MCP servers › net.builderlog › connector
MCP server · registry snapshot 2026-11-18 · last tested 2026-11-18
connector MCP server
Registry name net.builderlog/connector
Builderlog — the publisher's title
by builderlog.net · domain (the registry's namespace rule)Website ↗
Korean creator tools: Naver blog writing aids plus Shorts, Reels, TikTok and Clip checks. — the publisher's description
Summary
net.builderlog/connector is a remote MCP server listed in the official MCP registry at version 1.1.0, under the namespace of the domain builderlog.net. On 2026-11-18 ProtocolProbe connected to it in read-only mode and read its inventory: 67 tools, 0 resources and 0 prompts.
Record checks
1 of 2 record checks met · 7 do not apply
- met: Registry entry is active and says how to run it
- not met: Source repository link opens
- not applicable: Repository is not archived
- not applicable: Code pushed to the repository in the 90 days before our check
- not applicable: Repository publishes a security policy (SECURITY.md)
- not applicable: Package names its licence with a standard (SPDX) identifier
- not applicable: The version the registry lists can be installed and is not withdrawn
- not applicable: npm package carries build provenance (attestation)
- not applicable: No known critical or high advisory in the package or its dependencies
- Not ranked by downloads: a remote server publishes no download figure
- Not ranked by stars: no public GitHub repository
From public records, not a safety rating. Each check with its reason
Operate this server? Correct a fact · README badge · Run the checks yourself · Claim it
Key facts
- Runs
- remote (hosted by the publisher)
- Transport
- streamable HTTP
- Your own values
- none declared (not a guarantee)
- Sign-in
- none needed to open a session
- Tools
- 67
- Last tested
- 2026-11-18
Tool list size
25,646 tokens on Claude Opus 5.5
Added to every request that loads this server's tools (67 tools). Counted with Anthropic's token counter on 2026-11-18, from the tool list we read on 2026-11-18. Median across 28,560 counted servers: 2,657 tokens. How it is counted
How a client gets in
Connects without signing in
Read from the server's public metadata on 2026-11-18 (my.builderlog.net), in our read-only connection; no tool was called. It may have changed since. How it is read
Tool list at the three APIs
Not sent yet for this version (1.1.0).
How fresh this is
- Live-tested
- yes, a real session (not a text-only review)
- Last tested
- 2026-11-18
- Mode
- read-only (no tool calls)
- Latest version
- 1.1.0, published 2026-11-18 (registry, as of the 2026-11-18 snapshot)
- First listed version
- 2026-11-17 (earliest version still in the registry; older removed versions would be earlier)
- Version history
- 2 versions listed, 2026-11-17 to 2026-11-18; 2 in the 90 days before the 2026-11-18 snapshot.(versions still listed in the registry only)
Most recent 2 versions
1.1.0· 2026-11-181.0.0· 2026-11-17
- Registry data
- snapshot 2026-11-18
- Package and repository
- checked 2026-11-18
- Engine
- mcp-runtime-engine@0.1.0 · sdk@1.32.0
Dead or stale signals
None found in the records we hold
Looked for and not found: deprecated in the registry. Does not apply: listed version cannot be installed or is withdrawn; repository link does not open; repository archived; no push in over 365 days. Each line is a dated fact from a public record. It does not say whether the server still works, and a record can change after the date shown.
Changes since the last refresh
Version 1.0.0 (published 2026-11-17) → 1.1.0 (published 2026-11-18), between the registry lists of 2026-11-17 and 2026-11-18.
No release note: the registry entry links no GitHub repository.
Source: the official MCP Registry list on 2026-11-17 and on 2026-11-18; release notes from the GitHub Releases API, checked 2026-11-18.
What it is
What does this server offer?
Observed inventoryNone of its 67 tools are described as changing anything. For 67 the reading was uncertain, so no mark is shown.
- blog_ideas
“이번 달 일정(세금·제도·계절)과 사용자가 말한 블로그 분야·주제로 글감 3~5개를 만들어요.”
Publisher declares: read-only yes · open-world no
3 inputs
fieldstring“내 블로그 분야·주제(예: 육아, 재테크, IT 기기, 살림).”countinteger“글감 수(3~5, 기본 3)”kindstring“글 종류: general 일반 정보 · howto 사용법·설정 · money 돈·세금·계산 · it IT·제품 가격 · entertainment 방송·연예 리뷰 · review 제품 후기(직접 써 본 것) · visit 방문 후기(맛집·장소, 직접 가 본 곳)”
- blog_title_check
“네이버 블로그 글 제목 한 줄을 규칙으로 점검해요(글자 수 상한·키워드 위치·과장어·흐린 말·사용자가 준 예전 제목과 겹침).”
Publisher declares: read-only yes · open-world no
4 inputs, 1 required
titlestringrequired“점검할 제목 한 줄”keywordstring“검색 키워드(선택, 제목 앞 12자 안에 있는지 봐요)”kindstring“글 종류: general 일반 정보 · howto 사용법·설정 · money 돈·세금·계산 · it IT·제품 가격 · entertainment 방송·연예 리뷰 · review 제품 후기(직접 써 본 것) · visit 방문 후기(맛집·장소, 직접 가 본 곳)”past_titlesarray“이미 올린 내 글 제목들(겹침 확인, 선택)”
- blog_brief
“주제·키워드·글 종류로 글 설계표(제목 규칙과 틀, 소제목 순서, 쓰기 전에 열어 볼 근거 목록, 말투 규칙)를 만들어요.”
Publisher declares: read-only yes · open-world no
3 inputs, 1 required
topicstringrequired“쓸 주제 한 줄”keywordstring“검색 키워드(제목 앞 12자 안에 넣을 말)”kindstring“글 종류: general 일반 정보 · howto 사용법·설정 · money 돈·세금·계산 · it IT·제품 가격 · entertainment 방송·연예 리뷰 · review 제품 후기(직접 써 본 것) · visit 방문 후기(맛집·장소, 직접 가 본 곳)”
- blog_check
“네이버 블로그 초안을 기계 규칙으로 점검해요(제목 길이·키워드 위치·과장어·본문 길이·소제목 수·금지어·붙여 넣으면 깨지는 줄 등).”
Publisher declares: read-only yes · open-world no
5 inputs, 1 required
titlestring“제목(초안 첫 줄 # 제목이면 비워도 됨)”bodystringrequired“초안 전체(마크다운)”keywordstringkindstring“글 종류: general 일반 정보 · howto 사용법·설정 · money 돈·세금·계산 · it IT·제품 가격 · entertainment 방송·연예 리뷰 · review 제품 후기(직접 써 본 것) · visit 방문 후기(맛집·장소, 직접 가 본 곳)”past_titlesarray“이미 올린 내 글 제목들(겹침 확인, 선택)”
- blog_cover
“표지 문구로 1080×1080 표지 그림을 보여 주는 화면 주소를 만들어요.”
