API MCP server
com.politicalcomms/api·v0.2.1Compliant political SMS/MMS from MCP clients: projects, contacts, analytics, billing.
0 stars63 downloads/wk
Reviews
Write oneNobody has reviewed API yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
API tools (15, 3 write)
write = sends, deletes, buys or postsRead from the package source without running it. The installed server may list more.
archive_projectArchive a completed project so it no longer appears in default project listings. Only projects in completed status can be archived; other statuses are rejected with INVALID_STATE_TRANSITION.
copy_projectCopy an existing project into a new draft. The copy keeps the message, phone numbers, and settings but drops contact lists, schedule, and stats, and gets a versioned name (X becomes X_v2). Copying never sends messages.
create_projectwrite actionCreate a new messaging project (a draft send). Requires the owning organization, a name, protocol (sms or mms), sending phone number IDs, contact list IDs, and the message text. For channel=10dlc also pass brand_id and campaign_id; for channel=toll-free pass toll_free_verification_id. Creating a project does not send messages by itself.
get_contact_listGet one contact list by ID, including import progress and list analysis results when available.
get_hierarchyGet the full organization hierarchy tree visible to the API key, including nested child organizations and their brands.
get_ledger_usageGet billing usage totals and per-category breakdown from the ledger for a date range, optionally filtered to a descendant organization.
get_message_statsGet aggregate message stats (totals and daily breakdown) for a date range, optionally filtered by organization, brand, or campaign.
get_projectGet one project by ID with its full configuration: status, channel, message text, phone numbers, contact lists, link tracking settings, and schedule.
get_project_statsGet delivery and engagement stats for one project: sent, delivered, undeliverable, replies, opt outs, clicks, and the derived rates.
list_contact_listsList contact lists with their contact counts and import status. Optionally filter by organization or brand.
list_organizationsList all organizations visible to the API key, including their status and parent organization. Also useful as a credential check.
list_projectsList messaging projects (a project is one composed send: message text, sending numbers, and contact lists). Optionally filter by organization, brand, or campaign.
schedule_projectSchedule a project to send to its full contact lists at a specific date and time. This commits a real bulk send to every contact on the lists once the scheduled time arrives.
test_projectwrite actionSend real test messages for a project to up to 50 explicit phone numbers. This delivers actual SMS or MMS to those recipients and incurs cost.
unschedule_projectwrite actionRemove the schedule from a project so it will not send. Safe to call repeatedly; the project returns to an unscheduled state.
Public scan report
scanner v0.1.9 · 2026-09-24 · same rubric, same numbers if you re-run it
- Code scan2 source files scanned25/25
- –Live reliabilityno gateway calls yet and no remote to proben/a
- –Tool poisoningtools not inspected (local package is not executed); not countedn/a
- Auth qualitystatic API keys via environment variables6/15
- Maintenancelast push 0 days ago15/15
- Maintainer identitynamespace and repository owner differ; GitHub account older than a year6/10
How API compares
Against every graded MCP server, from our own scans and uptime checks. Updated after each scan run.
- Safety score
- 80/100
- higher than 60% of 48,255 servers
- Tools
- 15
- the typical server has 7
- Tools that change things
- 20%
- typical: 0%. Fewer write tools means less an agent can break
- Downloads a week
- 63
- more than 50% of 12,191 servers with a package
What its tools let an agent do: 11 read · 1 create · 2 change · 1 delete
Install API in Claude Code, Cursor or VS Code
Runs npx -y @political-comms/mcp on your machine. Read the scan report first; the gateway never runs local packages.
claude mcp add api -- npx -y @political-comms/mcp
What the publisher says
From the API repository's README, as published. We do not edit it. Read it on GitHub
Political Comms SDK
Official client libraries and tools for the Political Comms REST API. Direct-to-carrier political texting for campaigns, PACs, advocacy organizations, fundraisers, and elected officials.
The API surface covers Projects (compose, test, schedule, send), Contact Lists, Media Files, Organizations and hierarchy, Brands, Campaigns, Tracking Domains, Phone Numbers, Analytics, Billing, and Email (sending domains, sender identities, lists and imports, suppressions, templates and AI drafts, and campaigns). The full OpenAPI 3.1 specification lives at politicalcomms.com/openapi.json and the reference documentation at docs.politicalcomms.com.
Packages
Authentication
Every client authenticates with an API key passed in the X-API-Key header. Keys are created in the dashboard under Admin > API and are prefixed pclive. All packages read the POLITICALCOMMSAPI_KEY environment variable by default.
Development
Node 20 or later and Python 3.10 or later.
npm install
npm run build
npm test
cd python
python3 -m venv .venv
.venv/bin/pip install -e '.[dev]'
.venv/bin/pytestLicense
MIT. See LICENSE.
Nothing above is checked by us. What we check is on the safety report.
API: common questions
- Is API MCP server safe?
- Mostly: it is graded B (80/100). Read the API safety report
- How do I install API?
- It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
- Does API need an API key?
- Yes. The registry entry asks for
POLITICAL_COMMS_API_KEY. - Is API maintained?
- The last commit was 41 days ago (2026-09-24). The latest release is v0.2.1.
- How does API compare with other MCP servers?
- safety score 80/100 (higher than 60% of 48,255 servers); tools 15 (the typical server has 7); tools that change things 20% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.