面向 AI 代理的复杂行程工具。 多程停留、环球旅行、缺口程、地面段——这些是标准航班搜索无法处理的行程。当你的用户要求跨大洲 3 个以上停留点时，此服务器会基于真实的 AirTreks 运价构建数据给出航线分析：60 多家航空公司、53 条已知死腿航线、基于 1,400 多次真实运价尝试测得的可出票率，以及来自实际预订的 20 个经过验证的航线模板。
实时端点： https://mcp.airtreks.com/mcp——免费，无需 API 密钥，每天 100 次请求。
现在支持真实价格：任何航线在一秒内即可获得历史价格区间，特定行程可获取实时票价，完整的多程停留行程可按多张机票分别计价——同一行程因出票方式不同，价格可能相差三倍，这是其他航班工具不会告诉你的部分。
设置 → 连接器 → 添加自定义连接器 → 粘贴 https://mcp.airtreks.com/mcp。
claude mcp add --transport http airtreks https://mcp.airtreks.com/mcp添加到 .cursor/mcp.json（或 Cursor 设置 → MCP → 添加新服务器）：
{
"mcpServers": {
"airtreks": {
"url": "https://mcp.airtreks.com/mcp"
}
}
}任何工具都无需 API 密钥，包括顾问交接功能。密钥是可选的，仅用于提高每日限额；如果你的客户端无法发送自定义请求头（如 claude.ai 连接器），请将其附加到 URL 末尾：
https://mcp.airtreks.com/mcp?key=at_your_key设置 → 应用与连接器 → 启用开发者模式（Pro/Business 套餐）→ 将 https://mcp.airtreks.com/mcp 添加为自定义连接器。
与上方 Cursor 的 JSON 格式相同（Streamable HTTP）。偏好 stdio？本地运行：
npx airtreks-mcp然后向你的代理提问：
规划一次环球旅行：旧金山、东京、曼谷、新加坡、德里、伊斯坦布尔、伦敦，最后回到旧金山。
Related MCP server: wander-agent
你的用户想要环游世界六个站点。Google Flights 直接放弃。联盟环球机票预订网站可以让他们构建行程，但出票时会失败。一次 plan_route 调用就能告诉你的代理什么方案真正可行：
{
"cities": ["SFO", "NRT", "BKK", "SIN", "DEL", "IST", "LHR", "SFO"],
"budget": "mid"
}真实响应，为简洁起见已截断（完整版本包含所有 7 段航程的航空公司备选方案和顾问备注）：
{
"route": "SFO -> NRT -> BKK -> SIN -> DEL -> IST -> LHR -> SFO",
"totalLegs": 7,
"isRoundTrip": true,
"direction": "westbound",
"backtracking": false,
"regionsCrossed": ["americas", "asia", "europe"],
"recommended": {
"approach": "custom",
"confidence": "high",
"reason": "7 legs — alliance fares have <6% bookability. Custom build with mixed carriers is the way to go."
},
"customBuild": {
"strategy": "Mixed-carrier build using alliance carriers, Gulf bridge connections. 1 surface sector opportunity.",
"segments": [
{
"leg": 1, "from": "SFO", "to": "NRT",
"carrier": { "code": "NH", "name": "ANA", "why": "Best transpacific availability. LAX/SFO/SEA-NRT direct." }
},
{
"leg": 5, "from": "DEL", "to": "IST",
"carrier": { "code": "TK", "name": "Turkish Airlines", "type": "gulf-bridge", "why": "Cheapest Asia-Europe usually. IST connects everywhere." }
}
],
"surfaceSectors": [
{
"insteadOf": "BKK -> SIN (leg 3)",
"suggestion": "Bangkok to Singapore through Malaysia. Train, bus, or ultra-cheap LCC. Adds Malaysia and possibly Penang, KL, Melaka.",
"savings": "Saves $100-250"
}
]
},
"allianceFeasibility": {
"starAlliance": { "viable": false, "summary": "Technically possible on Star Alliance but only 6% bookability at 7 legs. Custom build strongly recommended." },
