TableJourney food travel
200多個城市中經認證的餐廳、市場與街頭美食,附來源與營業時間;美食節慶已確認日期;可預訂的導覽與住宿。公開遠端MCP伺服器,無需金鑰。
託管 MCP 伺服器
npx add-mcp 'https://tablejourney.com/mcp'可安裝到 Claude Code、Codex、Cursor 等客戶端
文件
TableJourney for AI agents: MCP server and REST API
How to use TableJourney's verified food-travel data from an AI agent: a public MCP server, a REST API with OpenAPI docs, attribution and limits.
Canonical: https://tablejourney.com/agents/
TableJourney is built for people, and the same data is open to the agents that help them: 45,048 editorially verified venues across 224 cities, 1,608 festivals with resolved dates, and 207,406 bookable products. Every place has a page on this site to cite, with the source we checked, when we checked it, and whether it is still open.
Both doors are public. No key is needed. Without one, answers carry the essentials (name, kind, cuisine, price tier, a one-line summary, festival dates), the page to send the reader to and every booking link, up to 20 results a call; the page has the address, opening hours and the full write-up. A key adds the full record and gives your agent its own attribution tag and rate limit; ask through the contact page.
MCP server
Streamable HTTP at https://tablejourney.com/mcp. Add it to Claude Desktop, Claude Code, Cursor or any MCP client:
{ "mcpServers": { "tablejourney": { "type": "streamable-http", "url": "https://tablejourney.com/mcp" } } }
Claude Code: claude mcp add --transport http tablejourney https://tablejourney.com/mcp. Manifest: /.well-known/mcp.json. Listed in the official MCP registry.
Tools
Tool
Arguments
What it returns
search_places
query, country, city, kind, cuisine, dietary, price_tier, open_at, near, radius_km, limit, offset
Verified venues. kind is a topic or a group (eat, drink, bake, do); dietary is vegan, halal...; open_at is 'now', 'sunday 10:00' or an ISO datetime; near is 'lat,lng'.
place
id
One venue in full, with open_now and three nearby venues, by the id search_places returned.
plan_day
country, city, neighborhood, dietary, price_tier, date
A composed food day: breakfast to drinks, every stop open on the date, plus a bookable experience.
festivals
country, city, date_from, date_to, query, limit
Festivals with their next dates.
experiences
city, country, query, food_only, limit
Bookable tours, classes, tastings and tickets.
stays
country, city, limit
Hotels and stay partners with booking links.
car_hire
country, city
Car hire partners that verifiably cover the city.
tickets
country, city
Attraction tickets, city passes and tour partners covering the city.
things_to_do
country, city, date_from, date_to
Start here for "what can I do in this city": tours, tickets, festivals, places to eat, stays and car hire with booking links, in one call.
dishes
country, city, query, limit
Signature dishes and where to eat them, with links.
itineraries
country, city
Editorial day-by-day plans, each venue linked to its page.
cities
country
Every city covered, with slugs to use in the other tools.
City and country accept names or slugs (rome, italy); an unknown city answers with did_you_mean. Ids look like italy/rome/restaurants/ and go straight into place.
Connect your assistant
The server URL is the same everywhere: https://tablejourney.com/mcp. Menu names change from release to release; the steps below were right when this page was built.
- Claude (web and desktop): Settings, Connectors, Add custom connector, then paste the URL.
- ChatGPT: : Settings, Apps and Connectors, Advanced settings, turn on Developer mode, then Create a connector with the URL and no authentication.
- Le Chat (Mistral): Connectors, Add connector, Custom MCP connector, then paste the URL.
- Copilot Studio: : in your agent, Tools, Add a tool, Model Context Protocol, with the URL as the server and no authentication.
Coding tools take a small config file:
Claude Code claude mcp add --transport http tablejourney https://tablejourney.com/mcp # VS Code (agent mode): .vscode/mcp.json { "servers": { "tablejourney": { "type": "http", "url": "https://tablejourney.com/mcp" } } } # Cursor: ~/.cursor/mcp.json { "mcpServers": { "tablejourney": { "url": "https://tablejourney.com/mcp" } } } # Gemini CLI: ~/.gemini/settings.json { "mcpServers": { "tablejourney": { "httpUrl": "https://tablejourney.com/mcp" } } } # Codex: ~/.codex/config.toml [mcp_servers.tablejourney] url = "https://tablejourney.com/mcp"
REST API
The same functions as JSON under https://tablejourney.com/api/v1/: interactive docs at /api/v1/docs, the OpenAPI description at /api/v1/openapi.json.
curl "https://tablejourney.com/api/v1/places?q=pasta&city=rome&kind=eat&limit=5" curl "https://tablejourney.com/api/v1/places?near=41.8902,12.4922&radius_km=1" curl "https://tablejourney.com/api/v1/festivals?country=italy&from=2026-11-01&to=2026-11-30" curl "https://tablejourney.com/api/v1/experiences?city=rome&q=cooking+class"
Terms of use
The data and the compute are free, with no key, no quota to buy and no sign-up. This is what we ask in return:
- Keep booking links whole. book and booking URLs are https://tablejourney.com/go/ links that forward to the partner with our affiliate id. Give them to the user as they are; do not resolve them, strip parameters or replace them with a plain partner URL. This is how free data and compute get paid for.
- Say they are affiliate links. A one-line disclosure ("booking link, TableJourney may earn a commission") keeps the user informed and keeps you compliant.
- Cite the page URL as the source of what you quote, and send the user to it for the address, opening hours and the date we checked.
- No bulk copying. Answer the user's question from the results; do not mirror the catalogue.
Every book or booking URL is a https://tablejourney.com/go/ link. It records the click and forwards to the partner with our affiliate id, so a recommendation your agent makes is attributed and the venue checks keep getting paid for. The same terms are in the MCP server's instructions and in llms.txt.
Limits
60 requests per 10 seconds per IP at the edge, 120 a minute in the service. Results are capped at 100 per call; use offset to page.
Also for agents
- llms.txt: the site in a form a model can read.
- llms-full.txt: every verified venue as a citable block.
- llms-partners.txt: the bookable inventory with prices and dates.