Api

com.politicalcomms由 politicalcomms.com 發布v0.2.1更新於 Nov 3, 2026

Compliant political SMS/MMS from MCP clients: projects, contacts, analytics, billing.

發布方自己的服務：Docs

已驗證STDIO僅桌面溝通與協作資料與分析商業與電商

服務詳細資訊

識別碼: com.politicalcomms/api
傳輸: STDIO
執行環境: Desktop only
信任: Verified
發布於: Sep 16, 2026

安全提示

MCP 服務會接收對話中的工具呼叫請求，並可能執行外部操作。啟用前請先了解該服務能做什麼，並只授予它所需的權限。

註冊中心已驗證此服務的命名空間屬於 politicalcomms.com。它以軟體包形式執行，而不是託管端點，因此沒有可與該網域比對的端點。

SourceWeft 的檢查只涵蓋條目是否完整、端點是否回應；不審查伺服器的程式碼，也不審查其工具的行為。

在 README 中新增徽章

向讀者展示該 MCP 服務已收錄於 SourceWeft，徽章連結到本頁。

[![Listed on SourceWeft](https://sourceweft.com/badge/mcp/com.politicalcomms%2Fapi.svg)](https://sourceweft.com/mcp/com.politicalcomms%2Fapi?utm_source=readme&utm_medium=badge)

概覽

AI 產生的概覽

針對 Political Comms API 的 MCP 伺服器，讓助理檢視政治類簡訊／多媒體訊息專案、聯絡人、分析與帳務，並建立、測試或排定發送。

可以做什麼: 列出組織、階層、專案及專案設定
讀取送達、互動、問卷與輸送量統計，以及訊息統計和帳務用量
瀏覽聯絡人清單、以 CSV 下載清單，並檢視對話及其訊息
檢視電子郵件網域、寄件者、清單、抑制名單、活動、統計與範本
建立、複製、測試、排定、暫停與取消排定簡訊／多媒體訊息專案，在對話中回覆，並排定電子郵件活動或匯入郵件清單
適用情境: 適合需要操作美國政治類簡訊／多媒體訊息帳戶的情境：在聊天用戶端中檢視專案、聯絡人清單與分析，或準備並排定合規的簡訊與電子郵件發送。
執行需求: 透過 npm 套件以 stdio 在本機執行，需要 Node 20 或更新版本。需要 Political Comms API 金鑰（前綴 pc_live_），透過環境變數 POLITICAL_COMMS_API_KEY 提供，並由人員在後台 Admin > API Keys 建立。電子郵件寫入工具需要組織具備郵件權限。

安裝前請注意

API 金鑰是正式憑證，透過環境變數傳入。多個工具會作用於真實受眾：test_project 會發送真實測試訊息，schedule_project 會提交大量發送，reply_to_conversation 會發送真實回覆，schedule_email_campaign 與 start_email_list_import 另需 confirm: true。發送可能產生費用；付費郵件流程僅在後台提供。伺服器不提供刪除操作。

安裝

在 SourceWeft 中

開啟儀表板中的 Api，將其新增到工作區。
為需要使用其工具的對話啟用該服務。

Desktop only，透過 STDIO。 STDIO 服務會啟動本機處理程序，因此需要 SourceWeft 桌面主機。

其他 MCP 客戶端

參照儲存庫中的啟動說明。

README

@political-comms/mcp

MCP (Model Context Protocol) server for the Political Comms REST API. Lets Claude and other MCP clients inspect organizations, projects, contact lists, analytics, and billing, and create, test, and schedule compliant political SMS and MMS sends in the US.

Runs over stdio. Requires Node 20 or later and a Political Comms API key (created in the dashboard under Admin > API, prefixed pc_live_).

