Skip to main content
Glama
compass-food

Compass DaaS

Official
by compass-food
OverviewSchemaRelated ServersScoreDiscussions
TypeScript
Remote

Compass DaaS MCP

Smithery badge

MCP server for Compass DaaS. It exposes three restaurant dietary decision tools over the Model Context Protocol and calls the Compass REST API with your API key.

Quick Start

npx -y @compass-food/mcp

Set COMPASS_API_KEY before starting the server:

export COMPASS_API_KEY=cmp_test_your_sandbox_key

For staging or local testing, set:

export COMPASS_BASE_URL=https://daas-api-veganmapai-1a8b7.a.run.app

Related MCP server: Maître d'MCP

Install

Claude Desktop

Edit ~/Library/Application Support/Claude/claude_desktop_config.json:

{
  "mcpServers": {
    "compass": {
      "command": "npx",
      "args": ["-y", "@compass-food/mcp"],
      "env": {
        "COMPASS_API_KEY": "cmp_test_your_sandbox_key"
      }
    }
  }
}

Cursor

Add to Cursor MCP settings (~/.cursor/mcp.json globally, or .cursor/mcp.json in a workspace):

{
  "mcpServers": {
    "compass": {
      "command": "npx",
      "args": ["-y", "@compass-food/mcp"],
      "env": {
        "COMPASS_API_KEY": "cmp_test_your_sandbox_key"
      }
    }
  }
}

Codex CLI

Edit ~/.codex/config.toml:

[mcp_servers.compass]
command = "npx"
args = ["-y", "@compass-food/mcp"]

[mcp_servers.compass.env]
COMPASS_API_KEY = "cmp_test_your_sandbox_key"

Get an API key

Sign up free — 1,000 Compass credits/month, no credit card required.

Tools

compass_search

Wraps POST /v1/search. The mode tool argument is sent to the REST API as the X-Compass-Mode header.

{
  "query": "strict vegan ramen in Brooklyn under $20",
  "user_profile": {
    "diet": "strict_vegan",
    "allergens": ["peanut"],
    "exclude_cross_contamination": true
  },
  "location": {
    "lat": 40.6782,
    "lng": -73.9442,
    "radius_m": 5000
  },
  "limit": 10,
  "mode": "rich"
}

compass_enrich_restaurant

Wraps POST /v1/enrich/restaurant. Use compass_id for direct lookup, or name plus address or google_place_id for fuzzy match.

{
  "name": "Buddha Bodai",
  "address": "5 Mott St, New York, NY"
}

compass_decide_fit

Wraps POST /v1/decision/restaurant-fit. The mode tool argument is sent to the REST API as the X-Compass-Mode header.

{
  "compass_id": "rest_xyz789",
  "user_profile": {
    "diet": "strict_vegan",
    "exclude_cross_contamination": true
  },
  "mode": "rich"
}

API Key Resolution

The server checks:

  1. COMPASS_API_KEY

  2. ~/.compass/config.json

Config file:

{
  "api_key": "cmp_live_abc123",
  "base_url": "https://api.compassfoodtechnologies.com"
}

Privacy

This package sends tool calls only to the configured Compass API base URL. It does not send secondary usage data.

Links

License

MIT

Available Tools

3 tools
compass_decide_fitDecide restaurant fitA
Read-onlyIdempotent

Conservative fit decision for a restaurant against a user dietary profile. Returns "fit", "not_fit", or "unknown" with reason codes, evidence, and user wording. Returns "unknown" rather than overclaiming.

ParametersJSON Schema
NameRequiredDescriptionDefault
compass_idYesCompass restaurant ID, obtained from compass_search or compass_enrich_restaurant
user_profileYesRequired dietary profile for the restaurant fit decision
modeNoResponse detail mode; rich includes fuller evidence and reasoningrich

Output Schema

ParametersJSON Schema
NameRequiredDescription
compass_idYesStable Compass restaurant ID
decisionYesConservative decision for the submitted profile
confidenceYesDecision confidence
reason_codesYesCompass public reason codes explaining the decision
evidenceYesEvidence supporting the decision
source_freshnessNoAge and refresh guidance for the evidence behind a result
risk_flagsNoRisk flags that should be surfaced to the user
recommended_user_textNoConservative user-facing wording
verification_requiredNoTrue when the user should verify with the restaurant before relying on the result
last_evaluated_atNoWhen Compass last evaluated this restaurant for decision freshness

