Vruum

ai.vruum由 vruum.ai 發布官方發布者v0.15.1更新於 Nov 7, 2026

Vruum AI revenue platform — outbound, deals, pipeline & CRM automation over one MCP.

已驗證Streamable HTTP可網頁執行效率與工作流溝通與協作商業與電商

概覽

AI 產生的概覽

Vruum 這套 AI 營收平台的官方 MCP 介接,讓助理研究潛在客戶、執行外聯、管理商機並讀取營收資料。

可以做什麼
  • 取得每日簡報、下一步行動建議與高風險商機檢視
  • 搜尋與研究潛在客戶、匯入名單、找出可引薦的人脈路徑
  • 讀取與管理聯絡人、客戶帳戶、人脈身分與知識庫
  • 檢視目標並管理外聯訊息、互動與內容
  • 讀取與管理商機、營收紀錄與績效指標
  • 管理設定、工作區、歷史匯入,並與 Vruum 助理對話
適用情境
適合已在使用 Vruum 的業務與行銷團隊,希望在自己的 MCP 用戶端裡讓助理起草外聯、處理回覆、追蹤目標與商機,並找出銷售管道的風險。
執行需求
本機 stdio 橋接需 Node 20+,或以 OAuth 2.1 直連託管端點。需要 Vruum 帳號與個人存取權杖(vk_live_...),透過 VRUUM_MCP_TOKEN 或 Authorization 標頭提供,也可沿用 Vruum CLI 登入留下的憑證。需能連線至 Vruum API。
安裝前請注意
部分工具會寄送外聯、發布內容,並消耗供應商額度或 LinkedIn 預算;某些寫入會產生外部影響。未設定權杖時橋接會讀取 Vruum 設定目錄中的既有憑證,因此在已登入狀態下執行會直接操作真實帳號,寫入即為真實寫入。呼叫失敗不會自動重試,以免重複寄送。權杖以 Bearer 標頭送往 Vruum API。

安裝

在 SourceWeft 中

  1. 開啟 儀表板中的 Vruum,將其新增到工作區。
  2. 連接 所需的 憑證。它們會被私密儲存,絕不會在公開頁面上展示。
  3. 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。

交給代理程式安裝

把這段提示詞貼上到 Claude Code、Codex、Cursor 等代理程式,或 SourceWeft 對話中。代理程式會讀取該伺服器的安裝指南,先向你展示發布者、端點和登入方式,經你同意後再把它新增到你的客戶端。金鑰不會寫進任何命令。

閱讀 https://sourceweft.com/mcp/ai.vruum%2Fmcp/install.md,並按其中說明把這個 MCP 伺服器接入我的客戶端。修改任何設定之前,先告訴我它的發布者、端點和登入方式,等我確認。不要把 API 金鑰寫進命令或我會提交的檔案;問我金鑰應從哪裡取得。

檢視代理程式所依據的安裝指南

其他 MCP 客戶端

把它新增到你客戶端的 mcpServers 設定中。 客戶端會在首次連接時完成 OAuth 登入。

{
  "mcpServers": {
    "vruum": {
      "type": "http",
      "url": "https://api.vruum.ai/mcp"
    }
  }
}

README

Vruum MCP (@vruum/mcp)

[npm] [license] [registry]

Official MCP access to Vruum, the AI revenue platform. Give your agent the whole revenue motion — research prospects, build pipeline, run email and LinkedIn outreach, triage replies, manage deals through close, and read Stripe-backed revenue truth — through 35 compound tools rather than a sprawl of endpoints. Outreach runs inside objectives: a goal, the people it targets, and the policy for reaching them.

This package is a stdio bridge: it serves the tool surface locally (no credentials needed to introspect) and proxies execution to https://api.vruum.ai/mcp under your token. Every call is authorized server-side — the bridge grants no authority your Vruum account doesn't already have.

[!TIP] Using a client that supports remote MCP? Connect directly instead. Claude Code, Claude Desktop, Cursor, Codex and friends should point straight at https://api.vruum.ai/mcp (OAuth 2.1). Fewer moving parts and no token in an env var. This bridge exists for stdio-only clients and for credential-free tool introspection. See vruum.ai/docs/mcp.

Quickstart

You need Node 20+ and a Vruum account. Create a personal access token in the web app under Settings → API tokens (vk_live_…).

Claude Desktop / Claude Code — claude_desktop_config.json or .mcp.json
json
{  "mcpServers": {    "vruum": {      "command": "npx",      "args": ["-y", "@vruum/mcp"],      "env": { "VRUUM_MCP_TOKEN": "vk_live_…" }    }  }}
Cursor — ~/.cursor/mcp.json
json
{  "mcpServers": {    "vruum": {      "command": "npx",      "args": ["-y", "@vruum/mcp"],      "env": { "VRUUM_MCP_TOKEN": "vk_live_…" }    }  }}
Codex CLI — ~/.codex/config.toml
toml
[mcp_servers.vruum]command = "npx"args = ["-y", "@vruum/mcp"]env = { VRUUM_MCP_TOKEN = "vk_live_…" }
Already use the Vruum CLI? — no token needed here
sh
npx @vruum/cli login --token vk_live_…

The CLI needs Node 22+. Credentials land in ~/.vruum/credentials and the bridge picks them up automatically — omit the env block entirely.