Publisher declares: read-only yes · open-world no
4 inputs, 1 required
line1stringrequired“큰 글자 첫 줄”line2string“빨간 강조 줄(선택)”labelstring“왼쪽 위 작은 꼬리표(선택, 예: 2026 기준)”stylestring
- pack_install
“블로그 팩을 사용자 컴퓨터(Claude 데스크톱 앱의 Code)에 설치하는 순서와 붙여 넣을 한 줄을 알려 줘요.”
Publisher declares: read-only yes · open-world no
Takes no inputs.
- blog_topic_risk
“글감·키워드·제목 후보에 소문·미발표 표현(루머·유출·~할 듯 등)과 이미 지난 날짜가 있는지 낱말과 날짜 모양으로 점검해요.”
Publisher declares: read-only yes · open-world no
2 inputs, 1 required
topicsarrayrequired“점검할 글감·제목 후보(최대 10개)”todaystring“기준일 YYYY-MM-DD(선택, 기본 오늘 한국 날짜)”
- blog_ai_tone_check
“초안에 남은 AI 상투 표현(“결론적으로”, “다양한 …을 통해” 등)·같은 어미 3문장 연속·3단 나열을 정규식으로 세어요.”
Publisher declares: read-only yes · open-world no
1 input, 1 required
bodystringrequired“초안 전체(마크다운)”
- blog_depth_check
“초안을 네 가지로 점검해요.”
Publisher declares: read-only yes · open-world no
2 inputs, 1 required
bodystringrequired“초안 전체(마크다운)”source_textstring“근거 원문(선택).”
- blog_tags
“초안에서 태그 후보 최대 12개를 낱말 빈도와 제목 속 이웃 낱말로 뽑아요(조사·어미 제거, 금액 제외).”
Publisher declares: read-only yes · open-world no
1 input, 1 required
bodystringrequired“초안 전체(첫 줄 “# 제목” 이면 제목 낱말을 앞에 둬요)”
- blog_dup_check
“새 초안과 사용자가 붙여 넣은 예전 글 본문(최대 20편)을 글자 3개 묶음 코사인으로 견줘 많이 겹치는 글을 알려요.”
Publisher declares: read-only yes · open-world no
2 inputs, 2 required
bodystringrequired“새 초안 전체(200자 이상)”past_postsarrayrequired“예전 글 본문들(각 200자 이상, 첫 줄 “# 제목” 이면 제목을 같이 보여 줘요)”
- blog_repurpose_plan
“완성한 블로그 글을 스레드·인스타 카드뉴스·숏츠 대본으로 줄일 때 쓰는 지시표를 만들어요.”
Publisher declares: read-only yes · open-world no
3 inputs, 1 required
bodystringrequired“완성한 블로그 글 전체(마크다운)”targetstring“thread 스레드 · cardnews 인스타 카드뉴스 · shorts 숏츠 대본(기본 thread)”audiencestring“읽는 사람 한 줄(선택)”
Show 55 more tools
- blog_link_slot_check
“초안의 링크를 점검해요.”
Publisher declares: read-only yes · open-world no
2 inputs, 1 required
bodystringrequired“초안 전체(마크다운)”has_affiliateboolean“제휴(수수료) 링크가 있으면 true(알려진 짧은 주소 모양은 자동으로도 봐요)”
- blog_collab_draft
“체험단 신청 글, 협찬 제안 메일, 협찬 글 맨 앞 표기 문구의 틀을 만들어요.”
Publisher declares: read-only yes · open-world no
6 inputs, 1 required
kindstringrequired“experience_apply 체험단 신청 글 · sponsor_pitch 협찬 제안 메일 · disclosure_note 협찬 글 맨 앞 표기 문구”brandstring“업체·브랜드 이름(선택)”productstring“제품 이름(선택)”blog_introstring“내 블로그 소개 한 줄(선택)”my_statsstring“직접 확인한 내 숫자(선택)”providedstring“받은 것(제품·원고료 등, 선택)”
- blog_reply_triage
“사용자가 붙여 넣은 댓글(최대 20개)을 질문·감사·불만·광고 의심·개인정보 요청으로 나누고 종류별 답글 틀을 돌려줘요.”
Publisher declares: read-only yes · open-world no
2 inputs, 1 required
commentsarrayrequired“댓글 본문들(최대 20개, 각 300자까지)”tonestring“답글 말투 한 줄(선택, 예: 다정한 존댓말)”
- blog_homefeed_check
“초안의 제목 길이·답 단어·첫 문단 길이·이미지 수와 첫 이미지 자리·태그 수를, 홈판·검색 상위 글 199편을 직접 센 기준(종류별 4가지)과 견줘요.”
Publisher declares: read-only yes · open-world no
4 inputs, 1 required
bodystringrequired“초안 전체(마크다운, 첫 줄 “# 제목”, 이미지는  줄로)”profilestring“general 일반 정보 · info 제품·IT 구매 · howto 사용법·설정 · entertainment 방송·연예(기본 general)”titlestring“제목(초안 첫 줄에 # 제목이 없을 때만)”tagsarray“붙일 태그들(선택, 개수만 견줘요)”
- blog_decay_check
“사용자가 붙여 넣은 글별 일별 조회 표(쉼표·탭 구분, 열: 날짜·제목·조회수)에서 최근 7일 조회가 직전 7일보다 20% 이상 줄어든 글을 찾고 손볼 방향(보강·합치기·방치 검토)을 알려요.”
Publisher declares: read-only yes · open-world no
3 inputs, 1 required
tablestringrequired“글별 일별 조회 표(첫 줄은 열 이름: 날짜,제목,조회수).”blogstring“표에 블로그가 여러 곳일 때 볼 블로그 이름(선택)”todaystring“기준일 YYYY-MM-DD(선택, 기본은 표의 마지막 날짜)”
- blog_internal_links
“새 초안과 사용자가 붙여 넣은 내 다른 글 목록(제목·주소·요약)을 견줘, 초안 안에 걸어 둘 만한 글 최대 5개와 넣기 좋은 문단을 알려요.”
Publisher declares: read-only yes · open-world no
2 inputs, 2 required
bodystringrequired“새 초안 전체(마크다운, 200자 이상)”postsarrayrequired“내 다른 글 목록(최대 100개).”
- blog_voice_profile
“내가 직접 쓴 글 2~3단락 이상에서 문장 길이·어미·끝맺음·말버릇·부호·경험을 말하는 방식을 세어 글을 쓰는 AI 에게 줄 말투 규칙표로 돌려줘요.”
Publisher declares: read-only yes · open-world no
1 input, 1 required
bodystringrequired“내가 직접 쓴 글(문장 10개·300자 이상, 최대 12,000자)”
- blog_keyword_volume
“키워드 최대 5개(로그인 없이 3개)의 네이버 월 검색량(PC·모바일)을 알려요.”
