OpenCurrent MCP server
ai.opencurrent/opencurrentopencurrent.aistreamable-httpv0.1.0Scanned
Dated, step-by-step AI workflows and agent setups your agent can search and follow (Korean).
8 tools: 1 change things and 7 only read.
- Reads private data · 0
- Reads text others write · 0
- Can send data out · 0
- 1 finding
Tools listed without sign-in. Remote posture
With Anlyon
1 tool here changes things. Govern it.
- Anlyon lists the tools and adopts none.
- Each tool you adopt gets approvals and receipts.
- Your agent never holds the key.
A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.
What the OpenCurrent MCP server can do
The OpenCurrent MCP server is published by opencurrent.ai, a domain the MCP Registry verified. It has 8 tools. It can create or change data (1 tool: report_outcome), but cannot delete data. 7 tools only read.
None of its tools reads private data, brings in text other people write, or sends data out.
The fixed checks matched 1 finding (annotation-conflict). Each one comes with the text it matched.
Its remote endpoint lists its tools without sign-in.
Last scanned Nov 21, 2026, version 0.1.0.
Tools
Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.
8 tools
Changes things 1Claude Code: ask
report_outcomeget_workflow로 받은 워크플로를 실제로 따라 한 뒤 결과를 알릴 때 사용.1 finding
Why it is in this group
- The description's first verb is "get": a word for reading.
- The server marks it as not read-only (readOnlyHint: false).
Findings
- Warn
The server marks "report_outcome" as not read-only (readOnlyHint: false), and its words say it reads.
What this check looks forMatched text
annotations: {"readOnlyHint":false,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The description's first verb is "get": a word for reading.
Description, as the server wrote it 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).
Annotations the server declares
- readOnlyHint: false
- idempotentHint: true
- destructiveHint: false
- openWorldHint: false
Only reads 7Show 7 read-only tools
get_cardsearch_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.No findings
Why it is in this group
- The name "get_card" says "get": a word for reading.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
- idempotentHint: true
- openWorldHint: false
get_workflowsearch_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.No findings
Why it is in this group
- The name "get_workflow" says "get": a word for reading.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
- idempotentHint: true
- openWorldHint: false
list_goals사용자가 하려는 일에 맞는 방법을 고를 때 먼저 사용.No findings
Why it is in this group
- The name "list_goals" says "list": a word for reading.
Description, as the server wrote it 사용자가 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.
Annotations the server declares
- readOnlyHint: true
- idempotentHint: true
- openWorldHint: false
list_signals최근 AI 모델·도구·기법 소식과 그 소식 때문에 다시 확인해야 할 워크플로를 받을 때 사용.No findings
Why it is in this group
- The name "list_signals" says "list": a word for reading.
Description, as the server wrote it 최근 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.
Annotations the server declares
- readOnlyHint: true
- idempotentHint: true
- openWorldHint: false
list_workflows검색어 없이 용도·주제·도구·상태·점수로 워크플로 목록을 훑을 때 사용(예: 'Claude Code를 쓰는 검증된 워크플로를 점수순으로').No findings
Why it is in this group
- The name "list_workflows" says "list": a word for reading.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
- idempotentHint: true
- openWorldHint: false
search_catalog모델의 능력·가격·컨텍스트 길이·출시일, AI 도구·에이전트의 기능과 쓰는 법, 기간별 AI 뉴스 정리를 찾을 때 사용.No findings
Why it is in this group
- The name "search_catalog" says "search": a word for reading.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
- idempotentHint: true
- openWorldHint: false
search_workflows사용자의 작업을 시작하기 전에, 사람들이 검증한 AI 활용 방법이 있는지 찾을 때 사용.No findings
Why it is in this group
- The name "search_workflows" says "search": a word for reading.
Description, as the server wrote it 사용자의 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.
Annotations the server declares
- readOnlyHint: true
- idempotentHint: true
- openWorldHint: false
This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.
Exfil surface
Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.
No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data or untrusted-input or outbound.
- Reads private data0
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write0
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out0
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.
Remote posture
What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.
Looked at Nov 21, 2026, 19:25 UTC, unchanged since Nov 21, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- yes
- HTTP status of an anonymous initialize
- 200
- tools/list served without credentials
- yes
- Tools that change things, listed without credentials
- 1
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- not observed
- Authorization servers
- not observed
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- not observed
- Client ID metadata documents
- not observed
- WarnThe whole server
The endpoint served tools/list without credentials, and the list has 1 tool that changes things (1 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://opencurrent.ai/mcp: tools/list returned 8 tools to an anonymous client, including report_outcome (write)
Findings
Matches of fixed checks, with the text they matched.
- Warnreport_outcome
The server marks "report_outcome" as not read-only (readOnlyHint: false), and its words say it reads.
What this check looks forMatched text
annotations: {"readOnlyHint":false,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The description's first verb is "get": a word for reading.
History
Changes to its tool definitions and to its remote endpoint, newest first.
No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.
Install
Pinned to version 0.1.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http opencurrent https://opencurrent.ai/mcpclaude mcp add --transport http opencurrent https://opencurrent.ai/mcpRun in a terminal.
Claude Code permissions
Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.
{
"permissions": {
"allow": [
"mcp__opencurrent__search_workflows",
"mcp__opencurrent__list_workflows",
"mcp__opencurrent__list_goals",
"mcp__opencurrent__get_workflow",
"mcp__opencurrent__list_signals",
"mcp__opencurrent__search_catalog",
"mcp__opencurrent__get_card"
],
"ask": [
"mcp__opencurrent__report_outcome"
],
"deny": []
}
}Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as opencurrent. Review it before you use it.
Pin
Keep the decision: fail CI when the tools change, follow every change, or show a badge.
Pin in CI
Fail a build when the tools you reviewed are not the tools the server serves today.
curl -s "https://radar.anlyon.com/api/v1/servers/ai.opencurrent/opencurrent/verify?hash=a48219cdce3bcec18b0f1ea4b0f54fc859d454175cbc62933001e82c412472bb" | jq -e '.changed == false'Pinned hash a48219cdce3b, from Nov 21, 2026, 03:17 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/ai.opencurrent/opencurrent/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/ai.opencurrent/opencurrent)Source: MCP Registry · repository. Synced Nov 21, 2026, 03:17 UTC.
OpenCurrent MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the OpenCurrent MCP server safe?
- No scan can promise that. What its definitions show: 8 tools, 1 of which can change, send or delete something, and 1 finding from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the OpenCurrent MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the OpenCurrent MCP server do things that cannot be undone?
- No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.
What tools does the OpenCurrent MCP server have?
- 8 tools: 1 write, 7 read. report_outcome, search_workflows, list_workflows, list_goals, get_workflow, list_signals, search_catalog and get_card.
Does the OpenCurrent MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the OpenCurrent MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the OpenCurrent MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 21, 2026.