@firsthandapi/mcp-server
@firsthandapi/mcp-server — FirstHandAPI MCP Server
エージェント向けゼロからジョブへ(ブートストラップモード)
まだAPIキーをお持ちでないですか?それでもサーバーを起動できます — 単一のsignupツールが公開されます:
npx @firsthandapi/mcp-server # no env var neededsignupをorg_nameとemailを指定して呼び出すと、APIキーと$2.50の無料クレジットを受け取れます(キーは一度だけ表示されます — 保存してください)。その後、設定して再起動してください:
claude mcp add firsthandapi -e FIRSTHAND_API_KEY=fh_live_... -- npx @firsthandapi/mcp-serverキーを設定すると、7つのジョブツールすべてが解放されます:create_job、create_job_and_wait、get_job、list_jobs、get_job_files、cancel_job、get_credits。
公式MCPサーバー(FirstHandAPI向け)— ヒューマン・イン・ザ・ループ(HITL)によるクラウドソーシングデータ収集。Claude Code、Cursor、その他のAIエージェントが、自動化されたAI品質スコアリング付きで、実際の人間のワーカーから写真、音声、動画、スクリーン録画を収集できるようにします。
ユースケース:UGC収集、AI評価用のグラウンドトゥルースデータ、マルチモーダルモデル向けのLLMトレーニングデータ。
Related MCP server: simple-fal-mcp
インストール
npm install @firsthandapi/mcp-server設定
Claude Code
{
"mcpServers": {
"firsthand": {
"command": "npx",
"args": ["@firsthandapi/mcp-server"],
"env": {
"FIRSTHAND_API_KEY": "fh_live_your_key_here"
}
}
}
}Cursor
.cursor/mcp.jsonに追加:
{
"firsthand": {
"command": "npx @firsthandapi/mcp-server",
"env": { "FIRSTHAND_API_KEY": "fh_live_..." }
}
}ツール
ツール | 説明 |
| コンテンツ収集ジョブを投稿する |
| ジョブのステータスと詳細を取得する |
| ジョブを投稿し、完了を待つ |
| フィルター付きで全ジョブを一覧表示する |
| オープン中のジョブをキャンセルする |
| ダウンロードURL付きの承認済みファイルを取得する |
| クレジット残高を確認する |
すべてのジョブ作成ツールは、オプションのlocationパラメータを受け付けます:テキストベースの場合は{ city, state }、座標ベースの制約の場合は{ latitude, longitude, radius_km }。
環境変数
FIRSTHAND_API_KEY(必須) — あなたのAPIキーFIRSTHAND_BASE_URL(オプション) — APIベースURL(デフォルト:https://api.firsthandapi.com)FIRSTHAND_TIMEOUT_MS(オプション) — リクエストタイムアウト(デフォルト:30000)
ライセンス
プロプライエタリ
Available Tools
1 toolsignupA
Create a FirstHandAPI buyer account and receive an API key plus $2.50 in free credits. Use this when the server is running without FIRSTHAND_API_KEY. The key is shown ONCE — store it, then restart the MCP server with FIRSTHAND_API_KEY set to unlock the job tools.
| Name | Required | Description | Default |
|---|---|---|---|
| Yes | Contact email for the account (must not be a disposable address) | ||
| org_name | Yes | Organization or project name |
TDQS
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 the critical behavioral trait that the API key is shown only once and that the server must be restarted with FIRSTHAND_API_KEY. It does not cover failure modes or response details, but the most important operational quirk is clearly communicated.
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 three sentences with no filler. It front-loads the action and outcome, then adds necessary operational guidance. Every sentence 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?
For a simple two-parameter setup tool with no output schema, the description covers the purpose, the trigger condition, and the critical one-time-key warning. It could be slightly more explicit about the response format, but the operational guidance is strong enough to make the tool usable.
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 100%, with both email and org_name already described in the input schema. The tool description adds no parameter-specific meaning beyond the schema, so the 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 uses a specific verb ('Create') with a clear resource ('FirstHandAPI buyer account') and states concrete outcomes (API key plus $2.50 in credits). This makes the tool's function unmistakable even without sibling tools.
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 states when to use the tool: 'when the server is running without FIRSTHAND_API_KEY.' It also provides clear follow-up steps (store the key, restart the MCP server, set the env var) and explains the purpose ('unlock the job tools').
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.
1 tool update
v0.2.0- First observed
signup
TDQS
Scored across 1 tool
Only one tool exists, so there is no possibility of confusion or overlap. Its purpose is clearly defined as account creation and API key retrieval.
With a single tool, naming is perfectly consistent by definition. The verb-form 'signup' is clear and unambiguous, even if it doesn't follow a verb_noun pattern.
The server's own description mentions 'job tools' that will be unlocked after restart, yet only signup is exposed. A single tool is too few for the apparent broader API scope, making the tool set feel thin and incomplete.
The server is described as a FirstHandAPI MCP server with the intent to provide job tools, but only signup is available. This creates a severe gap—users can create an account but cannot perform any actual job operations, leaving the advertised surface almost entirely absent.
Maintenance
Related MCP Connectors
MCP server that lets AI assistants use all OneSchema features exposed via the public API.
MCP Server for an Agent Task Marketplace
MCP server for building and testing AI agents with multi-model experimentation and insights.
MCP server for your apps' tools and custom tools, plus hosted AI agents and approval-gated workflows
Related MCP Servers
- AlicenseAqualityBmaintenanceMCP server for instruckt visual annotations. Enables AI agents to retrieve pending annotations, view screenshots, and resolve annotations.321 npmMIT
- AlicenseNot gradedqualityDmaintenanceMCP server for fal model discovery, execution, pricing, and local media processing, enabling AI model workflows via natural language.74 npmMIT
- AlicenseNot gradedqualityDmaintenanceMCP server for AgentHire, an AI talent marketplace enabling agents to browse jobs, apply, manage interviews, and handle offers. Supports employer job creation, candidate matching, and compliance tips.6 npmMIT
- FlicenseBqualityDmaintenanceMCP server for building a user-approved transcript corpus from Handy, optimizing post-processing prompts against LM Studio, and promoting winning inference settings.19-