FairValid

io.github.moonlitnayeem由 GitHub 帳號 moonlitnayeem 發布v1.1.0更新於 Nov 7, 2026

Verify emails and use FairMatch to search, quote and unlock verified work-email leads.

發布方自己的服務:Chat With Your Ads

已驗證Streamable HTTP可網頁執行安全與監控商業與電商

概覽

AI 產生的概覽

FairValid 可驗證電子郵件,並透過 FairMatch 讓助理搜尋、報價並解鎖已驗證的商務信箱名單,消耗工作區額度。

可以做什麼
  • 驗證單一電子郵件地址,或提交最多 5,000 個地址的批次,並讀取工作狀態、分頁結果或取消剩餘作業
  • 查詢工作區即時額度餘額
  • 取得 FairMatch 篩選條件與限制,預覽最多 50 位符合的人員,並對所選對象報價而不保留額度
  • 在明確的額度上限下解鎖 1–50 位已確認的聯絡人,接著輪詢批次並讀取已擁有的驗證聯絡人
適用情境
適合需要清理或驗證電子郵件名單的情況,也適合業務或招募流程中尋找商務聯絡人,並在事先核准的支出上限內購買已驗證的工作信箱。
執行需求
遠端 Streamable HTTP 端點,使用 OAuth 登入,不需本機套件。需在 FairValid 核准存取並選擇既有的 Live API 金鑰,其工作區、權限範圍與生命週期支出上限會套用於該連線。FairMatch 需要額外選擇加入的 leads:read 與 leads:acquire 權限,必須刻意重新連線才能取得。
安裝前請注意
即時驗證與名單解鎖會消耗工作區額度:每取得一個已驗證信箱扣 4 點額度,每筆完成的 Valid 或 Invalid 檢查扣 1 點。唯有使用者核准確切選擇與數字上限後才可設定 confirm。送出的地址與搜尋條件會傳送給 FairValid 及所連接的 AI 供應商。切勿將金鑰、密碼、OAuth 驗證碼或權杖貼到對話中;撤銷所選金鑰會終止其連線。

安裝

在 SourceWeft 中

  1. 開啟 儀表板中的 FairValid,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/io.github.moonlitnayeem%2Ffairvalid/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": {
    "fairvalid": {
      "type": "http",
      "url": "https://mcp.fairvalid.com/mcp"
    }
  }
}

README

[FairValid]

FairValid for AI assistants

FairValid 1.1.0: FairMatch API/MCP passed controlled production sandbox acceptance on November 6, 2026. Provider listings and native-client acceptance are tracked separately. Discover the connected server capabilities before use; acquisition requires an explicit numerical credit limit and confirmation.

Verify email addresses and use FairMatch by FairValid to find business leads, quote selected contacts, and unlock verified work emails with a confirmed credit ceiling. This package connects to FairValid's hosted Model Context Protocol (MCP) server and includes separate verification and FairMatch workflow skills.

Server: https://mcp.fairvalid.com/mcp
Transport: Streamable HTTP
Publisher and support: FairValid · [email protected]
Documentation: fairvalid.com/help/mcp

Connect your workspace

Use OAuth in a supported client. Sign in and approve access on FairValid, then select an existing Live API key covering the requested permissions. Its workspace, scopes, and lifetime spending cap apply to the connection. A workspace Owner or Manager can manage keys on the API keys page. Revoking the selected key ends its connections.

FairMatch adds opt-in leads:read and leads:acquire permissions. Existing keys and grants keep their existing permissions; a package update cannot expand them. To enable FairMatch, deliberately reconnect through native OAuth and select an appropriately scoped key. Review the new permissions and cap before consent. OpenAI 1.1.0 requests both lead scopes during fresh authorization. OpenClaw and Hermes include all six FairMatch tools alongside the three verification reads. Their filters do not grant OAuth permissions or authorize spending: unlock still requires leads:acquire, a quote and explicit approval of a numerical maximum.

No client secret is bundled or required for automatic public client registration. Never paste a key, password, OAuth code, or token into chat. For a client that uses bearer headers, configure an existing key through its protected credential settings. A direct Test key can be used for sandbox fixtures; OAuth currently selects Live keys.

