keithah-tessie-mcp
Unofficial integration! ## 鉁� Key Features ### 馃挵 Financial Intelligence - **Smart Charging Cost An鈥�
可用工具 （5 个）
该服务在 MCP 协议中暴露的工具，AI 可按需调用
tavily_search 14 个参数 需填 1 项
Search the web for current information on any topic. Use for news, facts, or data beyond your knowledge cutoff. Returns snippets and source URLs.
必填参数：query
tavily_extract 6 个参数 需填 1 项
Extract content from URLs. Returns raw page content in markdown or text format.
必填参数：urls
tavily_crawl 11 个参数 需填 1 项
Crawl a website starting from a URL. Extracts content from pages with configurable depth and breadth.
必填参数：url
tavily_map 8 个参数 需填 1 项
Map a website's structure. Returns a list of URLs found starting from the base URL.
必填参数：url
tavily_research 2 个参数 需填 1 项
Perform comprehensive research on a given topic or question. Use this tool when you need to gather information from multiple sources to answer a question or complete a task. Returns a detailed response based on the research findings.
必填参数：input
服务介绍
Tessie MCP Server v2
MCP server rebuilt on the latest developer.tessie.com API. Summary-first tools, composite commands, and live-tested smoke scripts.
# Quickstart
- Install (Smithery recommended):
npx -y @smithery/cli install @keithah/tessie-mcp - Set
TESSIE_API_KEY(https://dash.tessie.com/settings/api) in your MCP client or.env. In Smithery UI the field appears asaccessToken. - Try in a client: “List my vehicles” →
get_active_context, “Lock VIN ...” →manage_vehicle_commandwithconfirm: true.
# Tools
get_active_context— vehicle roster with next-step guidance.fetch_vehicle_state— locks, climate, battery, location snapshot.fetch_vehicle_battery— charging-focused battery view.search_drives— recent drives with optional date range.get_driving_path— coordinate series for mapping/analysis.manage_vehicle_command— lock/unlock, charging, climate, speed limit, sentry, cabin overheat, seat heat/cool, flash/honk, wake.
# # Command safety
Destructive operations require params.confirm: true.
{
"vin": "YOUR_VIN",
"operation": "lock",
"params": { "confirm": true }
}
Non-destructive actions like flash_lights / honk skip confirmation.
# Local dev & tests
- Build stdio:
npm run build:stdio - Build shttp:
npm run build:shttpornpm run build:all - Tests:
npm test(includes command validation) - Smoke with live Tessie token:
npm run smoke(raw client),npm run smoke:tools(MCP tools)
# Smithery
- Playground/dev tunnel:
npm run devornpx @smithery/cli dev - Transports: stdio (
npm run build:stdio), shttp (npm run build:shttp, default for publish) - Docs index: https://smithery.ai/docs/llms.txt ; TS quickstart:
npx create-smithery@latest - Config schema:
.well-known/mcp-config(expectsTESSIE_API_KEY). Server card:.well-known/mcp.json(aliases in.well-known/mcp-server.jsonand.well-known/mcp/server.json). - Publish/update:
npm run build:shttp→npx @smithery/cli publish(usesmanifest.json). EnsureTESSIE_API_KEYis provided in user config.
# Notes
- API references cached in
docs/llms-full.txtanddocs/tessie-api-metadata.jsonfor offline context. - Uses TypeScript MCP SDK and Tessie HTTPS API; all state stays in Tessie. Undo/confirmation is enforced in
manage_vehicle_command. - MCP design references: see
docs/glama-links.mdfor glama.ai best-practice articles. - Speed-limit operations accept
speed_limit_pin(sensitive); avoid logging or sharing it. - Optional debug logging: set
TESSIE_MCP_DEBUG=1(ortrue) to emit request failures with URLs/status only (no headers/API keys); retry/backoff is built-in for 429/5xx responses. - Tessie client caches read requests (vehicles, state, battery, drives, paths, historical states) per client instance with short TTLs (15-30s), capped size (200 entries), and VIN-scoped invalidation after commands to avoid stale state while keeping token usage low.
