MisarReach MCP Server
개요
제작자가 쓴 설명(영어 원문)
Find leads, enrich and score them, run multi-channel outreach, and manage the sales pipeline — from…
PopNx MCP의 세 기둥
이 세 가지는 절대 하나의 점수로 합치지 않아요. 의견, 측정, 인기는 서로 다른 것이니까요.
- 사용자 의견i아직 리뷰가 없어요리뷰는 다음 단계에서 계정 기능과 함께 열려요
- 우리의 기본 점검i3개 중 3개 통과공개된 정보로 점검했으며, 코드는 아직 스캔하지 않았어요
- 사용 정도i아주 새로움↓ 92/주 · ★ –
할 수 있는 일
이 서버는 아직 쉬운 말로 된 요약을 쓰지 못했어요. 아래는 레지스트리에서 읽어 온 사실이에요.
- 연결 방식: 컴퓨터 또는 클라우드
- 전송 방식: stdio, Streamable HTTP
- 카테고리: 마케팅 및 소셜 미디어
- 입력해야 할 값: MISARREACH_API_KEY, Authorization
설치
쓰고 있는 AI 앱을 고른 다음 설정을 복사하세요.
설치하기 전에
- 기본 점검: 3개 중 3개 통과
- 제작자의 서버에서 실행돼요. 내가 요청한 내용은 제작자의 서버를 거쳐요.
- 할 수 있는 일 31가지(도구) list_leads, search_leads, get_search_job_status, submit_lead_feedback …
- 직접 입력할 값:
MISARREACH_API_KEY,MISARREACH_BASE_URL,Authorization
비밀로 표시된 값은 내 계정의 열쇠예요. 절대 다른 사람과 공유하거나 채팅에 붙여 넣지 마세요.
필요한 것
어떤 앱을 쓰세요?
위에서 앱을 고르세요. 기억해 두었다가 다음부터는 버튼에 “…에 설치”라고 표시해요.
이 주소는 요청 header에 키가 필요한데, 커넥터 추가 메뉴에서는 넣을 수 없어요. 대신 Claude Code, Cursor, VS Code를 쓰세요.
또는 내 컴퓨터에서 실행하기
Claude Desktop → Settings → Developer → Edit Config를 열고 claude_desktop_config.json에 이 내용을 붙여 넣으세요
{
"mcpServers": {
"misarreach": {
"command": "npx",
"args": [
"-y",
"@misarreach/mcp"
],
"env": {
"MISARREACH_API_KEY": "your-value",
"MISARREACH_BASE_URL": "your-value"
}
}
}
}터미널에서 이 명령어를 실행하세요
claude mcp add --transport http misarreach https://api.misar.io/reach/mcp --header 'Authorization: your-value'또는 내 컴퓨터에서 실행하기
claude mcp add misarreach --env MISARREACH_API_KEY=your-value --env MISARREACH_BASE_URL=your-value -- npx -y @misarreach/mcp실행하기 전에 빈 값을 채워 주세요.
또는 설정을 직접 복사하기
프로젝트의 .cursor/mcp.json 또는 ~/.cursor/mcp.json에 붙여 넣으세요
{
"mcpServers": {
"misarreach": {
"url": "https://api.misar.io/reach/mcp",
"headers": {
"Authorization": "your-value"
}
}
}
}또는 내 컴퓨터에서 실행하기
또는 설정을 직접 복사하기
프로젝트의 .cursor/mcp.json 또는 ~/.cursor/mcp.json에 붙여 넣으세요
{
"mcpServers": {
"misarreach": {
"command": "npx",
"args": [
"-y",
"@misarreach/mcp"
],
"env": {
"MISARREACH_API_KEY": "your-value",
"MISARREACH_BASE_URL": "your-value"
}
}
}
}브라우저가 앱을 열지 물어본 다음, 앱이 설정을 보여 주고 확인을 요청해요. 키 값은 비워 두니 직접 입력하세요.