Setup

Claude Code

bash

claude mcp add political-comms \  --env POLITICAL_COMMS_API_KEY=pc_live_... \  -- npx -y @political-comms/mcp

claude mcp add political-comms \  --env POLITICAL_COMMS_API_KEY=pc_live_... \  -- npx -y @political-comms/mcp

Claude Desktop

Add to claude_desktop_config.json:

json

{  "mcpServers": {    "political-comms": {      "command": "npx",      "args": ["-y", "@political-comms/mcp"],      "env": {        "POLITICAL_COMMS_API_KEY": "pc_live_..."      }    }  }}

{  "mcpServers": {    "political-comms": {      "command": "npx",      "args": ["-y", "@political-comms/mcp"],      "env": {        "POLITICAL_COMMS_API_KEY": "pc_live_..."      }    }  }}

Tools

Read only:

Tool	Description
`list_organizations`	List organizations visible to the API key. Doubles as a credential check.
`get_hierarchy`	Full organization hierarchy tree with brands.
`list_projects`	List messaging projects, filterable by organization, brand, or campaign.
`get_project`	Full configuration of one project.
`get_project_stats`	Delivery and engagement stats for one project.
`get_project_survey_results`	Topline survey results for a survey project: per-question option counts and percentages, completion and dropoff rates. Returns a 409 `NOT_A_SURVEY` error for other projects.
`get_project_throughput`	Carrier-limit estimate for one project: recipients per carrier and how long AT&T takes (`will_pause` is always false).
`get_campaign_throughput`	A campaign's T-Mobile daily cap, use today, and AT&T per-minute rates.
`list_contact_lists`	Contact lists with counts and status.
`get_contact_list`	One contact list with import progress, analysis, and `downloads` URLs.
`download_contact_list`	A contact list as CSV text (`type` original or analyzed), truncated at 100,000 characters.
`get_message_stats`	Aggregate message stats for a date range.
`get_ledger_usage`	Billing usage for a date range.
`list_conversations`	Conversations with at least one inbound message, sorted by last inbound message.
`get_conversation`	One conversation: status, contact, message counts, last activity.
`list_conversation_messages`	Messages in one conversation, newest first.
`list_email_domains`	Email sending domains and their DNS verification status.
`get_email_domain`	One sending domain, including the DNS records to publish.
`list_email_senders`	Email sender identities (From addresses).
`list_email_lists`	Email lists with contact counts and status.
`list_email_suppressions`	Suppressed addresses at org, identity, or list scope.
`list_email_campaigns`	Email campaigns with status and audience counts.
`get_email_campaign`	One campaign, including `blocked`: why it will not schedule.
`get_email_campaign_stats`	Report tiles and per-link clicks.
`list_email_templates`	Saved email templates with subject and last-updated time.
`get_email_template`	One template including its full HTML body.

Write (each is annotated as non read-only; create_project, test_project, schedule_project, and reply_to_conversation additionally require confirm: true because they stage or send real messages):

Tool	Description
`create_project`	Create a draft messaging project.
`test_project`	Send real test messages to explicit phone numbers.
`schedule_project`	Commit a bulk send at a specific date and time.
`unschedule_project`	Remove a project's schedule.
`pause_project`	Pause a running or scheduled send; resume with `schedule_project`.
`copy_project`	Copy a project into a new draft (drops lists, schedule, and stats).
`reply_to_conversation`	Send a real reply (text, one `media_ids` entry for MMS, or both) inside an existing conversation. Requires `confirm: true`.
`schedule_email_campaign`	Commit an email send. Requires `confirm: true`.
`unschedule_email_campaign`	Return a scheduled campaign to a draft state.
`start_email_list_import`	Import a CSV of contacts into an email list. Requires `confirm: true`.

The server deliberately exposes no delete operations.

Email tools

Email write tools need the email entitlement on the organization and return 403 ENTITLEMENT_REQUIRED without it; reads are open. Paid and human-driven email workflows (AI drafting, result exports) and deliverability triage (pausing and resuming a live send) are dashboard features rather than tools: they cost money or need a human watching a send. There is no inbound email or inbox surface.

Errors

API errors are returned as tool errors with the machine readable code and a recovery hint. Rate limited requests (600 requests/minute per key) mention the X-RateLimit-Reset wait; authentication failures explain that a human must create a key in the dashboard.

Full API reference: docs.politicalcomms.com. OpenAPI spec: politicalcomms.com/openapi.json.