Prosyo MCP Server

io.github.ShubhamTutsv1.0.1更新於 Oct 4, 2026

Zero-config Prosyo MCP for LinkedIn, cold email, and inbox. No API key.

已驗證Streamable HTTP可網頁執行Business & CommerceProductivity & WorkflowCommunication & Collaboration

概覽

AI 產生的概覽

將 AI 助理連接到託管的 B2B 外聯工作區，讓它能讀取活動、研究潛在客戶，並草擬或寄送 LinkedIn 與電子郵件外聯。

功能
Prosyo 是託管型遠端 MCP 伺服器，串接涵蓋 LinkedIn、冷郵件與統一收件匣的多管道 B2B 外聯引擎。它提供約 30 個工具，分為工作區概觀與權益、活動（列出、預覽、建立、啟動、暫停、恢復）、潛在客戶與資料補全（搜尋、清單、研究、加入活動）、收件匣（列出對話、草擬與寄送回覆）、意向情報（訊號、劇本、審核佇列、解鎖潛在客戶）以及執行與安全。讀取類工具立即回傳資料；會寄送、啟動、加入、解鎖、研究或消耗額度的寫入類工具會先準備動作，只有在對話中明確同意後呼叫 confirm_action 才會執行。
適用情境
當助理需要在既有的 Prosyo 外聯工作區內工作時適用：檢視活動狀態、研究潛在客戶並草擬個人化內容、處理收件匣，或依據購買訊號線索採取行動。它適合已使用 Prosyo 進行 LinkedIn 與冷郵件外聯的團隊，而非一般用途。
執行需求
需要遠端 Streamable HTTP 端點 金鑰或驗證標頭。用戶端設定就是該 URL。首次連線時，Prosyo 會在瀏覽器開啟授權畫面以選擇工作區，只需確認一次。工具要回傳資料，需要具備方案、席次與額度的 Prosyo 帳號與工作區。
安裝前請注意
此伺服器操作的是真實外聯工作區：工具可以啟動活動、將潛在客戶加入活動、寄送 LinkedIn 或電子郵件回覆、解鎖線索並核准審核佇列中的人員。多項動作依人數消耗額度（研究、資料補全、解鎖、審核核准），花費取決於方案餘額。讀取立即執行，但寄送、啟動、加入、解鎖、研究與消費會在對話中確認後經 confirm_action 才執行；pause_campaign 與 save_intent_leads_to_list 立即生效。連線透過一次性瀏覽器授權畫面完成，而非在設定中放置金鑰。

安裝

在 SourceWeft 中

  1. 開啟 儀表板中的 Prosyo MCP Server，將其新增到工作區。
  2. 為需要使用其工具的對話啟用該服務。

Web executable，透過 Streamable HTTP。 遠端服務在工作區中設定後即可從網頁執行環境執行。

其他 MCP 客戶端

把它新增到你客戶端的 mcpServers 設定中。

{
  "mcpServers": {
    "prosyo": {
      "type": "http",
      "url": "https://app.prosyo.com/ai"
    }
  }
}

README

[Prosyo]

[License: MIT] [MCP Protocol Standard] [Zero-Config / No Auth Required] [Smithery Verified] [Official MCP Registry] [GitHub Pages guide] [Status: Active]

Prosyo MCP Server

Instant, zero-config Model Context Protocol server connecting AI agents (Claude, Cursor, Windsurf) directly to Prosyo's multichannel B2B outbound engine.

One URL. No API key. No authentication headers. No local install.
Paste https://app.prosyo.com/ai and the agent can read campaigns, research prospects, and work the inbox.

Open the live guide  ·  Prosyo  ·  Docs  ·  Smithery  ·  Registry  ·  Support

Quickstart  ·  Architecture  ·  30 tools  ·  Official registry  ·  Links

1-Minute Quickstart

The hosted endpoint is plug-and-play. There is no API key to create, no developer token to sign up for, and no authentication header to add. The client config is the URL: https://app.prosyo.com/ai.

The first time Claude or Cursor connects, Prosyo opens an allow screen in the browser so the workspace can be chosen. That confirm is once. It stays out of the config file.