또는 설정을 직접 복사하기
프로젝트의 .vscode/mcp.json에 붙여 넣으세요
{
"servers": {
"misarreach": {
"type": "http",
"url": "https://api.misar.io/reach/mcp",
"headers": {
"Authorization": "your-value"
}
}
}
}또는 내 컴퓨터에서 실행하기
또는 설정을 직접 복사하기
프로젝트의 .vscode/mcp.json에 붙여 넣으세요
{
"servers": {
"misarreach": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@misarreach/mcp"
],
"env": {
"MISARREACH_API_KEY": "your-value",
"MISARREACH_BASE_URL": "your-value"
}
}
}
}브라우저가 앱을 열지 물어본 다음, 앱이 설정을 보여 주고 확인을 요청해요. 키 값은 비워 두니 직접 입력하세요.
이 주소는 요청 header에 키가 필요한데, 커넥터 추가 메뉴에서는 넣을 수 없어요. 대신 Claude Code, Cursor, VS Code를 쓰세요.
선택한 앱은 이 기기의 쿠키에만 저장돼요. 계정은 필요 없어요.
직접 입력할 값
- Your MisarReach API key (mrk_…). Create one at https://reach.misar.io/settings/api-keys, or omit it and run the "login" tool to authenticate via browser.
MISARREACH_BASE_URLenvOverride the API base URL. Only needed for self-hosted instances.Authorization비밀 필수 HTTP headerMisarReach API key. Format: Bearer mrk_… — create one at https://reach.misar.io/settings/api-keys
이 설정은 제작자의 레지스트리 정보로 만들었어요. README와 다르면 README를 따르세요.
할 수 있는 일
도구 이름과 설명은 서버가 2026년 11월 7일에 알려 준 그대로예요. 우리가 아니라 제작자가 쓴 글이고, 일반 텍스트로만 보여 드려요.
list_leadsList leads already saved to the account, newest first, with paging and search. Use this to work with leads you already have. It does NOT find new ones — that is search_leads, which starts a job and costs credits. Narrow to one search job with job_id when you want just that job's
search_leadsStart an AI lead-search job and return its jobId immediately. This is ASYNCHRONOUS: results are not in the response. Poll get_search_job_status with the jobId until it reports completion, then read the leads with list_leads filtered by that job_id. Use it to find NEW leads; use l
get_search_job_statusPoll one lead-search job for its progress and results. This is the companion to search_leads: call it repeatedly with the jobId you were given until the job reports it has finished. Leave a few seconds between polls — searches take a while, and polling harder does not make them f
submit_lead_feedbackRecord whether an AI-generated outreach message for a lead was good or bad, as training signal for future generations. Use it when the user judges a drafted message — it improves later output rather than changing anything now. It does not edit, resend, or delete the message, and
discover_companiesFind COMPANIES matching firmographic criteria, optionally pulling contact emails for each. This is company-level discovery — reach for it when the user is targeting organisations by industry, location, headcount or tech stack. When they want named people, use search_leads. Filter
enrich_leadFill in a saved lead's missing person and company detail — seniority, department, LinkedIn, phone, company size, industry. Use it on one lead at a time, after list_leads has given you its id, and typically before writing outreach that needs context. Check the lead first: enrichin
verify_emailsCheck whether email addresses are deliverable, one or up to 20 at a time. Run this before a send to protect sender reputation — bouncing a campaign off dead addresses is what gets a domain blocked. Pass either `email` for one or `emails` for a batch, not both. CONSUMES VERIFICATI
score_leadsQueue AI qualification scoring for leads — either every unscored lead in a search job, or a specific set of ids. Pass jobId OR leadIds, not both. This runs in the BACKGROUND: it returns a count immediately and the scores appear on the leads afterwards, so re-read them with list_l
list_lead_listsList the managed lead lists this account has created or synced. Use it to find a listId before sync_lead_list, or to check whether a list already exists before create_lead_list makes a duplicate. These lists are held apart from the saved leads, which are separate from the leads s
create_lead_listCreate a new, empty managed lead list. Creating the list does not put anything in it, and it does not import anything locally — sync_lead_list does that. Call list_lead_lists first: each call creates a NEW list and nothing deduplicates by name. Requires an API key. Costs no credi
sync_lead_listImport a managed lead list into local lead records so the rest of these tools can work with it. Run it after create_lead_list, or on any existing list from list_lead_lists, to pull its contacts in. Until a list is synced its contacts are invisible to list_leads, enrich_lead and s
preview_messageDraft a sample AI-personalised outreach message for a named person, to show what the agent would say. This is a PREVIEW: nothing is sent, saved, or attached to a lead or campaign. Use it to check tone before committing to a sequence. The person does not need to exist as a lead —
send_to_campaignAdd saved leads to a campaign's contact list in bulk, up to 500 at a time. This is how leads enter an outreach sequence, so treat it as consequential: once they are on a running campaign's list they can start receiving messages. It does NOT send anything by itself and does not st