Publisher declares: read-only yes · open-world yes
1 input, 1 required
keywordsarrayrequired“검색량을 알고 싶은 키워드(최대 5개, 각 20자 안)”
- builderlog_setup
“빌더로그 도구에 붙일 수 있는 내 API 키(네이버 검색광고·네이버 검색·AI 이미지) 목록과 키별 발급 3단계, 키 없이 되는 것과 키를 붙이면 더 되는 것을 보여 줘요.”
Publisher declares: read-only yes · open-world no
1 input
keystring“자세히 볼 키(선택): searchad 네이버 검색광고 · naver_search 네이버 검색 · image_ai AI 이미지 · search_console 서치 콘솔”
- shorts_title_check
“쇼츠 제목 후보(최대 10개)의 길이(피드에서 잘리는 28자 기준)·제목 장치(질문·숫자·반전 등 12유형)·과장 표현·해시태그 수를 점검하고 점수 순으로 보여 줘요.”
Publisher declares: read-only yes · open-world no
2 inputs, 1 required
titlesarrayrequired“제목 후보(최대 10개)”past_titlesarray“예전 영상 제목(선택, 최대 50개)”
- shorts_hook_check
“첫 화면 글자(제목·첫 문장)가 결과부터 말하는지 낱말 모양으로 점검해요.”
Publisher declares: read-only yes · open-world no
2 inputs, 1 required
textstringrequired“첫 화면 글자(제목·첫 문장 한 줄)”profilestring“기본 shortform.”
- shorts_trend_pick
“사용자가 붙여 넣은 영상 표(채널·제목·조회수, 최대 100줄)를 채널별 중앙값 대비 배수로 줄 세우고, 2배 넘게 뜬 영상의 제목 유형을 세어요.”
Publisher declares: read-only yes · open-world no
1 input, 1 required
videosarrayrequired“영상 표”
- shorts_retention_cliff
“유튜브 스튜디오에서 받은 시청 지속(유지율) 곡선 CSV 를 붙여 넣으면 시청자가 가장 많이 빠진 구간(초)을 찾아요.”
Publisher declares: read-only yes · open-world no
3 inputs, 1 required
csvstringrequired“유지율 CSV 전체(첫 줄은 제목 줄: 시간·유지율 칸)”itemsarray“대본 항목 순서(선택)”topinteger“보여 줄 구간 수(기본 3)”
- shorts_script_tone_check
“말로 읽는 쇼츠 대본에 남은 AI 상투 표현(“결론적으로”, “살펴볼게요” 등)·같은 어미 5문장 연속·3단 나열을 정규식으로 세어요.”
Publisher declares: read-only yes · open-world no
1 input, 1 required
scriptstringrequired“대본 전체”
- shorts_number_check
“대본의 숫자(금액·%·날짜 등)가 근거 원문에 있는지 대조해요(80만원=800,000원처럼 같은 값은 같게 봐요).”
Publisher declares: read-only yes · open-world no
2 inputs, 2 required
scriptstringrequired“대본 전체”source_textstringrequired“근거 원문(공식 페이지 글 등)”
- reels_hook_check
“첫 화면 글자(제목·첫 문장)가 결과부터 말하는지 낱말 모양으로 점검해요.”
Publisher declares: read-only yes · open-world no
5 inputs
textstring“첫 화면 글자(선택)”formatstring“영상 꼴(선택): pov·before-after·전후·demo·시연·review·후기”first_shotstring“첫 1초 장면 표시(선택): result 면 결과 장면”scenestring“첫 프레임에 보이는 장면 한 줄 설명(선택)”cap_rationumber“첫 글자 높이 ÷ 화면 높이(선택, 예 0.035)”
- reels_first_second_fix
“직전 릴스의 스킵률(처음에 넘긴 비율 %)이 기준(기본 90%)을 넘으면 다음 편은 첫 1초만 바꾸라고 알려 주고, 결과 컷 시작 시각(초)을 주면 한도(기본 2초) 안으로 몇 초 당길지 계산해요.”
Publisher declares: read-only yes · open-world no
5 inputs
skip_ratenumber“직전 릴스 스킵률(%, 1~100, 선택)”avg_watchnumber“평균 시청 시간(초, 선택)”result_atnumber“결과 컷 시작 시각(초, 선택)”limitnumber“스킵률 기준(%, 기본 90)”cut_limitnumber“결과 컷 한도(초, 기본 2)”
- reels_insights_audit
“사용자가 붙여 넣은 게시물 표(계정 구분값·게시물 ID·조회·도달·공유·팔로우, 최대 300줄)로 계정별 조회 중앙값 대비 배수 상·하위 5편과 도달 대비 공유 상위를 보여 줘요.”
Publisher declares: read-only yes · open-world no
1 input, 1 required
postsarrayrequired“게시물 표”
- reels_script_tone_check
“말로 읽는 릴스 대본에 남은 AI 상투 표현·같은 어미 5문장 연속·3단 나열을 정규식으로 세어요.”
Publisher declares: read-only yes · open-world no
1 input, 1 required
scriptstringrequired“대본 전체”
- reels_number_check
“대본·캡션의 숫자(가격·%·날짜 등)가 근거 원문(상품 페이지 글 등)에 있는지 대조해요.”
Publisher declares: read-only yes · open-world no
2 inputs, 2 required
scriptstringrequired“대본·캡션 전체”source_textstringrequired“근거 원문”
- reels_subtitle_check
“SRT 자막의 구조를 점검해요: 시간 순서·겹침·영상 길이 넘김·빈 자막·3줄 이상·한 줄 글자 수(기본 42자).”
Publisher declares: read-only yes · open-world no
3 inputs, 2 required
srtstringrequired“SRT 자막 전체”durationnumberrequired“영상 길이(초)”max_charsinteger“한 줄 최대 글자 수(기본 42)”
- shorts_script_gate
“음성·이미지를 만들기 전에 대본 JSON 을 팩의 관문 규칙으로 점검해요: 빠진 칸·인사로 시작·목록 항목 수와 길이·장면표 수·내 해석(take)·숫자가 근거 원문에 있는지·첫 문장이 제목 약속을 말하는지·피할 낱말.”
Publisher declares: read-only yes · open-world no
4 inputs, 1 required
scriptobjectrequired“대본 JSON: title·hook·items(목록형) 또는 script(읽는 대본)·storyboard[{visual, motion}]·cta·take·sources[]”formatstring“대본 꼴(기본 list)”source_textstring“숫자를 대조할 근거 원문(선택)”rulesobject“채널 규칙(선택): list_items·item_max_chars·narrated_max_chars·take_max_chars·require_take·first_line_promise·banned_words·payoff_check”
- shorts_recent_topics
“사용자가 넣은 최근 14일 영상 표(채널·제목·주소·게시일·관측일·조회수, 최대 300줄)를 채널 중앙값과 견줘 3배 넘게 뜬 영상을 소재 후보로 보여 줘요.”
