How do I use amadeus-mcp-server?

1. Click on "Install Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@amadeus-mcp-server Is AF1234 delayed? What are my rights?" 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.

amadeus-mcp-server

by Thaynabarreiro

Overview Schema Source Related Servers Score Discussions Admin

Python

Remote

🛰️ Amadeus MCP Server

Python 3.11+ License: MIT

An open-source Model Context Protocol server that exposes the Amadeus Self-Service APIs as tools for Claude and any MCP client. Ask Claude "Is AF1234 delayed tomorrow? What are my rights?" and it answers with real flight data and cited passenger-rights passages.

Tools

Tool	Backing source	What it does
`flight_status`	Amadeus On-Demand Flight Status	Scheduled vs estimated times, delay minutes, cancellation flag
`predict_delay`	Amadeus Flight Delay Prediction	P(delay > 2h) for a flight
`search_flights`	Amadeus Flight Offers Search	Bookable non-stop offers with prices and seats left
`passenger_rights`	RAG corpus (EU261, carrier policies)	Policy passages with named sources — no un-cited entitlements
`handle_disruption`	amadeus-disruption-agent	Runs the full LangGraph disruption pipeline and returns the grounded passenger message + trace

Related MCP server: Amadeus Agent

Architecture

flowchart LR
    C[Claude / any MCP client] -- MCP (stdio) --> S[amadeus-mcp-server]
    S --> T1[flight_status]
    S --> T2[predict_delay]
    S --> T3[search_flights]
    S --> T4[passenger_rights]
    S --> T5[handle_disruption]
    T1 & T2 & T3 -.-> A[(Amadeus Self-Service APIs)]
    T4 -.-> R[(EU261 + carrier policy corpus · BM25 RAG)]
    T5 -.-> P[disruption-agent LangGraph pipeline]
    P -.-> A
    P -.-> R

All five tools are backed by the disruption-agent package — one shared data layer for OAuth2, response normalisation, mock/live parity and the policy corpus. The two projects compose: this server is the interface (any MCP client becomes a travel assistant), the agent is the automation (proactive end-to-end disruption handling).

Quickstart

Claude Code

claude mcp add amadeus -- uvx --from git+https://github.com/Thaynabarreiro/amadeus-mcp-server amadeus-mcp-server

Or from a local clone:

git clone https://github.com/Thaynabarreiro/amadeus-mcp-server
cd amadeus-mcp-server
python -m venv .venv && source .venv/bin/activate && pip install -e .
claude mcp add amadeus -- $(pwd)/.venv/bin/amadeus-mcp-server

Claude Desktop

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "amadeus": {
      "command": "/path/to/amadeus-mcp-server/.venv/bin/amadeus-mcp-server",
      "env": { "AGENT_MODE": "mock" }
    }
  }
}

Try it

No credentials needed — the default mock mode replays realistic fixtures. Ask Claude:

"Check the status of AF1234 tomorrow. If it's disrupted, what are my rights under EU261, and what rebooking options exist?"

"Run the disruption handler for AF1234 tomorrow and show me the passenger message."

Live mode

Set environment variables (free test keys at developers.amadeus.com):

"env": {
  "AGENT_MODE": "live",
  "AMADEUS_CLIENT_ID": "...",
  "AMADEUS_CLIENT_SECRET": "..."
}

Design notes

Grounded by construction — passenger_rights returns passages with sources, so the model can cite EU261 or carrier policy instead of asserting entitlements from memory.
Mock/live parity — mock fixtures mirror live response shapes; switching modes changes the data source, not tool behaviour. That makes the server testable in CI and demoable anywhere.
Thin server, shared core — tools delegate to the disruption-agent package; OAuth2 token caching, normalisation and retrieval logic live in one repository.

Development

pip install -e ".[dev]"
pytest          # 8 offline tests: tool behaviour + MCP protocol registration
ruff check src tests

Built by Thayná Barreiro · MIT License. Not affiliated with Amadeus IT Group; uses the public Amadeus for Developers Self-Service APIs.

Available Tools

5 tools

flight_statusA

Get the status of a flight (scheduled vs estimated times, delay, cancellation).