"oneworld": { "viable": false, "summary": "Technically possible on oneworld but only 6% bookability at 7 legs. Custom build strongly recommended." }
}
}这一次调用就告诉你的代理四件从别处无法获得的信息：
联盟环球机票在此行程上会失败。 7 段航程的出票率仅为 6%——你的用户会构建好行程，然后在出票时碰壁，最后怪罪于你。
可行的构建方案： 逐段航空公司方案——全日空跨太平洋，土耳其航空作为亚欧桥梁，每段都有备选方案和权衡取舍。
哪些航段根本不该飞： 曼谷到新加坡经马来西亚陆路更便宜，可节省 100-250 美元，还能多去一个国家。
通常的费用： fare_product_match 将此行程的联盟环球机票经济舱价格定为 2,500-8,000 美元，定制构建通常为 3,000-12,000 美元。
这些是诚实的区间，而非报价——7 段混合航空公司的行程精确价格取决于预订当天的舱位可用性。要获得真实数字，trip_idea_create 会将完整的航线分析交给 AirTreks 顾问，由他们为实际机票定价并出票。你的用户得到的是从一开始就掌握信息的专家，而不是一张需要填写的表格。
所有工具均免费，无需 API 密钥——每个 IP 每天 100 次请求。
工具 | 描述 |
| 主要入口——输入城市，它评估星空联盟环球机票、寰宇一家环球机票和自定义混合承运人方案，然后推荐最佳方案 |
| 验证多城市航线——联盟规则、死腿航线、毒承运人、可出票率 |
| 按地区、方向和联盟获取 3 条建议航线 |
| 两个机场之间的最佳中转——死腿检测 + 枢纽修正 |
| 匹配正确的运价产品（环球、环太平洋/大西洋、缺口程、定制）并给出典型价格区间 |
| 将复杂行程拆分为可单独出票的航段，并给出承运人建议 |
工具 | 描述 |
| 基于 AirTreks 运价历史的航线价格区间。无需日期，约四分之一秒即可回答——当有人在做任何决定之前问"这要花多少钱？"时，这是正确的工具 |
| 特定日期特定行程的实时票价，按单张机票计价 |
| 为整个多程停留行程定价，返回多种出票方式——最便宜、最快、停留最少——并附上每种方式所基于的机票。大约需要一分钟，因此会立即返回一个引用 |
| 通过引用获取 |
工具 | 描述 |
| 交接给 AirTreks 人工旅行顾问——提交附有完整航线分析的行程请求 |
此工具会提交真实的客户联系信息，因此只能在客户知情并同意的情况下调用。24 小时内重复提交相同的邮箱 + 航线会返回现有的行程请求，而不会创建重复项。
AirTreks 自 1987 年以来一直致力于构建复杂的多程停留行程。此服务器展示了这段历史教给我们的经验：
死腿航线——看起来可出票但在联盟运价下会失败的城市对，来自 1,400 多次真实运价构建失败的经验
按航段数统计的可出票率——实测而非估算（3-4 段为 91%，5-6 段为 61%，7 段以上为 6%）
毒承运人和枢纽修正——我们知道哪些航空公司组合会破坏出票，以及应该改走什么航线
经过验证的航线模板，来自为个人、家庭和大型团体处理多程停留和环球行程的经验
没有其他航班工具能返回这些信息，因为没有其他航班工具为这些失败付过代价。
每个工具同时也是普通的 REST 端点——相同的工具、相同的速率限制、JSON 输入/输出。适用于消费 REST 而非 MCP 的代理框架：
curl -X POST https://mcp.airtreks.com/api/plan_route \
-H "Content-Type: application/json" \
-d '{"cities": ["LAX", "NRT", "BKK", "LHR", "LAX"]}'完整 OpenAPI 3.1 规范：https://mcp.airtreks.com/openapi.json
免费： 每个 IP 每天 100 次请求，无需密钥——所有工具，包括 trip_idea_create
注册： 使用 API 密钥获得更高限额（X-API-Key 请求头，或无法设置请求头的客户端使用 ?key=）
路径 | 描述 |
| MCP 协议端点（Streamable HTTP） |
| 每个工具的 REST 对应端点（POST，JSON 请求体） |
| REST 接口的 OpenAPI 3.1 规范 |
| 健康检查 |
| 获取 API 密钥以提高速率限制（POST） |
| 隐私政策 |
| 服务器信息 |
AGPL-3.0-only
Break a complex multi-city itinerary into individually-ticketable segments with carrier recommendations. Handles routes that don't fit alliance fare rules — mixed carriers, LCCs, Gulf bridge connections, surface sectors. This is how AirTreks consultants build 90% of itineraries. Use this for any route with 4+ stops, backtracking, or region combinations that alliance fares can't cover.