Publisher declares: read-only yes · open-world no
3 inputs, 2 required
as_ofstring“기준일 YYYY-MM-DD(비우면 오늘 한국 날짜).”active_channelsarrayrequired“최근 활동을 확인한 채널 이름”videosarrayrequired“영상 표”
- shorts_highlight_picker
“긴 영상의 문장 시간표(start·end·text·sentence_end, 최대 2000문장)에서 문장 경계를 지키는 20~60초 구간을 30초에 가깝고 질문으로 시작하는 순서로 최대 5개 골라 줘요.”
Publisher declares: read-only yes · open-world no
1 input, 1 required
sentencesarrayrequired“문장 시간표”
- shorts_policy_title_check
“정책·제도 설명 쇼츠 제목을 팩의 경험 기준으로 점검해요: 과장 표현, 연도·나이·등급, 제도 이름(institution), 몇 %·언제·얼마 질문형, 영상 꼴, 해설형이면 첫 장면·끝맺음 초.”
Publisher declares: read-only yes · open-world no
6 inputs, 1 required
titlestringrequired“제목”institutionstring“제도 이름”formatstring“영상 꼴: hitcard_night(리스트형)·explainer(해설형) 등”hook_endnumber“해설형: 첫 장면 끝 초”cta_startnumber“해설형: 끝맺음 시작 초”open_endingboolean“해설형: 열린 끝맺음 여부”
- shorts_hook_ab_check
“제목 후보 20개(유형 두 개 × 10개)와 A/B 두 후보·고른 제목·첫 화면 문구가 팩의 규칙에 맞는지 점검해요: 등록 유형·중복·A/B 서로 다른 유형·빈칸 표시·날짜만 있는 제목.”
Publisher declares: read-only yes · open-world no
5 inputs, 1 required
title_candidatesarrayrequired“제목 후보(20개)”abarray“A/B 후보 번호 두 개(첫 후보는 0)”titlestring“고른 제목”hook_typestring“고른 제목의 유형”first_screenstring“첫 화면 문구”
- shorts_disclosure_check
“제휴 링크·가상인물 영상에 필요한 표시 계획(처음·끝 광고 문구, 전체 길이 가상인물)을 보여 주고, 넣은 자막 목록이 그 시간을 덮는지, 첫 화면·설명란 첫 줄 고지·합성 공개 값·링크 추적 ID 를 점검해요.”
Publisher declares: read-only yes · open-world no
9 inputs, 1 required
durationnumber“영상 길이(초)”affiliatebooleanrequired“제휴 링크 영상인가”virtual_personboolean“가상인물이 나오는가”labelsarray“넣은 표시 자막(선택)”first_screen_captionstring“첫 화면 자막(선택)”descriptionstring“설명란 글(선택)”synthetic_declaredboolean“업로드 화면의 변경·합성 콘텐츠 공개 값”linksarray“제휴 링크(선택)”link_guidestring“링크 안내 위치(선택): description·profile”
- shorts_warmup_plan
“새 유튜브 채널을 첫 게시 전 7일 동안 사람이 직접 하는 예열 루틴(오늘 할 일·하루 상한·하지 말 것·멈출 신호)을 시작일 기준으로 보여 줘요.”
Publisher declares: read-only yes · open-world no
2 inputs, 1 required
start_datestringrequired“예열 시작일 YYYY-MM-DD(1일차)”todaystring“오늘 날짜 YYYY-MM-DD(비우면 한국 날짜)”
- reels_shortform_plan_check
“릴스 계획서(컷·동작·프롬프트·제목 글꼴·문구·첫 화면 형식)를 팩의 기본 규칙으로 점검해요: 정지 사진 확대, AI 사람 장면의 걷기·넓게 느리게, 프롬프트 길이·레퍼런스 수·시도 횟수, 판매원 말투, 첫 화면 결과 먼저, 비교 영상의 직접 촬영.”
Publisher declares: read-only yes · open-world no
2 inputs, 1 required
planobjectrequired“계획서 JSON: shots[{id, source, motion, action, prompt, refs_count, takes, ai}]·title{text, font_class}·copy[{text, role}]·first_screen{format_no, text}·kind·shap…”last_format_nointeger“직전 영상의 첫 화면 형식 번호(선택)”
- reels_story_plan_check
“쇼핑 릴스 계획(문제→제품→사용→가격→링크 장면, 2초 자막, 제목 후보 20개, 후속 아이템 30개, 가격 출처)을 팩의 규칙으로 점검해요.”
Publisher declares: read-only yes · open-world no
1 input, 1 required
planobjectrequired“계획 JSON: beats[{beat, text, scene_keyword, source, start, end}]·captions[{start, end, text}]·titles[{text, angle}]·followups[{item, day}]·save_summary[]·price_…”
- reels_dm_link
“댓글 키워드 DM 에 넣을 내 페이지 주소에 유입 표시(출처 instagram·매체 dm·캠페인 ig-dm-키워드)를 붙여 줘요.”
Publisher declares: read-only yes · open-world no
2 inputs, 2 required
urlstringrequired“내 페이지 주소”keywordstringrequired“댓글 키워드(예: 가계부)”
- reels_affiliate_label_check
“캡션·설명·문서 글에서 주소가 있는 줄마다 광고 표시가 있는지 보고, 빠진 줄 번호를 알려 줘요.”
Publisher declares: read-only yes · open-world no
1 input, 1 required
textstringrequired“점검할 글(캡션·설명 등)”
- reels_warmup_plan
“새 인스타그램 계정을 첫 게시 전 7일 동안 사람이 직접 하는 예열 루틴(오늘 할 일·하루 상한·하지 말 것·멈출 신호)을 시작일 기준으로 보여 줘요.”
Publisher declares: read-only yes · open-world no
2 inputs, 1 required
start_datestringrequired“예열 시작일 YYYY-MM-DD(1일차)”todaystring“오늘 날짜 YYYY-MM-DD(비우면 한국 날짜)”
- tiktok_first_screen_check
“틱톡 첫 화면 글자가 결과부터 말하는지 낱말 모양으로 점검해요.”
Publisher declares: read-only yes · open-world no
4 inputs
textstring“첫 화면 글자(제목·첫 문장 한 줄)”profilestring“기본 shortform”formatstring“영상 꼴(선택): pov·before-after·전후·demo·시연·review·후기”first_shotstring“첫 1초 장면 표시(선택): result 면 결과 장면”
- tiktok_first2s_check
“틱톡 분석의 2초 지점 유지율(%)을 넣으면 2초 안에 넘긴 비율이 기준(기본 90%)을 넘는지 보고 첫 2초만 바꾸라고 알려 줘요.”
Publisher declares: read-only yes · open-world no
5 inputs
retention_2snumber“2초 지점 유지율(%, 0~100, 선택)”avg_watchnumber“평균 시청 시간(초, 선택)”result_atnumber“결과 컷 시작 시각(초, 선택)”limitnumber“넘김 비율 기준(%, 기본 90)”cut_limitnumber“결과 컷 한도(초, 기본 2)”
- tiktok_ideason 1 other server
“주제·시청자·해결할 불편·보여 줄 자료를 넣으면 팩의 주제 찾기·첫 2초 비교 틀(문제형·질문형·결과형)과 내 AI 에 붙여 넣을 요청문을 만들어 줘요.”