list_dealsList deals as a flat, paged array, optionally filtered by status, with revenue totals alongside. Use this when you want deals as data — to count them, filter one status, or page through many. For the board view with deals grouped into stages, use get_pipeline instead; the two ret
create_dealOpen a new deal against a lead's email address. Use it when a conversation turns into a real opportunity worth tracking. Each call creates a NEW deal — it does not check for an existing one on the same email, so list_deals first if you might be duplicating. To change a deal that
update_dealChange a deal's status, value, or notes. Only the fields you pass are altered. For moving a deal along the pipeline board prefer move_deal_stage, which is the same operation expressed in stage terms; use this one for value and notes. Setting status to 'closed' or 'lost' marks the
get_pipelineGet the sales pipeline as a board: deals grouped by stage, with revenue totals. Use this for 'how does the pipeline look' questions and stage-by-stage review. It is the board view of the same deals list_deals returns flat — reach for that one when you need filtering or paging, si
move_deal_stageMove one deal to a different pipeline stage — the equivalent of dragging its card on the board. This is the tool for pipeline progression; update_deal is for value and notes. Moving to 'closed' or 'lost' resolves the deal and removes it from open pipeline revenue, which changes r
start_autopilotStart an autonomous outreach run: give the agent a goal and it finds, contacts and follows up with leads on its own. This is the most consequential tool on this server. It is FIRE-AND-FORGET and it SENDS REAL MESSAGES TO REAL PEOPLE without returning for approval, so only start a
list_autopilot_runsList past and running autopilot runs with their status and result summaries. Use it to review what has already been run — and to check for a run already in flight before start_autopilot launches a second one against the same goal. For detail on one run, use get_autopilot_status.
get_autopilot_statusGet the current progress and results of one autopilot run. This is how you follow a run started by start_autopilot: call it with the runId, leaving time between polls. Reading status does not pause, stop, or alter the run in any way — it keeps going regardless, and there is no to
get_channels_statusReport the configuration, connection state and delivery stats for every outreach channel — WhatsApp, SMS and push. Check this before relying on a channel: a disabled or unconfigured one silently delivers nothing. It is also the natural first step before update_channel, so you kno
update_channelTurn one outreach channel on or off — WhatsApp, SMS or push. This changes how the account actually delivers messages, so it affects live campaigns and autopilot runs, not just future ones. DISABLING a channel silently stops delivery over it; enabling one that has no credentials c
get_sales_agent_configFetch the AI sales agent's current settings: whether it is enabled, its booking link, offer price, reply limits and confidence threshold. Read this before update_sales_agent_config so you change one field without clobbering the rest, and to check whether the agent is enabled at a
update_sales_agent_configChange the AI sales agent's settings — enable or disable it, set the booking link, offer price, reply limits and confidence threshold. These settings govern an agent that replies to real prospects, so treat them as live: ENABLING it lets it start responding on its own, the confid
get_sales_agent_actionsGet what the AI sales agent has done today, with summary stats — actions taken, deals created, replies sent. This is the audit trail: use it to see what the agent did on the account's behalf, and to sanity-check its behaviour after enabling it. Covers TODAY only, so it is not the
process_sales_agentRun the sales-agent pipeline over one conversation: decide the next action and carry it out. This ACTS on a real conversation — depending on what it decides, it can reply to the prospect, create a deal, or book a meeting. It is not a dry run and there is no preview, so call it on
search_verified_leadsFind people or businesses matching a plain-language description and return only leads with a real way to reach them (email, phone or LinkedIn), each read from a real record — never generated. Waits for the search to finish (up to wait_seconds) and returns the leads with each emai
reveal_company_contactsRead a company's own website now and return what it publishes: contact emails, a phone number, its social profiles and its detected tech stack. robots.txt is obeyed. One enrichment credit, charged only when the site publishes a way to reach the company, and at most once per compa
company_email_formatThe email address format a company uses (e.g. {first}.{last}@acme.com), learned only from addresses that were verified deliverable, with each pattern's share and a confidence level. Free. Returns 'not published' when there is not yet enough verified evidence for the domain.