Supported package formats

ClientIncluded configuration
Claude / Claude CodeDedicated plugin package in claude
ChatGPT / CodexSeparate portable plugin package in openai
Grok BuildClaude-compatible plugin and MCP files, plus the shared skill
Cursor.cursor-plugin/plugin.json, mcp.json, and shared skill
Gemini CLIRoot gemini-extension.json and shared skill
Hermes Agent (Nous Research)Native HTTP OAuth setup and shared skill in examples
OpenClawClaude-format bundle with marketplace installation and native sign-in
VS CodeRemote MCP server with native marketplace installation
DevinPersonal installation and setup skill verified; official marketplace submission awaiting review
ZedLocal transport extension and connection instructions in zed
Other MCP clientsProvider-specific configurations in examples

Package configuration does not establish a marketplace listing or prove a successful connection in every client. Provider account access, permissions, review, and native client acceptance are separate steps.

For Claude Code 2.1.275 or later, install inside a session with /plugin install fairvalid --marketplace moonlitnayeem/fairvalid-ai. For older versions, use /plugin marketplace add moonlitnayeem/fairvalid-ai followed by /plugin install fairvalid@fairvalid. These forms follow the official installation reference. The marketplace installs the dedicated claude/ package. A maintainer can validate that folder with claude plugin validate /path/to/fairvalid-ai/claude --strict --profile directory. Users can review and load a local public checkout with claude --plugin-dir /path/to/fairvalid-ai/claude. For Gemini CLI, the public repository can be installed with gemini extensions install https://github.com/moonlitnayeem/fairvalid-ai. These commands require that the referenced checkout or published repository exists. Review client trust prompts and complete OAuth before using the tools.

OpenClaw marketplace installation

FairValid 1.1.0 is published on ClawHub. Install and enable the FairValid plugin, then open Plugins → FairValid → Accounts in your OpenClaw Gateway. Choose Connect beside fairvalid and complete the FairValid browser consent. Select your workspace and a Live API key covering the requested permissions and an appropriate lifetime spending cap.

Start a new agent session and ask “Show my FairValid credit balance.” For FairMatch, ask to search and quote leads before approving an exact selection and numerical credit ceiling. The published bundle exposes all six FairMatch tools and three verification read tools. Existing connections need deliberate consent for the lead permissions.

On November 6, 2026, all six FairMatch tools passed a live end-to-end test through the installed ClawHub 1.1.0 bundle on OpenClaw 2026.11.1, using its native Claude CLI runtime with Claude Code 2.1.312. The test retrieved an existing owned contact through a confirmed zero-credit batch, with no additional acquisition charge.

VS Code marketplace installation

Open Chat → Open Customizations → Browse, search for FairValid, and choose Install on the MCP Gallery listing published by moonlitnayeem. The listing includes email verification and FairMatch and links to the public GitHub MCP Registry entry.

After installation, open MCP Servers to find FairValid. Start the server and complete the client's FairValid connection and consent flow before using tools. Choose a key with the lead permissions if you want to use FairMatch.

Native marketplace search and installation of version 1.1.0 were verified in VS Code 1.145.2 on November 6, 2026. That check did not require signing in to Copilot. OAuth and FairMatch tool execution in VS Code have not yet been qualified by this acceptance test.

Devin personal installation

FairValid is submitted to the official Devin marketplace and awaits provider review and merge. Public marketplace search and installation have not yet been established.

To install personally, open Customize → Plugins, choose Myself, then Add plugin → From repository. Enter https://github.com/moonlitnayeem/fairvalid-ai and subdirectory devin. The package includes the FairValid MCP connection and three skills: fairmatch-setup, fairmatch-leads, and verification-results.

Personal installation and /fairvalid:fairmatch-setup execution were verified in Devin Desktop 3.11.238 on November 6, 2026, using SWE-2 Flash Medium in Ask mode. The installed package matched the reviewed source, and the native session loaded the complete packaged setup skill before producing its response. This help skill uses public information and makes no MCP calls. The connection remained unconnected; OAuth and FairMatch business-tool execution in Devin have not yet been qualified. Package details.

What you can do

ToolPurposePermission
fairvalid_verify_emailSubmit one address for verificationsubmit
fairvalid_submit_jobSubmit a batch of 1 to 5,000 addressessubmit
fairvalid_get_jobRead a job's status and summaryread
fairvalid_get_resultsRead up to 50 results per pageread
fairvalid_cancel_jobCancel remaining job worksubmit
fairvalid_get_balanceRead live workspace creditsbalance
fairvalid_get_lead_filtersDiscover FairMatch filter keys, choices and limitsleads:read
fairvalid_search_leadsPreview up to 50 matching people; no paid unlockleads:read
fairvalid_quote_leadsQuote 1–50 selected people without reserving creditsleads:read
fairvalid_unlock_leadsStart a confirmed acquisition batch with a credit ceilingleads:acquire
fairvalid_get_lead_batchRead the same key's acquisition batch and chargesleads:read
fairvalid_get_leadsRead up to 100 owned verified contacts per pageleads:read

Examples of requests:

  • “Show my FairValid credit balance.”
  • “Show the current status and results for this FairValid job.”
  • “Verify these email addresses with FairValid.”
  • “Find FairMatch leads matching my criteria, then show a quote before unlocking.”
  • “Show my saved FairMatch leads without acquiring any new contacts.”