| Name | Required | Description | Default |
|---|---|---|---|
| pax | No | Number of passengers | |
| budget | No | Budget tier: 'budget' prioritizes LCCs, 'business' prioritizes J-class product quality | |
| cities | Yes | Ordered list of IATA city/airport codes (e.g. ['LAX', 'NRT', 'BKK', 'CMB', 'NBO', 'LIS', 'LAX']) | |
| preferences | No | Preferences: 'no-lcc', 'lounge-access', 'short-layovers', 'surface-ok' |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description carries full burden. It discloses the output (individually-ticketable segments with carrier recommendations) and scenarios handled (mixed carriers, LCCs, Gulf bridge connections, surface sectors). However, it does not mention side effects, auth needs, or statefulness, which would enhance transparency.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Four sentences, each earning its place: core purpose, handling details, credibility statement, usage guidance. No fluff, front-loaded with key info.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given complexity (4 params, no output schema, no annotations), the description explains the tool's role and niche well. It lacks details on return format or what 'carrier recommendations' entail, but is sufficient for an agent to understand when and why to invoke it.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so baseline is 3. The description adds context about why you'd use the tool (complex itineraries) but does not elaborate on individual parameters beyond what schema already provides. It helps understand overall purpose but not per-parameter semantics.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool breaks complex multi-city itineraries into individually-ticketable segments with carrier recommendations. It specifies the verb 'break' and resource 'multi-city itinerary', and distinguishes from sibling tools by mentioning handling routes that don't fit alliance fare rules, mixed carriers, etc.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly says 'Use this for any route with 4+ stops, backtracking, or region combinations that alliance fares can't cover,' giving clear when-to-use guidance. It implies when not to use (simpler routes) but does not name specific alternatives.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recommend the best fare product type for a route — RTW, Circle Pacific, Circle Atlantic, Open Jaw, or Custom Multi-City. Considers stop count, direction, and backtracking to match the right alliance fare structure.
| Name | Required | Description | Default |
|---|---|---|---|
| cities | Yes | Ordered list of IATA city/airport codes | |
| isOneDirection | No | Is the route traveling continuously in one direction (east or west)? | |
| includeBacktracking | No | Does the route backtrack or zigzag between regions? |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden for behavioral disclosure. It does not detail side effects, authentication needs, rate limits, or what happens with invalid inputs. The description only covers purpose, not runtime behavior.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence with a clear list of outputs and criteria. It is front-loaded with the main action and contains no filler or redundant information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool has 3 parameters, no output schema, and no annotations. The description explains the purpose and high-level logic but does not describe return format or success/failure conditions. For a recommendation tool, an agent might need to know what the output looks like (e.g., JSON structure with fare product type). Thus, completeness is adequate but not thorough.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, but the description adds meaning beyond parameter names by linking them to fare product logic (e.g., 'direction' and 'backtracking' correspond to isOneDirection and includeBacktracking). This helps an agent understand how parameters influence the recommendation.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: recommend the best fare product type for a route, listing specific examples (RTW, Circle Pacific, Circle Atlantic, Open Jaw, Custom Multi-City). It also mentions key criteria considered (stop count, direction, backtracking), making it distinguishable from sibling tools like custom_route_build or plan_route.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no explicit guidance on when to use this tool versus alternatives. It implies usage for fare product recommendation but does not state when not to use it or mention prerequisites. Sibling tools like route_validate or hub_check serve different purposes, but no comparison is given.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Check the best connection between two airports. Identifies dead legs (routes that fail on alliance fares), suggests hub routing fixes, and shows proven carrier combinations. Essential for transpacific, kangaroo, and intra-Asia routing.
