levels.fyi から報酬データを照会するためのMCPサーバー。
サーバー名: MyPlayground
ツール:
calculate_addition(a: int, b: int) -> int
get_mock_weather(city: str) -> str (モックの天気、実際のAPIデータではありません)
generate_username(base_name: str, add_numbers: bool = true) -> str
Related MCP server: FastMCP Demo Server
このセクションは、CursorでMCPサーバーをインストールして実行したいユーザー向けです。
Python >=3.11
Cursorがプロジェクト環境を直接使用するように uv run を使用してください。
{
"mcpServers": {
"user-MyPlayground": {
"command": "uv",
"args": ["run", "python", "main.py"],
"cwd": "/absolute/path/to/levels-fyi-mcp"
}
}
}CursorのMCP設定を開き、上記サーバー設定を追加します。
cwd がこのリポジトリのローカルクローンを指していることを確認します。
CursorでMCPサーバーを開始/リロードします。
calculate_addition、get_mock_weather、generate_username などのツールを呼び出します。
fastmcp コマンドを使用する場合Cursorで command: "fastmcp" を使用したい場合は、グローバルツールとしてインストールしてください:
uv tool install fastmcpCursorが fastmcp を見つけられない場合は、上記の推奨される uv run 設定を使用してください。
このセクションは、コード変更を行う貢献者向けです。
プロジェクトルートから実行:
uv syncuv run python main.pyuv add <package>
uv syncuv run python -c "import fastmcp; print('fastmcp ok')".
├── main.py
├── pyproject.toml
└── README.md原因: Cursorが fastmcp 実行ファイルを見つけられません。
解決策:
uv run python main.py を使用するCursor設定を優先する、または
uv tool install fastmcp でグローバルツールをインストールし、PATHにuvツールのbin（通常は ~/.local/bin）が含まれていることを確認する。
generate_username.add_numbers は数値や文字列ではなく、ブール値 (true/false) である必要があります。
get_mock_weather はデモ用にランダム化されたモックデータを返します。
ツールログは main.py から出力され、サーバーの出力に表示されます。
REQUIRED: Call this tool FIRST to find the company's specific level names (e.g., '63', 'L5', 'E4') versus the industry 'Standard' ladder. 'role' must be the full name: 'Software Engineer', 'Product Manager', etc.
| Name | Required | Description | Default |
|---|---|---|---|
| company_name | Yes | ||
| role | No | Software Engineer |
| Name | Required | Description |
|---|---|---|
No output parameters | ||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden. It discloses that the tool should be called first (a behavioral trait) but does not mention side effects, permissions, rate limits, or output structure beyond 'find level names'. The lack of behavioral details reduces 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?
Two sentences with no fluff. The first sentence front-loads the requirement and purpose. The second gives a concrete parameter rule. 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 the presence of an output schema (though not shown), the description adequately covers the tool's role as a prerequisite mapping function. It explains the core action and parameter requirements, sufficient for an agent to use it correctly in context with its sibling.
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 0%, so description must compensate. It adds meaning for 'role' (must be full name, gives examples) and implies 'company_name' as the company. This provides significant guidance beyond the raw schema, though company_name is not explicitly described.
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: 'find the company's specific level names versus the industry Standard ladder.' It uses a specific verb 'find' and resource 'level mapping', distinguishing it from the sibling tool 'get_recent_offers'.
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 explicitly says 'Call this tool FIRST' and specifies that 'role must be the full name'. It implies a prerequisite relationship to other tools, but does not explicitly state when not to use or provide alternatives.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Fetch the most recent specific salary offers for a given role to gauge current market trends. Example: company_name='Amazon', role='Software Engineer', level='SDE II'
Location must be a single city name (e.g., 'Seattle'). If the city is ambiguous, the most major tech hub will be chosen by default
| Name | Required | Description | Default |
|---|---|---|---|
| company_name | Yes | ||
| role | Yes | ||
| level | Yes | ||
| location | No |
| Name | Required | Description |
|---|---|---|
No output parameters | ||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden. It mentions location ambiguity handling but fails to disclose any other behavioral traits like data freshness, number of offers returned, or authorization needs.
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 plus an example, with no redundant information. It is front-loaded and gets straight to the point.
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?
Despite having an output schema, the description lacks important context such as how 'recent' is defined, the number of offers fetched, and any default behavior for the optional location parameter.
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 description coverage is 0%, yet the description only adds meaning for 'location' (single city name) and indirectly for the other parameters through the example. It provides minimal additional semantics beyond the parameter names.
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 verb 'Fetch' and the resource 'specific salary offers' with a purpose 'to gauge current market trends'. It distinguishes from the sibling 'get_level_mapping' by focusing on offers for a given role.
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 an example and a note on location format and ambiguity resolution, but does not explicitly state when to use this tool versus alternatives or any prerequisites.
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.
v1.0.0calculate_additiongenerate_usernameget_level_mappingget_mock_weatherget_recent_offersv0.1.0calculate_additiongenerate_usernameget_mock_weatherScored across 2 tools
The two tools have completely distinct purposes: one maps company-specific levels to standard ladders, the other fetches recent salary offers. No overlap in functionality.
Both tools use a consistent verb_noun pattern in snake_case: get_level_mapping and get_recent_offers, following the same style.
With only 2 tools, the server feels underdeveloped for its likely domain (compensation research). More tools like search by company or role would be expected, but the set is not extreme.
The surface covers level mapping and recent offers but lacks tools for discovering companies, roles, or historical salary trends. Some standard operations are missing, but core use cases are addressed.
Generate synthetic random user data for testing, demos, and development without using real persona.
Generate IDs, QR codes, and hashes, encode values, geolocate IPs, plus gated host diagnostics.
Developer utilities: color conversion, WCAG contrast, timestamps, UUIDs, and hashing.
Geocoding, weather forecasts, and timezone lookups