The verification request starts live work when connected through OAuth or a Live key. Only submit addresses you intend to verify and are authorized to process.

Credits and result interpretation

Live submissions can reserve credits and return an asynchronous job. Completed Valid and Invalid checks use one credit each. Genuine Unknown, unresolved catch-all, technical failures, and unprocessed items have no net verification charge. Cancellation does not reverse charges for completed checks; in-flight work may still finish. A spending cap does not add credits to a workspace.

An accepted job is not a completed result. Poll with backoff, honor retry hints, and follow the results cursor to read all pages. Keep pending and unprocessed items distinct from final results. Unknown or unresolved catch-all is not proof of validity; Valid is not a guarantee of inbox delivery.

Both submission tools require a stable idempotency_key. On an uncertain response, keep the same selected API-key identity, same key, and unchanged input. Reconnecting to a different API key can create another run even if the idempotency key is unchanged. Do not rotate keys or resubmit with a new key just to make an uncertain request appear successful.

FairMatch selection, credits and confirmation

FairMatch follows search → quote → explicit maximum-credit confirmation → unlock → poll batch → retrieve owned leads. Four credits are charged for each newly acquired verified work email; already-owned and unavailable contacts cost zero. A quote reserves no credits and does not guarantee a deliverable contact. Unlock accepts 1–50 distinct selection IDs, maximumCredits from 0–200, confirm: true, and a stable idempotency_key. Only set confirmation after the user approves that exact selection and numerical ceiling. Do not split work to bypass the ceiling, workspace balance or key's shared lifetime cap.

Live selections expire after 30 minutes. If admission is uncertain, reuse the original IDs, ceiling, idempotency key and API-key identity; do not refresh the selection or make another paid batch to hide uncertainty. Accepted batches can remain working; follow batch_id and report observed charged_credits after processing. Lead ownership does not authorize outreach.

See the FairMatch API/MCP guide for exact argument fields, permission upgrades, synthetic test cases and release limits, and the FairMatch skill for the complete workflow.

Connection and acceptance tests

A connection or installation request does not authorize customer verification or job cancellation or lead acquisition. For an authorized OAuth connection check, discover the currently available tools and call fairvalid_get_balance; that read spends no verification credits.

Default submission tests use a separate direct Test-key connection and the documented example.com fixtures. Sandbox work makes no live provider call and spends no verification credits; Test keys cannot read the live balance.

A controlled live acceptance test requires the workspace owner's explicit authorization. Stay within the authorized test addresses, workspace, selected Live key, and credit limit; live charges and idempotency safeguards still apply. Do not run live tests automatically, use customer lists as installation fixtures, or cancel customer jobs as part of installation tests.

The packages contain manifests, the workflow skill, examples, and brand assets. The optional Zed extension also downloads and runs a pinned local transport bridge and stores OAuth credentials in its extension work directory. No credentials are bundled. Client validation, live protocol checks, and native client tests must each be recorded according to what was actually performed; none implies a provider's approval or publication. See the static validation record.

Privacy policy

When you invoke a tool, the connected AI provider sends the supplied addresses, job and lead identifiers, search criteria, and other tool arguments to FairValid. FairMatch can return owned business-contact data to the connected assistant. FairValid processes them under its Privacy Policy and Terms. The AI provider also processes conversation and tool data under its own terms. Review those policies before connecting. The packages add no analytics. The Zed extension's local OAuth storage is described in its connection instructions. For support or data-handling questions, contact [email protected].

License and brand

The distribution code, manifests, and documentation are available under the MIT License. FairValid names and logos identify the publisher and do not grant trademark rights or permission to imply endorsement of another service. See brand guidance.

來源:README.md,提交 9d3e10c

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

2
  1. v1.1.0最新Nov 7, 2026
  2. v1.0.0Oct 30, 2026

評分

已滿足適用檢查項的 75%

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

    請在儲存庫或註冊中心條目中宣告授權條款。

其他 Valid 整合