| Name | Required | Description | Default |
|---|---|---|---|
| to | Yes | Destination IATA airport code (e.g. 'JFK') | |
| from | Yes | Origin IATA airport code (e.g. 'SYD') | |
| alliance | No | Preferred alliance: 'star' or 'oneworld' |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden. It discloses the tool's behavior: checks connections, identifies dead legs, suggests fixes, and shows carrier combos. It does not mention permissions or side effects, but the behavior is sufficiently transparent for a read-like analysis tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise with three sentences: first states purpose, then lists capabilities, then gives use cases. It is front-loaded and contains no redundant or irrelevant information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity and absence of output schema, the description covers purpose and usage well. It explains what the tool does and when to use it, but lacks explicit information about output format or return values, which could be inferred from the described behaviors.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Input schema has 100% coverage with descriptions for each parameter. The description adds context about alliance fares but does not elaborate on parameters beyond what the schema provides. Baseline score of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool checks the best connection between two airports and lists specific capabilities like identifying dead legs and suggesting hub routing fixes. It also distinguishes from siblings by focusing on hub routing and alliance fares, making it essential for specific routing contexts.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides clear context on when to use the tool, citing transpacific, kangaroo, and intra-Asia routing. However, it does not explicitly state when not to use it or compare with sibling tools, missing an opportunity to guide selection.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
The primary entry point for any multi-city trip. Give it your cities — it automatically evaluates Star Alliance RTW, oneworld RTW, AND custom mixed-carrier builds, then recommends the best approach. Handles direction detection, backtracking analysis, alliance feasibility, surface sectors, and carrier selection. The customer doesn't need to know if their trip is alliance or custom — this tool figures it out.
| Name | Required | Description | Default |
|---|---|---|---|
| pax | No | Number of passengers | |
| budget | No | Budget tier — affects carrier selection and fare strategy | |
| cities | Yes | Ordered list of IATA city/airport codes (e.g. ['LAX', 'NRT', 'BKK', 'LIS', 'LAX']) | |
| preferences | No | Travel preferences: 'no-lcc', 'lounge-access', 'short-layovers', 'surface-ok' |
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 discloses that the tool automatically evaluates three types of builds, handles direction detection, backtracking, and carrier selection, which provides sufficient behavioral insight for a computational tool. It does not discuss failure modes or concurrency, but is adequate.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is four sentences long, front-loaded with the primary purpose ('primary entry point for any multi-city trip'). Each sentence adds meaningful information without being verbose, though could be slightly tighter.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema, the description adequately covers the tool's role as a primary analysis tool. It explains inputs and internal logic sufficiently for an agent to decide when to invoke it. Lacks return value description but is acceptable for this type of tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% (all parameters have descriptions), baseline is 3. The description adds value beyond the schema by explaining that 'budget affects carrier selection' and 'cities are ordered list', and that preferences are travel preferences, which clarifies usage.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly defines this as the primary entry point for multi-city trips, automatically evaluating different alliance builds and recommending the best approach. It distinguishes itself from sibling tools like custom_route_build (which likely requires manual input) and route_suggest.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description states it is the 'primary entry point', implying it should be used first for multi-city trips. It outlines what the tool handles (direction detection, backtracking, alliance feasibility, etc.), but does not explicitly state when to use alternatives or provide exclusions, though the context is clear.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get suggested multi-stop flight routings based on regions, direction, and alliance preference. Returns up to 3 proven routing templates with bookability ratings. Great for trip planning inspiration.
| Name | Required | Description | Default |
|---|---|---|---|
| regions | Yes | Regions to visit: 'asia', 'europe', 'oceania', 'americas', 'africa', 'middle east', 'south america' | |
| alliance | No | Preferred alliance: 'star' or 'oneworld' | |
| maxStops | No | Maximum number of stops (legs). 3-6 recommended for best bookability. | |
| tripType | No | Trip type hint: 'honeymoon', 'backpacker', 'business', 'family', etc. | |
| direction | No | Travel direction preference |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description must fully disclose behavior. It mentions returns templates with ratings, suggesting read-only operation, but does not state mutability, authentication needs, or error handling. Moderately transparent but incomplete.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two concise sentences. The most critical information (what the tool does and its output) is front-loaded. No redundant phrasing.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given 5 parameters, no output schema, and no annotations, the description lacks details on return format, error scenarios, and edge cases. It says 'returns up to 3 templates' but does not define what a 'template' contains, leaving potential ambiguity for an agent.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so baseline is 3. The description repeats parameter concepts (regions, direction, alliance) without adding new semantics beyond what the schema already provides.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it suggests multi-stop flight routings based on regions, direction, and alliance, which differentiates it from siblings like custom_route_build or plan_route. However, it could more explicitly contrast with these alternatives.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies use for trip planning inspiration but does not specify when not to use it or mention alternative tools for other tasks. No explicit guidance on prerequisites or context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Validate a multi-city flight routing for feasibility. Checks alliance carrier rules, identifies dead legs, warns about poison carriers, and estimates bookability. Use this before building an itinerary to catch routing problems early.