Verify it works without configuring anything:

sh
npx -y @modelcontextprotocol/inspector --cli npx -y @vruum/mcp --method tools/list

Reliability diagnostics

The bridge records content-free operational metadata: generated attempt IDs, the declared client family (Claude/Codex/ChatGPT/unknown), known tool name, start/outcome, timestamp and duration. It never records tool arguments, results, credentials, raw error text or conversations. The private outbox is under ~/.vruum/mcp-diagnostics/ (or VRUUM_CONFIG_DIR), separated by endpoint.

Records survive bridge restarts and upload to that same endpoint's authenticated /diagnostics route after connectivity returns. Only a durable acknowledgement removes them. A restored connection drains the backlog in bounded batches. Transient failures retry once per minute while the bridge is alive; authentication or unsupported-endpoint responses wait for subsequent activity/startup. Uploads never follow redirects or transmit credentials over non-local HTTP. The queue retains at most 500 records per endpoint and reports overflow; disk failures print a coverage warning on stderr. Stdout remains MCP JSON-RPC.

Missing-token, connection, protocol, cancellation, invalid-cursor and call failures are observable when the bridge runs. An offline machine cannot deliver reports until it reconnects, and an old installed package has none of these diagnostics. A bridge success means it received the remote result, not that the host used it correctly. Business calls are never automatically replayed after an ambiguous failure. Server and bridge evidence correlate by attempt ID.

What you can ask for

Once connected, these are ordinary requests to your agent:

You sayWhat happens
"What should I work on today?"get_daily_briefing — pending approvals, new replies, stalled deals, warm paths, one recommended next action
"Review my outreach drafts"get_outreach_review → you approve, edit, or reject each one
"Research Acme Corp and tell me if they fit"research — website, funding, careers signals, ICP match with reasoning
"Find a warm intro to this person"find_warm_path — separates verified paths from unverified connector candidates
"Which objectives are actually working?"get_objective_outcomes — contacted, replied, and meetings booked, compared across objectives
"What's at risk in my pipeline?"inspect_pipeline — the 5 most at-risk deals, risk-first
"Draft a LinkedIn post about X"manage_content — your agent writes it, you approve, Vruum schedules and publishes

Your harness authors outreach copy, replies, LinkedIn posts, and comments through their review surfaces. It can also chat with Vruum through manage_assistant (start_conversation, append_message): the same chat as the app's floating panel, which reads your records and applies reversible record changes with Undo. The chat does not draft or send messages.

Tool surface

35 compound tools. Read operations inspect saved data; write operations mutate it. Some writes buy provider work or produce external effects. Each tool describes its own authorization and retry contract.

AreaTools
Daily operatingget_daily_briefing · get_next_actions · inspect_pipeline
Search & researchsearch · fetch · research · research_lookup · import_prospects · find_warm_path
Peopleget_person_360 · manage_person
Relationship identityget_network_identity_review · manage_network_identity_resolution
Objectives & outreachinspect_objective · get_outreach_review · manage_messages · manage_outreach · manage_relationship_action
Engagement & contentget_engagement_review · manage_engagements · get_content_review · manage_content
Performanceget_objective_outcomes · get_performance_metrics
Dealsget_deal_360 · manage_deal
Revenueget_revenue · manage_revenue
Accounts & knowledgemanage_account · manage_kb
Imports & assistantmanage_history_import · manage_assistant
Workspaces, config & skillsget_operator_companies · manage_settings · skill

manage_outreach also creates, configures, launches, and pauses objectives; inspect_objective reads an objective's setup, audience, forecast, and sourcing plan. No tool mixes reads with writes: research_lookup holds the external lookups (work email, LinkedIn profile, company website, careers page, LinkedIn people search), which can spend provider credits or LinkedIn budget. get_operator_companies lists the workspaces your login can act in; it is not limited to Vruum staff.

Full schemas, descriptions and MCP safety annotations live in tools.json — generated from the live server definition, never hand-edited.

The current package also carries the retained-email decision instructions in manage_messages. A saved email uses its displayed Action version, proposal revision, and fingerprint. Approval is not a delivery receipt; changed content requires new work.

Chat with Vruum through manage_assistant. start_conversation takes payload={request_id, message, context?} and waits up to 50 seconds for the answer; append_message takes id=<chat UUID> and the same payload. The result names the chat, the turn's state, the question, the answer, changes (each record change the chat applied, with its Undo state) and cards. A turn still running after 50 seconds returns running; read the chat later with inspect_assistant action=read id=<chat UUID>. Actions Undo cannot reverse, and actions that reach a customer or spend, come back as a card with the exact call, and the turn returns awaiting_approval. manage_assistant action=decide_card id=<item UUID> payload={decision: approved|declined} decides one, only with the user's own answer: approved runs that exact call once under your credentials, declined never runs it; it waits up to 50 seconds for the turn. manage_assistant action=undo id=<item UUID> runs a change's exact inverse and is refused when the record was edited since; action=rate id=<message UUID> rates an answer. Keep the same request_id on a retry after an uncertain response: the server runs each request once.

