Provides tools for searching businesses by text and location, looking up businesses by phone number, matching structured name and address to Yelp listings, retrieving full business profiles, and fetching reviews, all via the Yelp Fusion API.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@yelp-mcp-sdk search for coffee shops in Seattle"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Yelp Fusion MCP server built on the official MCP Python SDK.
Functionally identical to yelp-mcp-min (FastMCP), but uses the low-level
Server class directly — no framework abstractions.
Python 3.11+
uv 0.11+
Docker (optional)
A Yelp Fusion API key — https://www.yelp.com/developers/v3/manage_app
Related MCP server: Yelp Fusion MCP Server
uv sync
cp .env.example .env
# Edit .env and set YELP_API_KEY# stdio transport (for use with Claude Desktop or an MCP client)
uv run python -m server.main
# Docker
docker build -t yelp-mcp-sdk .
docker buildx build -t yelp-mcp-sdk .
docker run --env-file .env yelp-mcp-sdkVariable | Required | Default | Description |
| Yes | — | Yelp Fusion API bearer token |
| No |
| API base URL |
| No |
| Request timeout in seconds |
| No |
| Max retry attempts on 429/5xx |
| No |
| Min back-off wait in seconds |
| No |
| Max back-off wait in seconds |
| No |
| structlog level |
| No |
| Emit JSON log lines |
Tool | Yelp endpoint | Description |
|
| Full-text + geo search with pagination |
|
| Look up a business by E.164 phone number |
|
| Match structured name+address to Yelp listing |
|
| Full business profile by Yelp ID or alias |
|
| Customer reviews with pagination |
yelp://business/{id} — Full Yelp business profile as application/json.
Declared via list_resource_templates; fetched via read_resource.
yelp-mcp-sdk/
server/
main.py # Server("yelp-mcp", lifespan=...) + stdio run
core/
config.py # pydantic-settings
logging.py # structlog → stderr
client.py # async httpx + tenacity retry
models.py # Pydantic output models
handlers/
params.py # Pydantic input models (also generate inputSchema)
tools.py # list_tools() + call_tool() dispatcher
resources.py # list_resource_templates() + read_resource()
tests/
conftest.py
test_client.py
test_models.py
test_handlers.py
Dockerfile
pyproject.toml
.env.exampleuv run pytest -vAspect | yelp-mcp-min (FastMCP) | yelp-mcp-sdk (official SDK) |
Tool registration |
|
|
Input schema | Auto-generated from func sig |
|
Output type | Return Pydantic model directly |
|
Resources |
|
|
Dependency inject | None (captured via closure) |
|
Transport |
|
|
Server LOC | ~350 | ~450 |
Look up Yelp businesses that match a phone number. Use when you have a phone number and need to identify the business. Phone must be in E.164 format (+14155551234). Returns up to a handful of candidates; empty list means not found.
Inputs: phone (required).
Fetch the full Yelp profile for a specific business by its ID or alias. Use when you already have a Yelp business ID and need complete details: hours, all photos, full address, price tier, categories, and URL. Raises an error if the business ID does not exist on Yelp.
Inputs: business_id (required), locale.
Retrieve user reviews for a specific Yelp business. Use when the user wants to read customer opinions: ratings, comments, and reviewer info. Returns up to 50 reviews per call. Use offset to paginate; total field shows how many reviews exist.
Inputs: business_id (required), locale, sort_by, limit, +1 more.
Match a business by name and address to its canonical Yelp listing. Use when you have structured address data and need to verify or enrich it with Yelp data such as ID, rating, hours, and URL. name + address1 + city + state + country are required. Adding zip_code and phone significantly improves match precision.
Inputs: name (required), address1 (required), city (required), state (required), +4 more.
Search Yelp for businesses matching a term, location, or both. Use when the user wants to discover restaurants, services, or shops. Supports free-text search, geo coordinates, category filters, price tiers, open-now filtering, and pagination via limit/offset. Supply at least one of: location, or both latitude + longitude.
Inputs: term, location, latitude, longitude, +7 more.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 5 tools
Each tool has a clearly distinct purpose: phone lookup, get full business details, get reviews, match by name/address, and general search. No overlapping functionality, making selection unambiguous.
All tools follow a consistent snake_case verb_noun pattern (e.g., find_business_by_phone, get_business, search_businesses), with clear modifiers where needed. No mixing of conventions.
Five tools is well-scoped for a Yelp API wrapper: covering search, matching, detailed lookup, reviews, and phone lookup. It's neither overly sparse nor bloated.
The tool set covers the core Yelp use cases—discovery, matching, detailed info, and reviews. There are no obvious gaps for read-only access, as mutations are not part of Yelp's public API.
Yelp MCP — wraps the Yelp Fusion API (api.yelp.com/v3)
Yelp business search, place details and the full review feed, as structured JSON.
4 Yelp endpoints. Pay per call in USDC via x402.
Real-time local business places, reviews, geocoding & contact emails MCP. OAuth or API key.