Publisher declares: read-only yes · open-world no
6 inputs, 1 required
topicstringrequired“주제(예: 책상 정리)”audiencestring“시청자(선택)”problemstring“해결할 불편(선택)”materialstring“내가 보여 줄 수 있는 자료(선택)”goalstring“영상 목적(선택)”trendsarray“내가 모은 요즘 흐름·키워드(선택, 최대 50개)”
- tiktok_ai_tone_check
“말로 읽는 틱톡 대본에 남은 AI 상투 표현·같은 어미 5문장 연속·3단 나열을 정규식으로 세어요.”
Publisher declares: read-only yes · open-world no
1 input, 1 required
scriptstringrequired“대본 전체”
- tiktok_caption_check
“틱톡 설명·고정 댓글 글에서 눌리지 않는 링크·다른 앱으로 오라는 말·깨질 수 있는 원문자·지어낸 체험 표현을 찾아요.”
Publisher declares: read-only yes · open-world no
3 inputs, 1 required
captionstringrequired“설명 글 전체”ai_personboolean“AI 로 만든 사람(가상인물)이 나오는지”adboolean“광고·협찬인지”
- tiktok_plan_check
“영상 계획서(JSON)의 컷 동작·프롬프트(걷기·정지 사진 확대·길이·레퍼런스 수·돌린 횟수), 제목 글꼴, 판매원 말투 문구, 첫 화면 형식 순환, 첫 화면 글자·숫자 대조, 쇼핑 태그 규칙을 팩 기본 설정으로 점검해요.”
Publisher declares: read-only yes · open-world no
2 inputs, 1 required
planobject or stringrequired“계획서(JSON 객체나 JSON 글)”last_format_nointeger“직전 영상의 첫 화면 형식 번호(선택)”
- tiktok_number_check
“대본·설명 글의 숫자(가격·%·날짜 등)가 근거 원문(상품 페이지 글 등)에 있는지 대조해요.”
Publisher declares: read-only yes · open-world no
2 inputs, 2 required
scriptstringrequired“대본·설명 글 전체”source_textstringrequired“근거 원문”
- tiktok_video_prompt_check
“AI 영상 프롬프트 한 줄을 팩 기본 설정으로 점검해요: 사람 장면의 걷기·달리기(발 미끄러짐), 넓게·느리게 빠짐, 정지 사진 확대, 240자 넘음, 레퍼런스 7장 넘음, 3번 미만으로 돌림.”
Publisher declares: read-only yes · open-world no
4 inputs, 1 required
promptstringrequired“영상 프롬프트”personboolean“사람 동작을 주어 없이 적은 글인지(선택)”refs_countinteger“레퍼런스 이미지 수(선택)”takesinteger“같은 프롬프트를 돌린 횟수(선택)”
- tiktok_upload_checklist
“광고 여부·AI 생성 여부·가상인물·설명 글·영상 길이를 넣으면 광고 고지·AI 표시·가상인물 첫 줄과 띠·제휴 추적 ID·워터마크·출처를 해당·해당 없음·미확인으로 나눈 확인표를 만들어요.”
Publisher declares: read-only yes · open-world no
9 inputs
adboolean“광고·협찬인지”ai_videoboolean“AI 로 만든 장면이 있는지”ai_personboolean“AI 로 만든 사람(가상인물)이 나오는지”bannerboolean“영상에 '가상인물' 띠를 넣었는지”captionstring“설명 글(선택)”scriptstring“대본·자막(선택)”durationnumber“영상 길이(초, 선택)”affiliateboolean“제휴 링크·추적 ID 를 쓰는지”rights_confirmedboolean“자료 출처·권리를 확인했는지”
- tiktok_warmup_plan
“새 틱톡 계정의 7일 예열 권장 루틴을 시작일 기준으로 보여 줘요: 오늘이 며칠째인지, 그날 할 일·하루 상한·하지 말 것, 멈출 신호.”
Publisher declares: read-only yes · open-world no
2 inputs, 1 required
start_datestringrequired“예열 시작일(YYYY-MM-DD, 시작한 날이 1일차)”todaystring“오늘 날짜(선택, 비우면 한국 날짜)”
- tiktok_insight_traits
“붙여 넣은 내 영상 표(길이 초·제목·설명·끝 요청 문구·조회, 최대 300줄)를 길이 구간·제목 꼴·설명 길이·끝 요청 종류로 나눠 묶음별 조회 중앙값을 비교해요.”
Publisher declares: read-only yes · open-world no
1 input, 1 required
postsarrayrequired“내 영상 표”
- clip_title_check
“네이버 클립 게시 제목의 길이(40자)·띄어쓰기 없이 붙은 덩어리·상품명이나 브랜드가 들어갔는지, 컷 자막 길이(14자), 첫 컷이 결과 장면인지, AI 활용 표시를 켰는지 점검해요.”
Publisher declares: read-only yes · open-world no
7 inputs, 1 required
post_titlestringrequired“게시 제목”product_namestring“주인공 상품 이름(선택)”brandstring“브랜드(선택)”shotsarray“컷 순서대로(선택)”subtitlesarray“자막 줄만 있을 때(선택)”ai_generatedboolean“AI 로 만든 장면·목소리가 있으면 true”ai_label_onboolean“'AI 활용' 설정을 켰으면 true”
- clip_first_screen_check
“클립 0초 화면 글자(제목·첫 문장)가 결과부터 말하는지 낱말 모양으로 점검해요.”
Publisher declares: read-only yes · open-world no
4 inputs
textstring“첫 화면 글자(선택)”formatstring“영상 꼴(선택): before-after·전후·demo·시연·review·후기·pov”first_shotstring“첫 컷 표시(선택): result 면 결과 장면”scenestring“첫 프레임 장면 한 줄 설명(선택)”
- clip_ideas
“물건 이름과 결과·불편·대상을 넣으면 팩의 훅 유형(결과 먼저·문제 제시·대상 지목 등)으로 게시 제목 틀과 첫 컷·자막 요령을 만들어요.”
Publisher declares: read-only yes · open-world no
9 inputs, 1 required
itemstringrequired“물건을 부르는 짧은 말(예: 문풍지)”resultstring“쓰면 어떻게 되는지 한 줄(선택)”problemstring“불편한 상황 한 줄(선택)”targetstring“볼 사람(선택)”pricestring“가격(선택, 넣은 값만 써요)”categorystring“카테고리(선택)”product_namestring“판매 상품 이름(선택, 제목에 상품명이 들어갔는지 볼 때)”brandstring“브랜드(선택)”trendsarray“직접 모은 유행 제목 목록(선택, 최대 50개)”
- clip_upload_card
“게시 제목·훅·대본 앞 두 문장·해시태그로 광고 표시 첫 줄이 들어간 설명(300자 안)을 조립하고, 가상인물이 나오면 첫 줄을 가상인물 포함 · 광고로 바꿔요.”