Args: carrier_code: IATA carrier code, e.g. "AF". flight_number: Flight number without carrier, e.g. "1234". departure_date: Scheduled departure date, ISO format "YYYY-MM-DD".

ParametersJSON Schema

Name	Required	Description	Default
`carrier_code`	Yes
`flight_number`	Yes
`departure_date`	Yes

TDQS

A3.5/5.0

Behavior3/5

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

With no annotations, the description carries the full burden. It discloses that the tool returns scheduled vs estimated times, delay, and cancellation info, implying a read-only query. However, it does not mention any potential side effects, authorization needs, or response format details, leaving some behavioral aspects unclear.

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 extremely concise, using a single purpose sentence followed by parameter descriptions. It is front-loaded with the core action, and every sentence adds value without redundancy.

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?

Despite no output schema, the description hints at return content (times, delay, cancellation). Combined with clear parameter descriptions and a specific purpose, the description is sufficiently complete for an agent to invoke the tool, though explicit output details would improve it.

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?

Given 0% schema description coverage, the description effectively adds meaning to all three parameters: carrier_code (IATA, example 'AF'), flight_number (without carrier, example '1234'), and departure_date (ISO format 'YYYY-MM-DD'). This exceeds the raw schema and provides actionable guidance.

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

Purpose4/5

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

The description clearly states the purpose: 'Get the status of a flight' with specifics on what is included (scheduled vs estimated times, delay, cancellation). It distinguishes from sibling tools like search_flights (searching) and predict_delay (predicting) by focusing on current status retrieval. However, it does not explicitly differentiate from all siblings.

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

Usage Guidelines2/5

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

No guidance on when to use this tool versus alternatives is provided. The description lacks context on prerequisites or when not to use it, such as for historical data or predictions.

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

handle_disruptionA

Run the full disruption-handling agent for a flight: status check, disruption assessment, rebooking search, policy retrieval and a grounded passenger message.

Args: carrier_code: IATA carrier code, e.g. "AF". flight_number: Flight number, e.g. "1234". departure_date: ISO format "YYYY-MM-DD". scenario: In mock mode only: "delay", "cancellation" or "on_time".

ParametersJSON Schema

Name	Required	Default
`scenario`	No	delay
`carrier_code`	Yes
`flight_number`	Yes
`departure_date`	Yes

TDQS

A4/5.0

Behavior3/5

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

No annotations exist, so the description must cover behavior. It lists the steps (status check, assessment, rebooking, policy, message) and notes the scenario parameter is mock-only, but does not clarify if actions are immutable, require permissions, or produce side effects.

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 concise with a clear opening on purpose followed by parameter details. Every sentence adds value without redundancy.

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

Completeness3/5

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

For a multi-step tool with no output schema, the description omits what the tool returns (beyond 'grounded passenger message'), error conditions, or idempotency. This gap hinders full understanding of tool behavior.

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

Parameters5/5

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

Despite 0% schema description coverage, the 'Args' section in the description provides thorough explanations for all parameters: carrier_code format, flight_number usage, departure_date ISO format, and the scenario mock options. It also specifies required parameters.

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 clearly states the tool's purpose: running a full disruption-handling agent with multiple steps. It distinguishes itself from sibling tools like flight_status and search_flights by bundling those tasks into one orchestration.

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 usage when a comprehensive disruption workflow is needed, but it does not explicitly state when to use this tool versus individual sibling tools, nor does it provide when-not-to-use conditions.

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

passenger_rightsA

Look up passenger rights and carrier disruption policies (EU261, rebooking, baggage, duty of care). Returns the most relevant policy passages with sources, so every entitlement you state can be cited.

Args: question: Natural-language question, e.g. "compensation for a 3 hour delay". top_k: Number of passages to return (default 3).

ParametersJSON Schema

Name	Required	Description	Default
`top_k`	No
`question`	Yes

Output Schema

ParametersJSON Schema

Name	Required	Description
`result`	Yes

TDQS

A4.4/5.0

Behavior3/5

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

With no annotations, the description carries full burden. It discloses the return format ('most relevant policy passages with sources') but does not mention side effects, permissions, or limitations. This is adequate but not thorough.