verify_emailCheck whether one email address can receive mail. Returns valid, invalid, accept_all (a catch-all domain: the server accepts every address, so this one cannot be confirmed — do not treat it as valid), webmail, disposable or unknown. Consumes one verification credit. The verdict i
기본 점검i
누구나 볼 수 있는 정보를 점검했고, 코드는 읽지 않았어요. 해당하지 않는 항목은 개수에서 뺐어요. · 2026년 11월 8일 점검
- ✓ 통과
제작자와 저장소 일치
레지스트리 이름이 GitHub 계정 Misar-AI 기준으로 확인되었고, 이 계정이 저장소를 소유하고 있어요
- … 아직 점검 안 함
계속 관리되고 있음
아직 GitHub에서 이 저장소를 읽어 오지 않았어요
- … 아직 점검 안 함
라이선스 있음
아직 GitHub에서 이 저장소를 읽어 오지 않았어요
- ✓ 통과
엔드포인트 응답
704ms 만에 응답(HTTP 200)
- – 해당 없음
OAuth로 로그인
로그인 필요 없음
- ✓ 통과
도구 설명에 숨겨진 지시 없음
도구 설명 31개를 읽었고, AI에게 보내는 숨겨진 지시는 없었어요
마케팅 및 소셜 미디어 카테고리의 다른 서버와 비교i
- 이 카테고리의 다른 서버 3592개 중 0%보다 스타가 많아요
- 이 카테고리의 다른 서버 3592개 중 59%보다 최근에 레지스트리에 공개됐어요
- 기본 점검 결과가 이 카테고리의 다른 서버 3592개 중 100%와 같거나 더 좋아요
레지스트리에서 이 카테고리의 활성 서버 전체와 비교했어요. 스타는 게시자가 저장소를 소유한 경우에만 세요.
자주 묻는 질문
MisarReach MCP Server, 안전한가요?
해당하는 기본 점검 3개 중 3개를 통과했어요. 코드는 읽지 않았어요. 키나 토큰을 넣기 전에 서버가 어떤 권한을 요구하는지 확인하고, 꼭 필요한 권한만 있는 키를 쓰세요.
어떤 키나 코드가 필요한가요?
입력해야 할 값: MISARREACH_API_KEY, Authorization
내 컴퓨터에서 실행되나요, 클라우드에서 실행되나요?
둘 다 가능해요. 내 컴퓨터에 설치해도 되고, 클라우드 버전에 연결해도 돼요.
아직 관리되고 있나요?
GitHub 저장소는 마지막으로 – 변경됐고, 최신 버전(5.2.1)은 22일 전 레지스트리에 올라왔어요.
어떤 앱에서 쓸 수 있나요?
Claude Desktop, Claude Code, Cursor, VS Code처럼 MCP를 지원하는 앱에서 쓸 수 있어요. URL로 연결되기 때문에, 원격 MCP 서버를 지원하는 앱(예: 개발자 모드의 ChatGPT)에서도 쓸 수 있어요.