Publisher declares: read-only yes · open-world no
11 inputs
post_titlestring“게시 제목(선택, 없으면 훅)”hookstring“훅 한 줄(선택)”scriptarray“대본 문장(앞 두 문장만 써요)”hashtagsarray“해시태그(선택, 최대 30개, # 없으면 붙여 줘요)”music_creditstring“배경음 출처(선택)”disclosure_linestring“광고 표시 문구(선택, 기본: 쇼핑 커넥트 제휴 수수료 안내)”categorystring“1차 카테고리(선택)”product_namestring“상품 태그로 찾을 상품 이름”product_urlstring“상품 주소(선택)”brandstring“브랜드(선택)”virtual_personboolean“AI 로 만든 사람이 나오면 true”
- clip_candidate_check
“직접 모은 상품 후보 목록(최대 200개)을 중복·이미 올린 상품·소재 종류(공식 상품 영상·본인 촬영)·화면 대조 확인·수수료율·판매량·확인 시각으로 점검하고 확인할 순서로 줄 세워요.”
Publisher declares: read-only yes · open-world no
2 inputs, 1 required
productsarrayrequired“상품 후보”published_product_idsarray“이미 올린 상품 번호(없으면 빈 목록)”
- clip_rhythm_check
“붙여 넣은 내 최근 게시 기록(최대 300줄)으로 오늘 올린 수·직전 간격·낮 시간대·최근 템플릿·글꼴·배경음·설명·해시태그 반복·제목 끝 틀·하루 고친 수를 한국 시간 기준으로 점검해요.”
Publisher declares: read-only yes · open-world no
15 inputs, 1 required
titlestringrequired“이번 영상 게시 제목”productstring“이번 상품 번호(선택)”descriptionstring“이번 설명(선택)”templatestring“템플릿 이름(선택)”fontstring“제목 글꼴(선택)”bgmstring“배경음(선택)”postsarray“최근 게시·수정 기록”edit_countnumber“이번에 한꺼번에 고칠 표지·제목 수(선택)”nowstring“기준 시각(선택, 시간대 포함 ISO.”templatesarray“돌려 쓸 템플릿 이름들(선택)”fontsarray“돌려 쓸 글꼴 이름들(선택)”daily_maxnumber“하루 상한(기본 5)”min_gap_minutesnumber“최소 간격 분(기본 120)”window_start_hournumber“낮 시간 시작 시(기본 9)”window_end_hournumber“낮 시간 끝 시(기본 21)”
- clip_ai_tone_check
“클립 설명·자막·대본에 남은 AI 상투 표현(“결론적으로”, “살펴볼게요” 등)·같은 어미 5문장 연속·3단 나열을 정규식으로 세어요.”
Publisher declares: read-only yes · open-world no
1 input, 1 required
textstringrequired“설명·자막·대본 글”
- clip_number_check
“클립 대본·설명의 숫자(가격·%·용량·날짜 등)가 근거 원문(상품 페이지 글 등)에 있는지 대조해요(2만원=20,000원처럼 같은 값은 같게 봐요).”
Publisher declares: read-only yes · open-world no
2 inputs, 2 required
scriptstringrequired“대본·설명 전체”source_textstringrequired“근거 원문”
- clip_metrics_review
“직접 옮겨 적은 클립 누적 지표(조회·좋아요·댓글·저장, 최대 300줄)를 한 모양으로 정리하고 빠진 시간대·중복 번호·관측 뒤 게시·잘못된 숫자를 알려요.”
Publisher declares: read-only yes · open-world no
4 inputs, 1 required
collection_statusstring“수집 상태”observed_atstring“관측 시각(시간대 포함 ISO)”source_kindstring“옮긴 방법”clipsarrayrequired“클립별 누적 값”
- clip_virtual_label_check
“AI 로 만든 사람이 나오는 클립의 설명 첫 줄에 가상인물 포함 표시를 붙인 글을 돌려주고, 영상 띠 글자·자리를 점검하고, 자막·대본에서 직접 써 본 것 같은 말(써 보니·내돈내산 등)을 찾아요.”
Publisher declares: read-only yes · open-world no
5 inputs
descriptionstring“설명·캡션(선택)”textsarray“자막·대본 줄(선택)”adboolean“광고(제휴)면 true(기본 true)”label_textstring“영상 띠 글자(선택)”positionstring“띠 자리(선택)”
- clip_warmup_plan
“새 네이버 클립 계정의 7일 예열 일정표를 줘요.”
Publisher declares: read-only yes · open-world no
2 inputs, 1 required
start_datestringrequired“예열 시작일(YYYY-MM-DD, 1일차)”todaystring“오늘 날짜(선택, 비우면 오늘 한국 날짜)”
Each quoted sentence is the first sentence of the publisher’s own description. The kind of tool and the “changes data” mark are our AI model’s reading of that description, not something we tested: two differently worded runs had to agree, otherwise no label is shown, and nobody has checked them by hand. A tool without the “changes data” mark is described as only reading, searching or calculating, or the two runs did not agree. No tool was called. Read the publisher’s full description before relying on it. “Publisher declares” lists the hints the server itself sends with the tool (MCP annotations: read-only, destructive, idempotent, open-world); they are the publisher's claims, not checked by us. Inputs are the parameters in the tool's own input schema: name, declared type, whether it is required, and the first sentence of its description. Read 2026-11-18.
How well are its tools described?
Features #4 and #5
How clearly this server's own tool descriptions say what a tool does, and how consistent its tool list is. The first part is an AI model's yes/no reading of each description; the second part is counted. We do not turn it into a grade.
Descriptions
AI reading of each description
No AI reading was available for this server's tools (the two runs did not agree, or the listing was not reviewed).
Counted from the listing
- Parameters with a description
- 99% of 219
- Tools with a description
- 100% of 67
- Typical description length
- 139 characters
The tool set
Counted from the listing
- Tools
- 67
- Size of the list
- about 11,460 tokens for an agent to load (characters ÷ 4)
- Naming
- 67 of 67 names use snake_case
AI reading: easy to mix up
No pair found.
The AI items cover 0 of 67 tools: for a tool where two differently worded runs disagreed, that item is left out. They were not checked by hand, and no tool was called. “Easy to mix up” means two tools whose names or descriptions overlap without saying how they differ; the AI found none, comparing tools within groups of 40. We do not rate whether the tool set is complete or whether side effects are spelled out, because our AI reading of those was not reliable enough.
How do I add it to my client?
Config from the registry entry
From the remote endpoint (Streamable HTTP)
We connected to this URL on 2026-11-18 (a read-only session: no tool was called).
Add to CursorAn install link in the format Cursor documents, holding the Cursor config below.
