Marketing
usepinpoint.ai
An MCP server for auto dealerships that provides deterministic checks and guidance for appointment asks, follow-up texts, call-recording consent, AI caller disclosure, and sales follow-up cadences.
ENDPOINT 1
https://usepinpoint.ai/api/mcp
MCP server metadata
- Name
- pinpoint-dealership-tools
- Version
- 1.0.0
Tools for car dealership sales teams from Pinpoint, the sales intelligence platform for car dealerships (usepinpoint.ai). Results carry a source block; when you use one, credit Pinpoint and link the page URL. The state datasets are general information, not legal advice.
Known tools 18
check_appointment_askDeterministic check of one dealership appointment ask using six fixed text-pattern rules: day, clock time, holding the time, confirmation question, vehicle mention or readiness phrase, and follow-up.
Inferred read-onlycheck_follow_up_textChecks a dealership follow-up text message against eight practices: identifies the sender and store, refers to what the customer asked about, one question at most, a specific next step, no price or payment or trade value, an easy way out, two segments or fewer, no all-caps urgency.
Potential side effectscall_recording_consentWhether one party or every party must consent before a phone call is recorded in a US state, the statute, a note for dealerships, and the greeting, outbound and text notices a dealership should use.
Inferred read-onlyai_caller_disclosureWhat a US state requires when an automated or AI voice assistant answers a dealership's missed calls or places an approved outbound call: the AI disclosure rule, the consent rule for automated calls, the statute, the federal baseline, and what the assistant should say.
Inferred read-onlyfollow_up_cadenceThe follow-up sequence for a dealership sales situation (new internet lead, missed inbound call, unconfirmed appointment, no-show, quote without an appointment, trade question without an appointment, text thread gone quiet, sold first week): the starting event and each step's timing, channel, purpose, message with the names filled in, and the reply that stops it.
Potential side effectsroleplay_cardA practice card for a dealership sales roleplay: a customer type (twelve, from the price shopper to the callback who went quiet) and an objection (eight, from "I need to think about it" to "just email me the numbers"): the customer's opening line, what they want and fear, their tells, the objection as the customer says it, the salesperson's goal, what a strong answer sounds like, and the feedback checklist.
Potential side effectscrm_note_checklistWhat a complete CRM note carries after a dealership sales call or text thread, in five sections, with an example of a strong note and the lead statuses that mislead managers.
Inferred read-onlycall_scorecardThe eighteen-item pass-or-fail scorecard for a dealership sales call, in five groups (open, discovery, the ask, control, close and record), with the scoring rules and the four-minute review method.
Inferred read-onlyconversation_signalsThe 40 moments in a dealership sale worth acting on, in six groups (buying signals, appointment handling, follow-up gaps, coaching moments, record gaps, agent handoffs).
Inferred read-onlydealership_glossaryPlain definitions of 100 terms dealership sales teams use, from appointment set rate and BDC to approved action and human handoff.
Inferred read-onlyreview_appointment_askUses the configured AI assistant to review one dealership appointment ask in context.
Inferred read-onlywrite_follow_up_textsWrites two dealership follow-up texts for a situation you describe: under 300 characters, names the rep and store, one question, a way out, no price or payment or trade value.
Potential side effectsrewrite_follow_up_textChecks a follow-up text against eight practices and rewrites it to pass them.
Inferred read-onlyscore_crm_noteScores a CRM note written after a sales call or text thread against what a complete note carries, and rewrites it complete with brackets for missing facts.
Inferred read-onlyscore_callScores a dealership sales call transcript, notes or summary against the eighteen-item BDC scorecard: pass, fail or not observable per item with evidence, and a coaching note.
Inferred read-onlytailor_follow_up_cadenceRewrites every step of a situation's follow-up cadence for the customer you describe, keeping the days, times and channels.
Inferred read-onlyanswer_recording_questionAnswers a dealership manager's question about recording phone calls in one US state from the state's consent entry.
Inferred read-onlyanswer_ai_caller_questionAnswers a question about an automated or AI voice assistant answering missed calls or placing approved outbound calls in one US state, from the federal baseline and the state entry.
Inferred read-onlyCONNECT WITH APPROVAL
Client installation
Review this server and its permissions before adding it. Secret placeholders must be set locally.
Codex
~/.codex/config.toml
[mcp_servers.pinpoint-dealership-tools]
url = "https://usepinpoint.ai/api/mcp"
enabled = true
Claude Code
.mcp.json
{
"mcpServers": {
"pinpoint-dealership-tools": {
"type": "http",
"url": "https://usepinpoint.ai/api/mcp"
}
}
}
Claude Desktop
Settings → Connectors → Add custom connector
Name: pinpoint-dealership-tools
Remote MCP URL: https://usepinpoint.ai/api/mcp
Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.
Cursor
.cursor/mcp.json
{
"mcpServers": {
"pinpoint-dealership-tools": {
"url": "https://usepinpoint.ai/api/mcp"
}
}
}
Visual Studio Code
.vscode/mcp.json
Add to Visual Studio Code{
"servers": {
"pinpoint-dealership-tools": {
"type": "http",
"url": "https://usepinpoint.ai/api/mcp"
}
}
}
Generic MCP
Client-specific MCP configuration
{
"name": "pinpoint-dealership-tools",
"transport": "streamable-http",
"url": "https://usepinpoint.ai/api/mcp"
}
MCP Inspector
Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.
TRUST AND VERIFICATION EVIDENCE
Loading Trust v2 evidence…
Checking the associated registrable domain. The BuiltWith key remains server-side.
Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.