Configuration

Env varMeaningDefault
VRUUM_MCP_TOKENVruum personal access tokenfalls back to VRUUM_TOKEN, then ~/.vruum/credentials
VRUUM_MCP_URLHosted MCP endpointhttps://api.vruum.ai/mcp
VRUUM_MCP_TIMEOUT_MSPer-call timeout — research and imports run long300000
VRUUM_CONFIG_DIRCredentials directory~/.vruum

How it works

your agent  ──stdio/JSON-RPC──▶  @vruum/mcp                                     │                    tools/list ──────┤  served locally from tools.json                                     │  (no network, no credentials)                                     │                    tools/call ──────┴──HTTPS+Bearer──▶  api.vruum.ai/mcp                                                          (authorized server-side)

Listings are a static snapshot bundled at release. That's what makes credential-free introspection possible, and it means a newly added tool won't appear until the next release — calls still execute correctly, since they proxy through. In the monorepo, a snapshot test fails any change that lets tools.json drift from the server definition, so a release never ships a stale listing.

Safety and credentials

  • Server-side authorization. The bridge adds no permissions. Your token is exactly your Vruum account, and role/tenant checks happen on the server.
  • No automatic retries. A failed tools/call is never replayed. Many of these tools send outreach or spend money, and an ambiguous failure may mean the server already executed — a silent retry could double-send. The connection is discarded, the error says so, and your agent decides whether re-running is safe.
  • Your token never leaves your machine except as a Bearer header to api.vruum.ai.

[!WARNING] The bridge picks up ambient credentials. With no VRUUM_MCP_TOKEN set it falls back to ~/.vruum/credentials. If you are logged in with the Vruum CLI, then running this server — via the MCP Inspector, a client, or a script — executes against your real account and real data. Write tools will really write.

To poke at it with no credentials, pass an explicit env that reaches the process:

sh
env -i PATH="$PATH" HOME=/tmp/empty node dist/index.js

Note that MCP clients following the SDK default only forward an allowlist (HOME, PATH, SHELL, TERM, USER, LOGNAME) to spawned servers — so setting VRUUM_CONFIG_DIR in your shell may be stripped before it reaches the bridge, while HOME survives and the credentials file is found anyway. Set credentials in the client's own env block instead.

Development

This repo is a build artifact of the Vruum monorepo, resynced automatically on release. tools.json is generated from the server definition, and a snapshot test in the monorepo fails when the two differ. Between releases, the hosted server can be ahead of this snapshot.

src/index.ts   the bridge — token resolution, static listings, proxied callstools.json     generated tool surface (do not edit by hand)test/          black-box tests: spawn the built binary, speak raw JSON-RPC
sh
npm installnpm test        # builds, then runs the black-box suitenpm run typecheck

Tests drive the built binary over stdin/stdout and assert at the wire level rather than through an SDK client — an SDK-mediated test hides protocol mistakes, since it will happily hand back a result object whether the server returned result or error. They cover the initialize handshake (including negotiation down to older clients on earlier spec revisions), credential-free listing, protocol-vs-execution error semantics, cursor rejection, capability declaration, and stdout hygiene.

Issues and PRs are welcome here. Maintainers apply accepted changes upstream in the monorepo and they flow back on the next sync — so a merged fix here may appear as part of a sync commit rather than your original one. Changes to tools.json must come from the generator, not by hand.

Links

Vruum · MCP docs · Getting started · CLI reference

Registry entry ai.vruum/mcp · Claude & Codex plugin vruum-gtm/skills

License

MIT

來源:README.md,提交 d550802

工具

0
該伺服器需要登入,因此 SourceWeft 無法在沒有帳號的情況下讀取其工具,也未收錄。已連接帳號所能看到的內容可能因帳號及其權限而異。

版本歷史

9
  1. v0.15.1最新Nov 7, 2026
  2. v0.14.0Oct 9, 2026
  3. v0.12.3Oct 8, 2026
  4. v0.11.0Oct 6, 2026
  5. v0.9.0Oct 5, 2026
  6. v0.7.1Oct 5, 2026
  7. v0.7.0Oct 3, 2026
  8. v0.6.0Sep 23, 2026
  9. v0.4.0Sep 16, 2026

評分

已滿足適用檢查項的 85%

該評分衡量此收錄條目的完整程度,依據註冊中心條目、端點與公開來源計算得出。它不是對伺服器本身的評價,也不表示伺服器安全或目前可用:可連通性是帶日期的檢查結果,評分也不包含安裝量或使用者評價。

  • 近 30 天內可連通必需25 分
  • 已宣告認證方式必需10 分
  • 已列出工具15 分

    請讓伺服器在無憑證時回應 tools/list,或發布可在沙箱中無憑證啟動的軟體包。

  • 描述必需15 分
  • 圖示10 分
  • 文件15 分
  • 授權條款10 分