Skip to main content
Glama

LoafLoaf Toronto Restaurants

Server Details

Search Toronto and GTA restaurants by location, cuisine and budget. Read menus and CAD prices, hours, awards and reservation links through four read-only MCP tools. Hosted Streamable HTTP; no account or API key required.

If you are the author of this connector, you can claim ownership. Claimed connector authors can inspect health checks, view analytics, and manage their listing.
Status
Healthy
Uptime
100.0% over the last 24 hours
Last Tested
Transport
Streamable HTTP · MCP 2025-11-25
URL
ChatGPT
–
Claude
–

TDQS

A4/5.0

Scored across 4 tools

Disambiguation5/5

find_restaurant (name lookup for a known restaurant) and search_restaurants (location-based discovery with filters) are explicitly differentiated in their descriptions, including when to use each. get_restaurant (profile/hours/booking) versus get_menu (menu contents) target clearly distinct resources, so an agent can select without ambiguity.

Naming Consistency5/5

All four tools follow a consistent snake_case verb_noun pattern (find_restaurant, get_restaurant, get_menu, search_restaurants). The verbs differ (find/get/search) but each is used correctly and predictably for its action type.

Tool Count4/5

Four tools is on the lean side but each covers a distinct stage of the restaurant lookup workflow (discover, resolve name, profile, menu). Nothing feels redundant, though the surface is minimal enough that a slightly broader set could be justified.

Completeness4/5

The core read-only lifecycle is covered: discovery via search, name resolution via find, detail via profile, and content via menu, with clear hand-offs (place_id) and next-step hints. Gaps are minor, e.g. no reviews, real-time availability, or a direct booking action, though booking links are surfaced through get_restaurant.

Available Tools

4 tools
find_restaurantA
Read-onlyIdempotent
Inspect

Look up a Toronto restaurant you already have a name for.

Returns candidates, each with name_match (exact | partial | fuzzy | none) and a place_id. An exact match is the restaurant; otherwise check the address. Next: get_restaurant(place_id) or get_menu(place_id).

Inputs: name (required), near, limit. Returns: near, query, candidates

get_menuA
Read-onlyIdempotent
Inspect

The menu, read from the restaurant's own website: sections and items with prices as printed. Menus that are only images or scanned PDFs come back as attached images for you to read; a result holds a few, and says how to get the rest. Typically 5-90 s the first time (slow sites can take longer), then served from cache for the configured lifetime. website_status explains an empty result (no_menu_found, blocked, robots_disallowed, unreachable...).

Inputs: website, place_id, media_offset. Returns: skipped, sources, website, renderer, +5 more

get_restaurantA
Read-onlyIdempotent
Inspect

One restaurant's full profile: weekly hours (and kitchen, brunch, happy-hour hours), price per person, phone, website, how to book (booking platform link, the restaurant's own booking page, or phone), ordering links (own storefront, delivery apps), amenities (reservable, outdoor seating, vegetarian food...) and awards. Takes a few seconds: it reads the restaurant's website for booking and ordering links.

Inputs: place_id (required). Returns: lat, lng, name, hours, +24 more

search_restaurantsA
Read-onlyIdempotent
Inspect

Find restaurants around a location, with Google's filters plus a per-person budget.

Each result has a place_id, rating, price range, distance, whether it is open now and any awards. excluded counts places dropped by the filters and why. Next: get_restaurant(place_id) for hours, booking and ordering links; get_menu(place_id) for the menu.

Inputs: near (required), sort, limit, query, +11 more. Returns: notes, pages, filters, results, +3 more

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    Related MCP Servers

    • A
      license
      Not graded
      quality
      C
      maintenance
      Remote MCP server that lets AI assistants read tracked competitive intelligence — competitor news, reviews, website changes, social posts and ads — and act on it by managing projects, competitors, battle cards, reports and canvases. Every answer carries a source and a date, and write actions only publish when explicitly shared.
      MIT
    • A
      license
      A
      quality
      D
      maintenance
      Enables brand visibility monitoring across major AI platforms like ChatGPT, Claude, Gemini, and Perplexity. It allows users to track visibility scores, analyze competitor data, and receive actionable insights to improve AI-generated brand recommendations.
      16
      11 npm
      1
      MIT
    • A
      license
      Not graded
      quality
      C
      maintenance
      Browse IndustryLens's published competitive-intelligence reports and head-to-head competitor comparisons from any AI agent — real, source-backed data.
      MIT
    Try in Browser

    Glama MCP Gateway

    Add one secure layer between your agents and this server.

    Resources