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 front-loaded with purpose and value, followed by a clean Args block. Every sentence serves a purpose with no waste.

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 tool is a retriever with an output schema, the description adequately covers its function. It mentions sources and relevance, which combined with output schema, provides complete context.

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

Parameters5/5

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

Schema description coverage is 0%, so the description compensates fully. It explains both parameters: question with example, and top_k with default value, adding meaning beyond schema.

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 clearly states the tool's purpose: 'Look up passenger rights and carrier disruption policies' with specific references (EU261, rebooking, baggage, duty of care). It distinguishes from siblings like flight_status and handle_disruption by focusing on policy lookup with citations.

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 implies use when needing to cite entitlements with sources. However, it does not explicitly state when not to use or compare to alternatives, leaving some guidance unstated.

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

predict_delayA

Predict the probability that a flight is delayed by more than 2 hours.

Args: origin: Origin IATA airport code, e.g. "NCE". destination: Destination IATA airport code, e.g. "CDG". departure_datetime: Scheduled departure, ISO format "YYYY-MM-DDTHH:MM". carrier_code: IATA carrier code, e.g. "AF". flight_number: Flight number, e.g. "1234".

ParametersJSON Schema

Name	Required	Description	Default
`origin`	Yes
`destination`	Yes
`carrier_code`	Yes
`flight_number`	Yes
`departure_datetime`	Yes

TDQS

A3.7/5.0

Behavior2/5

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

No annotations provided, so the description carries the full burden. It does not disclose behavioral traits such as whether the tool is read-only, rate limits, authentication needs, or what happens on invalid input. The description only covers basic purpose and parameters.

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 efficient with a clear purpose sentence followed by a structured 'Args' list. No redundant text, and the most important information comes first.

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

Completeness3/5

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

The description covers the tool's purpose and all parameters, but lacks any information about the return value or output format. Since there is no output schema, the description should have mentioned what the prediction result looks like (e.g., probability value). Also missing error handling context.

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?

Despite 0% schema description coverage, the description adds value by explaining each parameter with examples (e.g., origin 'NCE', departure_datetime format 'YYYY-MM-DDTHH:MM') and clarifying codes. This helps agents understand required formats beyond schema titles.

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 clearly states the tool predicts the probability that a flight is delayed by more than 2 hours. It uses a specific verb 'predict', identifies the resource 'flight delay probability', and distinguishes from siblings like 'flight_status' which likely gives current status rather than prediction.

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?

No explicit guidance on when to use this tool versus alternatives. The description implies it's for prediction, but does not mention exclusions or recommend other tools for current status or actions.

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

search_flightsA

Search bookable flights for a route and date (non-stop, one adult).

Args: origin: Origin IATA airport code, e.g. "NCE". destination: Destination IATA airport code, e.g. "CDG". departure_date: ISO format "YYYY-MM-DD". max_results: Maximum number of offers to return (default 5).

ParametersJSON Schema

Name	Required	Description	Default
`origin`	Yes
`destination`	Yes
`max_results`	No
`departure_date`	Yes

Output Schema

ParametersJSON Schema

Name	Required	Description
`result`	Yes

TDQS

A4.1/5.0

Behavior3/5

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

No annotations are provided, so the description carries the full burden. It specifies constraints (non-stop, one adult) but does not disclose whether it is a live search, whether it modifies data, or the format of return results. Additional context on side effects or access patterns would be beneficial.

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?

Description is concise with a clear header and a straightforward list of args. Every sentence adds value; no wasted words. Well-suited for quick comprehension.

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 presence of an output schema, the description does not need to detail return values. It covers the essential input semantics and constraints. However, it could mention that the search is for commercial flights (bookable) and that results may vary over time.

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

Parameters5/5

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

Schema description coverage is 0%, so the description must compensate. It explains all four parameters with examples (IATA codes, ISO date format) and default values for max_results. This adds significant meaning beyond the bare schema properties.

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?

