨텍스트 길이·출시일, AI 도구·에이전트의 기능과 쓰는 법, 기간별 AI 뉴스 정리를 찾을 때 사용. OpenCurrent 운영자가 공식 문서로 확인한 큐레이션 정보. 이름(예: 'Claude Sonnet 5.5', 'Cursor')이나 상황으로 찾고, 전체 내용은 get_card로 받을 것.
Show parametersHide parameters
querystringrequired모델·도구 이름이나 찾는 내용kindstringmodel(모델), tool(도구·에이전트), digest(뉴스 정리)로 좁히기capabilitystring이 기능을 가진 도구만 (D100). 활용법의 capabilities idlimitinteger최대 개수, 기본 5
- get_card1 param
search_catalog로 찾은 카드의 전체 사실 정보(모델: 가격·한도·컨텍스트·API id, 도구: 쓰는 모델·MCP 지원·시작하기, 뉴스 정리: 항목)와 출처, 확인 시점을 받을 때 사용.
Show parametersHide parameters
idstringrequired카드 id (kind/slug, 예: model/claude-sonnet-5-5) 또는 웹 주소
Checked by Serverdex with a plain initialize + tools/list call to opencurrent.ai/mcp, no credentials, about once a day. A failed check is never a removal.
On GitHub
read Nov 21, 2026- Stars
- 0
- Forks
- 0
- Last push
- Nov 10, 2026
- License
- MIT
From the README
OpenCurrent plugin 에이전트에 바로 연결하는 최신 AI 활용법. One install connects your coding agent to OpenCurrent and adds one skill, latest-first: before an agent-setup task (MCP, skills, hooks, subagents, plugins, CI), the agent looks up the latest dated method and follows it. Install Claude Code Codex No key needed (200 full workflows per day per IP). A free key from https://opencurrent.ai/account/keys raises the limit. What it sends Search words and workflow ids to https://opencurrent.ai/mcp. Never your code, files or conversation. The server is read-only. What is inside • .mcp.json / mcp.json: the remote MCP server https://opencurrent.ai/mcp • skills/latest-first/SKILL.md: when to look things up and how to follow them
Read the full README on GitHub →Remotes
- streamable-http
https://opencurrent.ai/mcp
Alternatives to OpenCurrent
All OpenCurrent alternatives →Best Other servers →The most-starred Other servers in the index, with their live-check result.
| Server | Stars | Last push | Live check |
|---|---|---|---|
| Labelhead Artist Momentum | 114,594 | Nov 2026 | Working |
| World Monitor | 91,002 | Nov 2026 | Needs sign-in |
| Tldraw | 51,470 | Nov 2026 | Working |
| OpenSEO | 28,515 | Nov 2026 | Needs sign-in |
| Windows MCP | 11,833 | Nov 2026 | Local / not checked |
OpenCurrent: questions people ask
- Is OpenCurrent a remote or a local MCP server?
- According to its entry in the official MCP registry, OpenCurrent ships as a hosted endpoint (streamable-http) that your client connects to by URL.
- Does OpenCurrent need an API key?
- Its hosted endpoint completed the Serverdex live check — an MCP initialize + tools/list call — with no credentials on Nov 22, 2026. Individual tools may still ask for a key when called.
- Is OpenCurrent safe to use?
- Looks healthy: OpenCurrent is maintained, open source, hosted endpoint answering without a key. In detail — maintained: Active; official registry: Active; source: Open source, MIT; runs: Hosted by the publisher; credentials: None needed to connect. Serverdex check of Nov 22, 2026. This is a reading of the repository, the registry entry and the live check, not a code audit; run the Serverdex security scan on the endpoint before trusting it with real data.
- Is OpenCurrent still maintained?
- Active: the repository's last commit 12 days ago. Last push Nov 10, 2026, 0 GitHub stars, MIT licence. Read from GitHub on Nov 21, 2026.
- What tools does OpenCurrent expose?
- 8 tools as listed by the server itself during the live check, including search_workflows, list_workflows, list_goals, get_workflow, list_signals. The full list with parameters is in the Live check section above.
- How do I add OpenCurrent to Claude, Cursor or VS Code?
- Copy the config in "Connect this server" into your client's MCP config file (claude_desktop_config.json, ~/.cursor/mcp.json or .vscode/mcp.json), or use the one-click Add to Cursor / Add to VS Code buttons and the one-line commands for Claude Code and Codex; then restart the client.
More Other servers
Browse all Other →OpenSwitchboard
openswitchboard-ai
Your AI posts what you want or have. You are introduced anonymously to whoever has the other half.
OrgGen AI
OrgGen-AI
Human-agent interface for projects: you prioritize and decide, your AI agents execute. Over MCP.
Spaces by Peakflo
peakflo
Hand off repetitive finance and ops work to cloud agents or people.
Pilot5
ThomasWainstein
Five AI models debate your decision blind, then give one recommendation and the strongest objection.
ProductNow
ProductNowAI
Connect AI agents to ProductNow's context engine to search, create, review, and act.
ProofSlip
Johnny-Z13
Receipt-based verification for AI agent workflows — create, verify, and poll ephemeral proof objects
Add the badge to your site
Show visitors that OpenCurrent is listed here — it’s also the link we check for a free listing.
HTML — for your website
<a href="https://serverdex.io/server/ai-opencurrent-opencurrent?utm_source=badge"><img src="https://serverdex.io/brand/badge.svg" alt="OpenCurrent — listed on Serverdex" width="123" height="40" loading="lazy"></a>Recommended. A dofollow link from your own domain is the one that counts for search engines, and it's the link we check for a free listing.
Markdown — for your README
[](https://serverdex.io/server/ai-opencurrent-opencurrent?utm_source=badge)Nice for visibility, but GitHub marks README links nofollow, so it doesn't pass authority. Use the HTML badge on your site as well.
Install buttons — for your README
[](https://serverdex.io/install/cursor/ai-opencurrent-opencurrent) [](https://serverdex.io/install/vscode/ai-opencurrent-opencurrent) [](https://serverdex.io/install/claude-code/ai-opencurrent-opencurrent)One click opens Cursor or VS Code with this server's config prefilled; the Claude Code button lands on the one-line command. The links point at Serverdex, so when your config changes the buttons keep working.
Install buttons — HTML for your docs
<a href="https://serverdex.io/install/cursor/ai-opencurrent-opencurrent"><img src="https://serverdex.io/brand/install-cursor.svg" alt="Add to Cursor — via Serverdex" width="140" height="28"></a>
<a href="https://serverdex.io/install/vscode/ai-opencurrent-opencurrent"><img src="https://serverdex.io/brand/install-vscode.svg" alt="Add to VS Code — via Serverdex" width="147" height="28"></a>
<a href="https://serverdex.io/install/claude-code/ai-opencurrent-opencurrent"><img src="https://serverdex.io/brand/install-claude-code.svg" alt="Open in Claude Code — via Serverdex" width="180" height="28"></a>Same buttons as plain links for a docs page or website.
Prefer a live badge with the score, stars and live check? Score badge (links to a page that explains the number and back to this listing).