Claude Desktop or claude.ai
Settings → Connectors → Add custom connector, then paste: https://my.builderlog.net/connector
Cursor · .cursor/mcp.json in a project, or ~/.cursor/mcp.json
{
"mcpServers": {
"connector": {
"url": "https://my.builderlog.net/connector"
}
}
}VS Code · .vscode/mcp.json
{
"servers": {
"connector": {
"type": "http",
"url": "https://my.builderlog.net/connector"
}
}
}VS Code (command line) · Bash or zsh terminal (macOS, Linux)
code --add-mcp '{"name":"connector","type":"http","url":"https://my.builderlog.net/connector"}'Claude Code
claude mcp add --transport http connector https://my.builderlog.net/connector
Cline · cline_mcp_settings.json (Cline CLI: ~/.cline/data/settings/; in the editor: MCP Servers → Configure → Configure MCP Servers)
{
"mcpServers": {
"connector": {
"type": "streamableHttp",
"url": "https://my.builderlog.net/connector",
"disabled": false,
"autoApprove": []
}
}
}Gemini CLI · ~/.gemini/settings.json, or .gemini/settings.json in a project
{
"mcpServers": {
"connector": {
"httpUrl": "https://my.builderlog.net/connector"
}
}
}OpenAI Codex · ~/.codex/config.toml, or .codex/config.toml in a trusted project
[mcp_servers.connector] url = "https://my.builderlog.net/connector"
Zed · Zed settings file (command: zed: open settings file)
{
"context_servers": {
"connector": {
"url": "https://my.builderlog.net/connector"
}
}
}Try it in the MCP Inspector · runs on your machine, opens in your browser · Node 22.19+
npx @modelcontextprotocol/inspector@2.11.0 --server-url https://my.builderlog.net/connector --transport http
- The server runs on the operator's infrastructure; it may ask you to sign in when you first connect.
- Zed's docs we read on 2026-10-26 describe remote servers by URL and do not name the transport.
- The MCP Inspector lists the server's tools, resources and prompts; a tool you call there runs for real.
Built from the server's registry entry with each client's documented format (checked 2026-10-14; the Cursor link and the VS Code command 2026-10-19; the MCP Inspector command 2026-10-21; Cline, Gemini CLI, OpenAI Codex and Zed 2026-10-26). Values in < > are yours to fill in; this page never contains a key. Where the server needs a setting the entry does not declare, it can still fail to start.
What do the published files and outside lists say?
Read as text · nothing run · no tool called
Package files
- MCP SDK in the package files. Not read yet: added with the next daily run.
- Build workflow. Not read yet: added with the next daily run.
Outside lists
- CVE records (NVD). No CVE record in the NVD feeds we read links this server's repository. Source: read 2026-11-18. This product uses the NVD API but is not endorsed or certified by the NVD.
- GitHub advisories. No GitHub advisory names this entry's listed package. Source: read 2026-11-18. GitHub Advisory Database, CC BY 4.0
- Docker MCP catalogue. Not in the Docker MCP catalogue on 2026-11-18. Source: read 2026-11-18.
- Cline marketplace. Not in the Cline marketplace on 2026-11-18. Source: read 2026-11-18.
Own host
- security.txt. No security.txt at https://my.builderlog.net/.well-known/ (HTTP 404, 2026-11-18). No security.txt at https://builderlog.net/.well-known/ (HTTP 404, 2026-11-18). Source: my.builderlog.net/.well-known/security.txt · read 2026-11-18.
- A2A agent card. No A2A agent card at https://my.builderlog.net/.well-known/ (HTTP 404, 2026-11-18). No A2A agent card at https://builderlog.net/.well-known/ (HTTP 404, 2026-11-18). Source: my.builderlog.net/.well-known/agent-card.json · read 2026-11-18.
Read as text from published files and outside lists. Nothing was installed or run, and no tool was called. A fact, not a rating. How each fact is read
Does the registry listing match what we found?
Feature #6The registry checks an entry when it is published (each new version), and nothing re-checks it on a schedule. A difference below is about the listing, not a judgement of the publisher.
| Registry says | We found | Result | Source · date |
|---|---|---|---|
| Remote endpoint my.builderlog.net/connector | Session opened | matches | our test · 2026-11-18 |
| No credential declared as required | Opened a session without any credential | matches | our test · 2026-11-18 |
Tool list changes
Our reads compared · no tool calledHosted endpoint my.builderlog.net/connector
1 of 1 comparison between consecutive reads showed a change (2 reads, 2026-11-17 to 2026-11-18; versions 1.0.0 to 1.1.0).
Last change seen between our reads on 2026-11-17 (version 1.0.0) and 2026-11-18 (version 1.1.0).
Added (46) (25 shown):
clip_ai_tone_checkclip_candidate_checkclip_first_screen_checkclip_ideasclip_metrics_reviewclip_number_checkclip_rhythm_checkclip_title_checkclip_upload_cardclip_virtual_label_checkclip_warmup_planreels_affiliate_label_checkreels_dm_linkreels_first_second_fixreels_hook_checkreels_insights_auditreels_number_checkreels_script_tone_checkreels_shortform_plan_checkreels_story_plan_checkreels_subtitle_checkreels_warmup_planshorts_disclosure_checkshorts_highlight_pickershorts_hook_ab_checkand 21 more.
Compared from the tool lists our read-only connection recorded, separately for each hosted endpoint and each package: each tool's name, title, description, input schema and annotations (the order of keys and of tools is ignored). We see a list only when we read it: a change is shown between the two reads where we first saw it, and anything after 2026-11-18 is not known yet. No tool was called. How it is compared
Choosing
Record checks
Public records · not a safety rating1 of 2 record checks met · 7 do not apply
- Not ranked by downloads: a remote server publishes no download figure
- Not ranked by stars: no public GitHub repository
- MetRegistry entry is active and says how to run itActive, with a package or a remote address.
- Not metSource repository link opensThe registry entry gives no repository link.What changes this check: This check opens the repository link in the registry entry. GitHub's documentation describes changing a repository's visibility in its Settings, under Danger Zone, Change visibility. GitHub: setting repository visibility
- Does not applyRepository is not archivedNo public GitHub repository to read.
- Does not applyCode pushed to the repository in the 90 days before our checkNo public GitHub repository to read.
- Does not applyRepository publishes a security policy (SECURITY.md)No public GitHub repository to read.
- Does not applyPackage names its licence with a standard (SPDX) identifierRemote server: it ships no package.
- Does not applyThe version the registry lists can be installed and is not withdrawnRemote server: it ships no package.
- Does not applynpm package carries build provenance (attestation)Remote server: it ships no package.
- Does not applyNo known critical or high advisory in the package or its dependenciesRemote server: it ships no package.
