Cadence MCP server

Read from the package source without running it. The installed server may list more.

• cadence_check_brand_readinesswrite action

  Run the carrier-readiness check: crawls the site, validates the privacy policy, messaging terms,

• cadence_check_consent

  Whether a brand may message a number, and why not if it may not. Check this rather than attempting

• cadence_close_conversation

  Close a conversation. Stops turn counting.

• cadence_create_agentwrite action

  Create an agent under a brand. A local record until it is synced to Google — nothing reaches Google here.

• cadence_create_brandwrite action

  Create a brand — the business carriers review. Fields are snake_case on brand routes.

• cadence_get_brand

  A brand's details, its latest readiness report, what is blocking submission, and its agents.

• cadence_get_conversation

  State, channel, trust level and turn count for one conversation.

• cadence_get_messages

  The transcript. Read deliveredText rather than body — on the SMS leg they differ, and body is the

• cadence_get_started

  How Cadence works and what to do first. Call this before anything else if you have not used it before.

• cadence_invite_tester

  Allowlist a phone number as a test device on an agent, so it can receive real RCS before carrier

• cadence_launch_readiness

  What is still blocking an agent's carrier launch, while everything is still cheap to change. The

• cadence_list_brands

  The brands on your account with each one's carrier-approval status.

• cadence_list_keys

  The API keys on this account — prefix, kind, label, brand scope and whether each is revoked.

• cadence_onboarding_status

  The go-live checklist, computed from your account's real state. Each step names the call that completes it.

• cadence_open_conversation

  Start a conversation and send the first message. The agent speaks first and opt-in provenance is required.

• cadence_preview_go_live

  Rehearse the irreversible step. Creates NOTHING and returns exactly what would be sent to Google:

• cadence_request_launch

  IRREVERSIBLE. Requests carrier launch. The launch questionnaire cannot be edited afterwards

• cadence_request_verification

  IRREVERSIBLE. Asks Google to verify the brand behind this agent, and permanently freezes the

• cadence_sendwrite action

  Send the next turn in an open conversation. Rich content degrades to smsFallbackText on the SMS leg.

• cadence_simulate_reply

  Deliver a reply as though the recipient sent it. SANDBOX KEYS ONLY — refused on live keys, because

• cadence_sync_google

  IRREVERSIBLE. Creates every not-yet-synced agent on this brand at Google. Google deprecated

• cadence_update_brandwrite action

  Set the details carriers verify. Do not guess legalEntity — carriers reconcile it against the site,

• cadence_usage

  Usage and cost for a calendar month, for the account this server is authenticated as — which is

• Code scan3 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
• Maintenancerepository not readable: repo not found3/15
• Maintainer identityverified namespace with website, no repo4/10

Safety score

58/100

higher than 15% of 4,460 AI and agents servers

Tools

23

the typical AI and agents server has 6

Tools that change things

22%

typical: 0%. Fewer write tools means less an agent can break

Downloads a week

61

more than 50% of 1,538 AI and agents servers with a package

Cadence: common questions

Is Cadence MCP server safe?

With care: it is graded C, so read the findings first (58/100). Read the Cadence safety report

How do I install Cadence?

It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.

Does Cadence need an API key?

Yes. The registry entry asks for CADENCE_API_KEY.

Is Cadence maintained?

The latest release is v0.3.1.

What can I use instead of Cadence?

Servers from other publishers that do the same job: llmtrim MCP server and Clawdcursor MCP server.

How does Cadence compare with other AI and agents MCP servers?

safety score 58/100 (higher than 15% of 4,460 AI and agents servers); tools 23 (the typical AI and agents server has 6); tools that change things 22% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.