| Name | Required | Description | Default |
|---|---|---|---|
| cities | Yes | Ordered list of IATA city/airport codes (e.g. ['LAX', 'NRT', 'BKK', 'LHR', 'LAX']) | |
| alliance | No | Preferred alliance: 'star' or 'oneworld' | |
| carriers | No | Optional carrier codes for each leg (e.g. ['NH', 'TG', 'BA', 'BA']) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the burden. It discloses core behaviors: checking alliance rules, dead legs, poison carriers, and estimating bookability. This provides insight beyond the schema, though it doesn't explicitly state read-only nature or 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.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences with no filler. The first sentence states the purpose, the second gives usage guidance. Every word earns its place.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given 3 parameters with full schema coverage and no output schema, the description explains the tool's functionality well. However, it omits details about the return format (e.g., a boolean or list of issues), which could be important for an agent.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so baseline is 3. The description adds context about ordered IATA codes and optional per-leg carriers, but the schema already describes parameters well. The description doesn't significantly enhance parameter understanding beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool validates multi-city flight routing feasibility, checking alliance rules, dead legs, poison carriers, and bookability. This distinguishes it from sibling tools like custom_route_build or fare_product_match.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
It explicitly advises using this tool before building an itinerary to catch problems early, giving clear context. It doesn't list specific alternatives or when not to use, but the guidance is sufficient.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Create a trip idea in AirTreks APEX system — hands off to a human consultant. Automatically runs plan_route to include full routing analysis, carrier recommendations, and consultant value assessment in the lead. The consultant starts informed, not cold. Use this when the customer is ready to get a real quote.
| Name | Required | Description | Default |
|---|---|---|---|
| name | No | Customer full name | |
| cabin | No | Cabin class preference | |
| dates | No | Departure dates for each leg (ISO format, e.g. '2026-09-15') | |
| Yes | Customer email address (required) | ||
| notes | No | Additional notes or special requests from the customer | |
| phone | No | Customer phone number | |
| budget | No | Budget tier | |
| cities | Yes | Ordered list of IATA city/airport codes | |
| passengers | No | Number of passengers (default 1) | |
| preferences | No | Travel preferences: 'no-lcc', 'lounge-access', 'short-layovers', 'surface-ok' | |
| agentContext | No | Summary of what the AI agent learned about this trip (auto-generated routing analysis, customer preferences discussed, etc.) | |
| flexibleDates | No | Are travel dates flexible? |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description carries burden. It discloses that it automatically runs plan_route and that the consultant starts informed. Does not mention permissions or side effects, but for a creation tool, adequate.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences, front-loaded with main action, efficient and no wasted words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Covers purpose, process, and usage context. Lacks info on return value or system response, but acceptable given the tool's nature and no output schema.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, baseline is 3. Description adds no extra insight beyond schema; mentions automatic plan_route but does not elaborate on parameter usage.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Clearly states the action ('Create a trip idea') and the outcome ('hands off to a human consultant'). Distinguishes from sibling tools by mentioning it automatically runs plan_route.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly says 'Use this when the customer is ready to get a real quote.' Implies that for routing analysis alone, plan_route might be used separately, but no explicit alternatives listed.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
custom_route_buildfare_product_matchhub_checkplan_routeroute_suggestroute_validatetrip_idea_createMost tools have distinct purposes, but 'plan_route' and 'custom_route_build' both handle custom routing; descriptions clarify that 'plan_route' is the primary entry point while 'custom_route_build' is for complex cases.
All tool names follow a consistent verb_noun pattern with snake_case (e.g., 'custom_route_build', 'fare_product_match', 'hub_check'). No mixed conventions or ambiguous names.
Seven tools cover the core workflow of multi-city trip planning: planning, custom building, fare matching, hub checking, route suggestion, validation, and lead creation. This scope is well-balanced.
The tool set covers the main planning and validation needs, but lacks update/delete operations for trip ideas, which may require human follow-up. This is a minor gap given the domain.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Flight Intelligence MCP — search, cheapest dates, multi-city, airline compare via Google Flights
Official airline award MCP. Search 12.3M+ award flights across 48 loyalty programs.
MCP server for Travel & Transportation
Skiplagged MCP Server for flight search, hotel booking, and travel planning
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/Airtreks/airtreks-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