Description clearly states it searches bookable flights for a route and date, with explicit constraints (non-stop, one adult). It differentiates from sibling tools like flight_status or handle_disruption by focusing on searching, not status or disruption handling.

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?

Implied usage for searching flights, but no explicit guidance on when to use this tool over alternatives like flight_status or predict_delay. No exclusions or use-case boundaries mentioned.

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.

5 tool updatesv1.0.0Jul 11, 2026
- First observedflight_status
- First observedhandle_disruption
- First observedpassenger_rights
- First observedpredict_delay
- First observedsearch_flights

Install Server

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

A3.9/5.0

Scored 2026-07-11 13:30 across 5 tools

Disambiguation5/5

Each tool has a clearly distinct purpose: one checks flight status, one runs a disruption agent, one retrieves passenger rights, one predicts delays, and one searches flights. No overlap.

Naming Consistency5/5

All tool names follow a consistent verb_noun pattern in snake_case (e.g., flight_status, handle_disruption, search_flights).

Tool Count4/5

5 tools is a reasonable count for a flight disruption management server. It covers core functions without being too sparse or excessive, though a few more specialized tools could exist.

Completeness4/5

The tool surface covers the main workflows: status, disruption handling, rights lookup, prediction, and search. Some minor gaps like airport code resolution or direct rebooking are absent but the handle_disruption tool may encapsulate those.

Maintenance

ActivityStale

ResponsivenessNo issues

Resources

GitHub Repository

Need Help?

Related Servers

Unclaimed servers have limited discoverability.

Looking for Admin?

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

Related MCP Connectors

World Airfares Flight Search A
com.worldairfares
Flight search MCP server providing search, pagination, and itinerary details for AI assistants.
Travel & Transportation Search
32
ALLFLYGHTS
io.github.dev-allflyghts
Geo-based flight search MCP server. Find more flights between any two places on earth
Travel & Transportation Location Services
2
Flight MCP
com.flight-mcp
Search and compare flight offers through a cache-aware Streamable HTTP MCP server for AI agents.
Travel & Transportation Search
1
strata
ai.klavis
MCP server for progressive tool usage at any scale (see https://klavis.ai)
Agent Orchestration Autonomous Agents Developer Tools
25,748

Related MCP Servers

Amadeus MCP Server
Travel & Transportation Search
privilegemendes
A
license
Not graded
quality
D
maintenance
A Model Context Protocol server that connects to Amadeus API, enabling AI assistants to search flights, analyze prices, find best travel deals, and plan multi-city trips.
Updated a year ago (2025-03-28 07:31 UTC)
17
6
MIT
Amadeus Agent
Travel & Transportation Agent Orchestration
EEGRCENEM
F
license
Not graded
quality
D
maintenance
A proof-of-concept MCP server that allows LLM agents to query live flight booking information via Amadeus, including cheapest tickets, destinations, and airline routes.
Updated a year ago (2025-06-02 19:20 UTC)
1
-
Naver Flight MCP
Travel & Transportation
InSIkHwang
F
license
Not graded
quality
D
maintenance
A Model Context Protocol (MCP) server built with mcp-framework that provides tools for flight-related operations. This appears to be a template or starter project with example tools that can be extended for flight search and booking functionality.
Updated 10 months ago (2025-11-04 23:49 UTC)
1
-
Amadeus Flight Availabilities
Travel & Transportation Search
amrahman90
A
license
Not graded
quality
C
maintenance
An MCP server that integrates with the Amadeus Flight Availabilities Search API to allow users to search for available flights and view seat availability in real-time.
Updated 6 months ago (2026-03-10 20:16 UTC)
MIT

Latest Blog Posts

Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)
By Om-Shree-0709 on July 25, 2026.
mcp
Agent Identity
OAuth 2.1
Your AI Chatbot Just Exposed Your CEO's Salary to an Intern
By Om-Shree-0709 on July 2, 2026.
Agent Identity
MCP Security
OAuth Delegation
Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)
By Om-Shree-0709 on June 30, 2026.
Agentic Ai
Prompt Injection
WebAssembly

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/Thaynabarreiro/amadeus-mcp-server'

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