Read from public records only: the registry entry, npm/PyPI, GitHub and advisory databases, checked 2026-11-18. No tool was called. Only “met” and “not met” are counted, so the total differs between servers; a check that does not apply or that we could not run is listed, never counted against it. It is not a safety rating, and the same rules apply to every server. How each check works · Leaderboards · How we stay neutral
Common questions about net.builderlog/connector
Answered from the data aboveWho publishes net.builderlog/connector?
The registry ties the namespace net.builderlog to the domain builderlog.net; only its owner can publish under it. These are facts from the registry and GitHub, not a rating.
Does net.builderlog/connector need an API key or sign-in?
It opened a session without any credential on 2026-11-18. The registry entry declares no required credential; no declaration is not a guarantee.
Has net.builderlog/connector been security tested?
Partly. 3 of the 15 checks that apply to it were exercised. We connected and read what the server declares, but did not call its tools: ProtocolProbe calls no server's tools for anything it publishes, except for a server whose operator has claimed it and given permission (that server's page says so). This is our choice, not a block by the server. ProtocolProbe publishes no security verdict for a named server.
Found this page useful?
Anonymous · no sign-inA quick, anonymous reaction — no account, no email. One per kind from your browser. The tally updates when the page is next refreshed, and it is only a rough count, never a safety rating or a measured number of people.
Compare with another server
Side by side: registry entry, our read-only session, the tools and the 18 classification fields. Same values as each page; no score.
Security testing
What did we test, and what did we leave out?
18 checks · features #1, #2
Not probed (no operator permission)
We connected and read what the server declares, but did not call its tools: ProtocolProbe calls no server's tools for anything it publishes, except for a server whose operator has claimed it and given permission (that server's page says so). This is our choice, not a block by the server. No security score is given; a check we did not run is never counted as passed.
- Inventory: exercised
- Hidden instructions: exercised
- Real execution: not run · our policy
- Secret leak: not run · nothing to check it against
- Internal addresses: not run · our policy
- Unconfirmed changes: not run · our policy
- Bad input: not run · our policy
- Model requests: not run · nothing to check it against
- Sensitive questions: not run · nothing to check it against
- Folder boundary: not run · our policy
- Log leaks: not run · nothing to check it against
- Hidden content: not run · nothing to check it against
- Fake assistant turns: not applicable
- Token passthrough: not applicable
- Token audience: not applicable
- Sign-in redirect: not run · our policy
- Consent handling: not testable from outside
- Sign-in metadata: exercised
3 exercised12 not run (reason given)3 not applicable
Each check ends in exactly one state: exercised, not run (with the reason), or not applicable (with the reason). 3 of the 15 checks that apply to it were exercised. We do not publish security-check outcomes for named servers. These 18 checks are separate from the record checks at the top of this page, which read public records only.
- 1Inventory
tool-listReads the declared tools, resources and prompts.exercised - 2Hidden instructions
description-poisoningLooks for hidden instructions in tool descriptions.exercised - 18Sign-in metadata
oauth-url-schemeChecks the published sign-in metadata for unsafe URLs.exercised
- 3Real execution
real-executionCalls a tool and checks what really happens.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes, except for a server whose operator has claimed it and given permission (that server's page says so); an operator can run this check on their own server with our self-test command.not run · our policy - 4Secret leak
canary-leakPlants a fake secret and checks whether it leaks.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against - 5Internal addresses
ssrfChecks whether a tool can be steered to internal addresses.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes, except for a server whose operator has claimed it and given permission (that server's page says so); an operator can run this check on their own server with our self-test command.not run · our policy - 6Unconfirmed changes
write-without-confirmationChecks whether tools that change data act without asking.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes, except for a server whose operator has claimed it and given permission (that server's page says so); an operator can run this check on their own server with our self-test command.not run · our policy - 7Bad input
error-handlingSends bad input and watches how the server answers.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes, except for a server whose operator has claimed it and given permission (that server's page says so); an operator can run this check on their own server with our self-test command.not run · our policy - 8Model requests
samplingChecks whether the server asks the client's model to act for it.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against - 9Sensitive questions
elicitation-sensitive-dataChecks whether the server asks users for sensitive data.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against - 10Folder boundary
root-boundaryChecks whether the server reaches outside the folders it was given.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes, except for a server whose operator has claimed it and given permission (that server's page says so); an operator can run this check on their own server with our self-test command.not run · our policy - 11Log leaks
logging-side-channelChecks whether log messages carry data they should not.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against - 12Hidden content
audience-hidingChecks resources that hide content from the user.This check needs content the server returns, and nothing was read or called.not run · nothing to check it against - 16Sign-in redirect
open-redirectChecks the sign-in redirect for abuse.Testing the sign-in redirect means sending probes to the operator's sign-in service, which we do not do.not run · our policy - 17Consent handling
confused-deputyChecks consent handling when one service acts for another.Depends on the operator's own consent screen, which differs per server and cannot be tested from outside.not testable from outside
- 13Fake assistant turns
fake-assistant-turnChecks prompts that pose as the assistant's own words.The server exposes no prompts.not applicable - 14Token passthrough
token-passthroughChecks whether the server forwards a user's token to other services.The server opened a session without sign-in, so there is no token flow to check.not applicable - 15Token audience
token-audience-validationChecks whether tokens meant for another service are accepted.The server opened a session without sign-in, so there is no token flow to check.not applicable
Source: our own test, 2026-11-18, mcp-runtime-engine@0.1.0. Which checks count and why follows our published scoring model.
What happened during the test?
Feature #8
The steps in order, as the test record holds them.
- 0 msStarted a read-only session with the server's remote endpoint
- 378 msConnected after 0 redirects. No credential was sent or needed.
- Read the inventory: 67 tools, 0 resources, 0 prompts.
- 1,396 msFinished: 3 checks exercised.
Reference
How is it classified?
18 fields
One value per field, each with its source. Fields written by AI models are marked. A field with no value says why.
“Not stated” means the source did not state it; “does not apply” means it does not apply to this kind of server; “our limit” means our own lookup failed. A linked value opens the directory filtered to the same value.
Cite or correct this page
Sources and corrections
Suggested citation
ProtocolProbe. “net.builderlog/connector: MCP server record.” Data checked 2026-11-18. https://protocolprobe.com/mcp/servers/net.builderlog/connector
Figures are valid for the date shown. Our facts on this page are CC BY 4.0: reuse them with a link and the check date. Quoted text (the publisher’s descriptions, website quotes, tool names) is not ours to license.
As JSON: this record in the API · API documentation.
Badge for your README
[](https://protocolprobe.com/mcp/servers/net.builderlog/connector)
It shows this server's record-check count: facts from public records, no tool called. It is not a security rating or a pass. It links here and updates after each data reload.
Something wrong, or is this yours?
If a fact here is wrong, tell us and we will re-check it. If you operate this server, you can run our checks on it yourself with the free self-test command; we call no server’s tools ourselves for anything shown here, except for a server whose operator has claimed it and given permission (that server's page says so).
Write to hello@protocolprobe.com · corrections log · methodology