대신 쓸 수 있는 건 뭐가 있나요?
같은 카테고리에는: MCP YouTube Transcript, Google Analytics MCP, BibiGPT YouTube Video Summarizer
대안
같은 카테고리에서 다른 제작자가 만든 서버예요. 스타 순으로 정렬했어요.
카드 보는 법:↓ 주간 다운로드i★ GitHub 스타i세 기둥: 리뷰 · 점검 · 사용 정도i업데이트 = 최신 버전을 레지스트리에 공개한 날i
Google Analytics MCP
GA4 MCP server for AI agents: schema discovery, server-side aggregation, analysis-ready defaults.
BibiGPT YouTube Video Summarizer
AI video summarizer: summarize and transcribe YouTube, Bilibili, TikTok and podcast videos.
제작자의 README
README 열기
제작자의 저장소에서 쓰인 그대로 가져왔어요. PopNx MCP가 검토하거나 보증한 내용이 아니에요. HTML, 이미지, 스크립트는 제거했어요. 링크를 누르면 이 사이트를 벗어나요.
MisarReach MCP Server
Find leads, enrich and score them, run multi-channel outreach, and manage the sales pipeline — from any AI assistant.
31 tools · 5 prompts · 4 resources · 4 agent skills
Works with Claude (Desktop, Code, and web), Cursor, VS Code, Windsurf, Cline, Zed, Gemini CLI, ChatGPT, and any other MCP-compatible client — over stdio or Streamable HTTP.
Install
Smithery (recommended)
npx -y @smithery/cli install misar/misarreach-mcp --client claude
Claude Code
claude mcp add misarreach -- npx -y @misarreach/mcp@latest
Manual (any client)
{
"mcpServers": { "misarreach": { "command": "npx", "args": ["-y", "@misarreach/mcp@latest"], "env": { "MISARREACH_API_KEY": "mrk_your_key_here" } } } }
Ready-made configs for every client live in connectors/.
Remote (no install)
{
"mcpServers": { "misarreach": { "type": "streamable-http", "url": "https://api.misar.io/reach/mcp", "headers": { "Authorization": "Bearer mrk_your_key_here" } } } }
Authentication
Two options — no copy-paste needed for the first:
- Browser login. Start the server with no key and run the
logintool. It opens the MisarReach consent screen, you review the requested permissions, and the key is delivered straight back and saved to~/.misarreach/config.json. - API key. Create one at https://reach.misar.io/settings/api-keys and set
MISARREACH_API_KEY.
Self-hosted instances: set MISARREACH_BASE_URL.
Tools
| Tool | Description |
|---|---|
list_leads | List leads already saved to the account, newest first, with paging and search. |
search_leads | Start an AI lead-search job and return its jobId immediately. |
get_search_job_status | Poll one lead-search job for its progress and results. |
submit_lead_feedback | Record whether an AI-generated outreach message for a lead was good or bad, as training signal for future generations. |
discover_companies | Find COMPANIES matching firmographic criteria, optionally pulling contact emails for each. |
enrich_lead | Fill in a saved lead's missing person and company detail — seniority, department, LinkedIn, phone, company size, industry. |
verify_emails | Check whether email addresses are deliverable, one or up to 20 at a time. |
score_leads | Queue AI qualification scoring for leads — either every unscored lead in a search job, or a specific set of ids. |
list_lead_lists | List the managed lead lists this account has created or synced. |
create_lead_list | Create a new, empty managed lead list. |
sync_lead_list | Import a managed lead list into local lead records so the rest of these tools can work with it. |
preview_message | Draft a sample AI-personalised outreach message for a named person, to show what the agent would say. |
send_to_campaign | Add saved leads to a campaign's contact list in bulk, up to 500 at a time. |
list_deals | List deals as a flat, paged array, optionally filtered by status, with revenue totals alongside. |
create_deal | Open a new deal against a lead's email address. |
update_deal | Change a deal's status, value, or notes. |
get_pipeline | Get the sales pipeline as a board: deals grouped by stage, with revenue totals. |
move_deal_stage | Move one deal to a different pipeline stage — the equivalent of dragging its card on the board. |
start_autopilot | Start an autonomous outreach run: give the agent a goal and it finds, contacts and follows up with leads on its own. |
list_autopilot_runs | List past and running autopilot runs with their status and result summaries. |