The same steps are on the live guide, with a card for each client.

Claude Desktop

Add this to claude_desktop_config.json. Full walkthrough: Connect Prosyo to Claude.

json
{  "mcpServers": {    "prosyo": {      "url": "https://app.prosyo.com/ai"    }  }}

Restart Claude Desktop. Turn Prosyo on in the chat and ask.

Cursor

Add this to .cursor/mcp.json in the project, or to the global Cursor MCP config.

json
{  "mcpServers": {    "prosyo": {      "url": "https://app.prosyo.com/ai"    }  }}

Reload MCP servers. Prosyo is available in Agent chat.

Windsurf

Add this to ~/.codeium/windsurf/mcp_config.json. Windsurf's remote field is serverUrl. Headers stay empty.

json
{  "mcpServers": {    "prosyo": {      "serverUrl": "https://app.prosyo.com/ai"    }  }}

VS Code and GitHub Copilot

Add this to .vscode/mcp.json. The top-level key is servers, and the type is http.

json
{  "servers": {    "prosyo": {      "type": "http",      "url": "https://app.prosyo.com/ai"    }  }}

Smithery

Install into Claude from the verified Smithery listing:

bash
npx @smithery/cli install hello-kmun/prosyo --client claude

Try it the moment it connects

  • "Give me the Prosyo overview: running campaigns, unread replies, and credits." → get_overview
  • "Draft a four-touch campaign for heads of talent at UK agencies. LinkedIn first, email on day five. Leave it as a draft." → create_campaign
  • "Show unread inbox threads and draft a reply. Do not send it." → list_inbox, draft_reply

Reads run immediately. Anything that sends, launches, enrolls, unlocks, researches, or spends credits stops and waits for a yes in chat, then confirm_action.

Architecture

The agent talks to one hosted endpoint. Prosyo runs the outbound engine behind it. Nothing is installed on the machine. Diagram on the live guide.

mermaid
flowchart LR  A["AI Client (Claude / Cursor)"] -->|HTTPS Streamable HTTP| B["https://app.prosyo.com/ai"]  B --> C["Outbound Engine (LinkedIn + Cold Email + Unified Inbox)"]
HopWhat happens
AI Client (Claude / Cursor)Claude, Cursor, Windsurf, or VS Code calls a tool from chat.
HTTPS (Streamable HTTP)One remote connection. No stdio process. No API key header.
https://app.prosyo.com/aiProsyo's hosted MCP server. Manifest: server.json.
Outbound EngineLinkedIn, cold email, and the unified inbox for this workspace.

Tools Directory

30 tools. Read tools return data immediately. Write tools that change who gets contacted, or that spend credits, prepare the action and finish only after confirm_action once the chat says yes. pause_campaign and save_intent_leads_to_list apply immediately.

Workspace · Campaigns · Prospecting · Inbox · Intent · Safety

The same directory, with the same anchors, is on the GitHub Pages guide.

Workspace

ToolType (Read/Write)Description
get_overviewReadDashboard snapshot: running campaigns, replies, unread inbox, credits, and account health for this Prosyo workspace.
get_entitlementsReadCurrent plan name, trial or paid status, LinkedIn and email seat counts, active campaign limit, and credit balance.

Campaigns

ToolType (Read/Write)Description
list_campaignsReadList campaigns in this workspace. Optional status filter: draft, running, paused, completed, archived.
get_campaignReadCampaign detail: status, enrolled count, sequence step types, and connected seats.
preview_campaignReadMerge a real prospect into the campaign sequence so the messages can be read before launch.
create_campaignWriteCreate a draft campaign. Does not launch or enroll anyone. Modes: blank, preset (preset_id), ai (ai_brief), or intent (audience fills with people who show intent_signals and fit the ideal customer; each waits for review first). Stays a draft until a later launch is confirmed.
launch_campaignWritePrepare launching a draft campaign. Sending does not start until confirm_action after a yes in chat.
pause_campaignWritePause a running campaign immediately so it stops queueing new sends. Idempotent.
resume_campaignWritePrepare resuming a paused campaign. Sending does not restart until confirm_action after a yes in chat.