TDQS

A4/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations declare readOnlyHint, idempotentHint, and openWorldHint, which the description does not contradict. The description adds valuable behavioral context: it is 'conservative' and returns 'unknown' rather than overclaiming, which goes beyond the annotations by clarifying the decision philosophy.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two sentences long, front-loads the key action and outputs, and contains no wasted words. Every sentence contributes essential information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (3 parameters with a nested object, annotations, output schema), the description adequately covers the core behavior. It explains the conservative nature and the three possible outcomes. Missing details like what 'reason codes' and 'evidence' entail are likely covered by the output schema, so the description is largely complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema description coverage is 100%, so the schema already documents all parameters. The description adds high-level behavioral context (conservatism, 'unknown' return) but no additional parameter-specific meaning beyond what the schema provides. Baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses the specific verb 'decide' and resource 'restaurant fit', and clearly states it returns 'fit', 'not_fit', or 'unknown' with additional artifacts. It distinguishes itself from the sibling tools (compass_search finds restaurants, compass_enrich_restaurant enriches data) by focusing on the fit decision.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies a conservative decision approach and warns against overclaiming, but does not explicitly state when to use this tool versus its siblings or any prerequisites. It lacks explicit context on when not to use it, leaving the agent to infer from the purpose.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

compass_enrich_restaurantEnrich restaurantA
Read-onlyIdempotent

Match a restaurant by name and address, then return Compass enrichment data including VeganScore, vegan dietary profile, and evidence. Does not return certification/free-from facts. Returns "matched: false" with candidates if confidence is below threshold.

ParametersJSON Schema
NameRequiredDescriptionDefault
compass_idNoCompass restaurant ID for direct lookup
nameNoRestaurant name
addressNoStreet address (improves match)
google_place_idNoGoogle Place ID (highest match confidence)

Output Schema

ParametersJSON Schema
NameRequiredDescription
matchedYesWhether Compass confidently matched the submitted restaurant
compass_idNoStable Compass restaurant ID for the matched restaurant, when matched
restaurantNoCompass restaurant result
candidatesNoCandidate matches returned when confidence is below threshold
confidenceNoMatch confidence when available
vegan_scoreNoDeterministic Compass VeganScore summary
dietary_profileNoPublic restaurant dietary facts supported by launch evidence. Compass does not expose allergen-safe or certification claims.
evidenceNoEvidence for the enrichment result

TDQS

A4.5/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already indicate readOnly, idempotent, and open world. The description adds value by disclosing that the tool does not return certification/free-from facts, and explains the matching confidence threshold behavior. This provides useful behavioral context beyond what annotations offer.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is three sentences, each adding essential information: purpose and returned data, exclusions, and low-confidence behavior. It is front-loaded and concise without redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the output schema exists, the description covers all necessary context: purpose, input options, constraints, and edge-case behavior. It is complete for a read-only enrichment tool with no need for additional state or authentication details.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so parameters are well-documented. The description adds semantic value by explaining that google_place_id provides the highest match confidence, and that compass_id is for direct lookup. This enhances the agent's understanding of parameter use.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description specific verb 'Match' and resource 'restaurant enrichment data' clearly defines the tool's function. It lists returned data types (VeganScore, vegan dietary profile, evidence) and explicitly states what is not returned (certification/free-from facts), providing a precise purpose that distinguishes it from siblings.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explains the input parameters (name and address as primary matching; compass_id or google_place_id as alternatives) and describes the behavior when confidence is low (returns 'matched: false' with candidates). While it doesn't explicitly state when not to use this tool, the context for enrichment vs. search/decide is implied by the sibling tool names.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. 3 tool updatesv0.1.0
    • First observedcompass_decide_fit
    • First observedcompass_enrich_restaurant
    • First observedcompass_search
Install Server
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

A4.4/5.0
Disambiguation5/5

Each tool has a distinct purpose: decide_fit makes a dietary fit determination, enrich_restaurant returns enrichment data for a specific restaurant, and search allows natural-language queries. There is no overlap or ambiguity.

Naming Consistency5/5

All tools follow the consistent pattern 'compass_verb_noun' (decide_fit, enrich_restaurant, search). The naming is predictable and uniform.

Tool Count5/5

With only 3 tools, the set is appropriately scoped for the narrow domain of restaurant dietary matching. Each tool is essential and there is no bloat.

Completeness5/5

The tools cover search, enrichment, and fit decision, which are the core operations for the domain. No obvious gaps exist given the stated purpose of providing dietary data service.

Maintenance

ActivityInactive
ResponsivenessSyncing

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

Related MCP Servers

  • MCP Compass

    liuyoshio
    A
    license
    B
    quality
    D
    maintenance
    MCP Compass is a discovery and recommendation service that assists AI assistants in finding and understanding Model Context Protocol servers through natural language queries.
    1
    142
    245
    MIT

  • Maître d'MCP

    devingoodsell
    F
    license
    A
    quality
    D
    maintenance
    An MCP server for restaurant discovery and booking across Resy and OpenTable via natural language. It integrates Google Places data with dietary preferences, visit history, and weather awareness to provide personalized dining recommendations and group reservation management.
    23
    -

  • FLUX Restaurants MCP Server

    sabamen88
    F
    license
    Not graded
    quality
    Not graded
    maintenance
    An AI-native restaurant discovery service that enables searching and receiving natural language recommendations for over 2,200 restaurants across 15+ US cities. It provides tools for accessing detailed restaurant info, curated lists, and cuisine-specific searches through the Model Context Protocol.
    -

  • menami

    Menami-AI
    A
    license
    Not graded
    quality
    D
    maintenance
    Personalized restaurant recommendations, table bookings, and delivery via MCP, CLI, or API, learning user taste and acting proactively.
    MIT

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/compass-food/compass-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server