get_autopilot_status | Get the current progress and results of one autopilot run. |
get_channels_status | Report the configuration, connection state and delivery stats for every outreach channel — WhatsApp, SMS and push. |
update_channel | Turn one outreach channel on or off — WhatsApp, SMS or push. |
get_sales_agent_config | Fetch the AI sales agent's current settings: whether it is enabled, its booking link, offer price, reply limits and confidence threshold. |
update_sales_agent_config | Change the AI sales agent's settings — enable or disable it, set the booking link, offer price, reply limits and confidence threshold. |
get_sales_agent_actions | Get what the AI sales agent has done today, with summary stats — actions taken, deals created, replies sent. |
process_sales_agent | Run the sales-agent pipeline over one conversation: decide the next action and carry it out. |
search_verified_leads | Find people or businesses matching a plain-language description and return only leads with a real way to reach them (email, phone or LinkedIn), each read from a real record — never generated. |
reveal_company_contacts | Read a company's own website now and return what it publishes: contact emails, a phone number, its social profiles and its detected tech stack. |
company_email_format | The email address format a company uses (e.g. |
verify_email | Check whether one email address can receive mail. |
Prompts
Reusable workflows your client exposes as slash-commands.
| Prompt | Description |
|---|---|
build_lead_list | Find, enrich, verify and score a target lead list before any outreach. |
outreach_sequence | Design and preview a multi-channel sequence, sending only after approval. |
pipeline_review | Review deal pipeline health and recommend the next actions. |
autopilot_audit | Check what autopilot has been doing and whether it should keep running. |
sales_agent_tuning | Review the AI sales agent's configuration and recent actions. |
Resources
Read-only context an agent can attach without spending a tool call.
| URI | Description |
|---|---|
misarreach://channels | Which outreach channels are connected and healthy. |
misarreach://lead-lists | Your saved lead lists with sizes, so a campaign targets a real audience.. |
misarreach://pipeline | Current pipeline by stage — the baseline for any performance question.. |
misarreach://autopilot/status | Whether autopilot is running, and its current sending posture.. |
Agent skills
Bundled in skills/ — guidance an agent loads when a task matches.
| Skill | Use when |
|---|---|
audit-autopilot-and-agent | Check what MisarReach autopilot and the AI sales agent have been doing, and whether they should keep running. Use when asked to review automation, autopilot, or agent behaviour. |
build-and-qualify-a-lead-list | Find companies matching an ICP, enrich and verify the contacts, score them, and save a qualified list. Use when asked to find leads, build a prospect list, or research a target market in MisarReach. |
review-the-sales-pipeline | Report deal pipeline health and recommend next actions. Use when asked about deals, pipeline, forecast, or sales performance in MisarReach. |
run-an-outreach-sequence | Design, preview and send a multi-channel outreach sequence. Use when asked to run a campaign, start outreach, or message a lead list in MisarReach. |
Safety
Destructive and irreversible actions are annotated (destructiveHint) so clients can prompt before running them. The skills instruct agents to confirm before anything that sends mail, publishes content, or is otherwise visible to other people.
Discovery (initialize, tools/list, prompts/list, resources/list) never requires credentials, so registries can index the server without one. Every action does.
Links
- Website — https://www.misarreach.com
- App — https://reach.misar.io
- Documentation — https://docs.misar.io/reach/mcp
- Smithery — https://smithery.ai/server/misar/misarreach-mcp
- npm — https://www.npmjs.com/package/@misarreach/mcp
- Source — https://github.com/Misar-AI/misarreach-mcp
MIT © Misar.AI