Prospecting & Enrichment

ToolType (Read/Write)Description
search_prospectsReadSearch people in this workspace by name, company, or email.
list_listsReadProspect lists with people counts.
get_prospect_researchReadA prospect's latest research (facts with sources) and personalised lines: icebreaker, connection note, LinkedIn message, email subject, and body.
enroll_prospectsWritePrepare adding a list or specific people to a campaign. Does not enroll until confirm_action after a yes in chat.
research_prospectsWritePrepare researching prospects: sourced facts plus a personalised icebreaker, connection note, LinkedIn message, and email. Costs credits per person; fresh research is reused free. Runs only after confirm_action.
enrich_prospectsWritePrepare enriching prospects (enrich_only) or writing a personalised first line (personalized_line). Costs credits per person. Runs only after confirm_action.

Unified Inbox

ToolType (Read/Write)Description
list_inboxReadRecent LinkedIn and email conversations. Optional search and unread filter.
get_threadReadOne inbox conversation with recent messages.
draft_replyWriteDraft an inbox reply. Returns text only and does not send. Use send_inbox_reply after the reply should go out.
send_inbox_replyWritePrepare sending a LinkedIn or email reply from Inbox. The message is not sent until confirm_action after a yes in chat.

Intent Intelligence

ToolType (Read/Write)Description
get_intent_summaryReadIntent overview: whether tracking is on, this month's included people used and left, today's deliveries, High-intent and Warm counts, and how many wait for review.
list_intent_leadsReadPeople or companies showing buying signals, strongest first, each with intent score, ideal-customer fit, and why now. Locked people show only their signals until unlocked.
get_intent_leadReadOne Intent person or company: every signal with its source and date, fit reasons, research status, and personalised lines.
get_ideal_customerReadThe workspace's ideal customer rules (roles, industries, company size, locations, exclusions) and the High-intent and automatic delivery settings.
list_playbooksReadPlaybooks and Intent-led campaign audiences: which signals they watch, Review first or Autopilot, matches, people added, and credits used this month.
list_review_queueReadPeople a playbook matched who are waiting for approval, or whose researched message is ready to review.
get_intent_resultsReadWhat Intent found and produced: signals by source, people delivered, researched, contacted, replied, meetings, customers, credits per reply, and the best signals and playbooks.
save_intent_leads_to_listWriteSave unlocked Intent people to a prospect list (existing list_id or a new list_name). Their personalised lines go with them. Free. Locked people are skipped. Idempotent.
unlock_intent_leadsWritePrepare unlocking locked Intent people. Uses the plan's included people first, then credits per person. Nothing is unlocked until confirm_action after a yes in chat.

Execution & Safety

ToolType (Read/Write)Description
approve_reviewWritePrepare approving people waiting in the review queue (run ids from list_review_queue). Approval researches them for credits. The message is still visible before it is sent. Runs only after confirm_action.
confirm_actionWriteRun a launch, enroll, resume, inbox send, unlock, research, enrichment, or review approval after an explicit yes in this chat. Pass confirmation_token from the previous tool.

Official MCP Registry

Prosyo is listed in the Official MCP Registry as io.github.ShubhamTuts/prosyo version 1.0.1.

The registry is the community index of publicly accessible MCP servers. The Model Context Protocol organization on GitHub runs it collaboratively, backed by Anthropic, GitHub, Microsoft, and PulseMCP.

Official platformModel Context Protocol Registry
Registry servicemodelcontextprotocol/registry, the Go service behind the centralized index
Reference serversmodelcontextprotocol/servers, reference implementations maintained by the MCP steering group
Record formatOpen server.json schema: reverse-DNS name, discovery metadata, and the remote execution path
Downstream useUpstream metadata index that clients, integrations, and other registries can read
Live guideshubhamtuts.github.io/prosyo-mcp-server

Prosyo's record points at the hosted Streamable HTTP endpoint https://app.prosyo.com/ai. The manifest declares no API key and no authentication headers.

Resource Links

Copyright (c) 2026 Prosyo.

來源：README.md，提交 27ecd20

工具

0
工具後設資料尚未被收錄。

版本歷史

1
  1. v1.0.1最新Oct 4, 2026