加载中…
Extracts PDF text locally, with macOS PDFKit and Vision OCR fallbacks and optional AI retry.
PDF To Text 是 ChatHome Skills 收录的 MCP 条目，来源为 Official MCP Registry，质量分 78/100。 作为 Model Context Protocol 服务器，它向 Claude、Cursor、Copilot 等兼容 MCP 的 LLM 客户端暴露可直接调用的工具，让 agent 的能力超出模型内置范围。 该条目由 ChatHome Skills 的每日抓取从官方 registry 和 GitHub 发现查询中收录，每次运行都会重新核验仓库事实、新鲜度信号和安装元数据。 质量分综合了官方 registry 收录情况、可用安装命令、许可证完整性、仓库活跃度和 GitHub star 趋势，完整算法说明见来源页。安装命令已列于上方，可直接复制使用。 在将 PDF To Text 加入生产 agent 工作流前，请核对上方的最近更新日期和仓库状态——下方事实快照是最近一次抓取的时点值。
npx -y @jim-panse/pdf-to-text-mcp@0.7.0运行此命令前，请先核对上游源码。
{
"_meta": {
"io.modelcontextprotocol.registry/official": {
"status": "active",
"isLatest": true,
"updatedAt": "2026-10-15T12:15:52.697115Z",
"publishedAt": "2026-10-15T12:15:52.697115Z",
"statusChangedAt": "2026-10-15T12:15:52.697115Z"
}
},
"server": {
"name": "io.github.Jim-Panse/pdf-to-text",
"title": "PDF To Text",
"$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
"version": "0.7.0",
"packages": [
{
"version": "0.7.0",
"transport": {
"type": "stdio"
},
"identifier": "@jim-panse/pdf-to-text-mcp",
"registryType": "npm",
"registryBaseUrl": "https://registry.npmjs.org",
"environmentVariables": [
{
"name": "PDF_TO_TEXT_MCP_ROOT",
"isRequired": true,
"description": "Required existing directory that defines the root-relative filesystem namespace for PDF input and derived text output."
},
{
"name": "OPENAI_API_KEY",
"isSecret": true,
"description": "Optional secret. Enables one AI extraction retry when local extraction is inadequate; omit for local-only operation."
},
{
"name": "OPENAI_MODEL",
"description": "Optional OpenAI model used only for AI retry. Defaults to gpt-5.4-mini.",
"placeholder": "gpt-5.4-mini"
},
{
"name": "AI_MAX_OUTPUT_TOKENS",
"default": "32000",
"description": "Optional cap for all AI-generated output tokens, including non-visible reasoning tokens. Integer minimum 800; defaults to 32000.",
"placeholder": "32000"
},
{
"name": "MAX_PARALLEL_EXTRACTIONS",
"description": "Integer concurrency limit from 1 to 32. Defaults to min(os.availableParallelism(), 4)."
},
{
"name": "EXTRACTION_QUEUE_CAPACITY",
"default": "10",
"description": "Integer maximum waiting requests from 0 to 100; zero disables waiting."
},
{
"name": "EXTRACTION_QUEUE_WAIT_MS",
"default": "60000",
"description": "Maximum queue wait in milliseconds, integer 1 through 2147483647. Does not limit active work."
},
{
"name": "WRITE_TEXT",
"format": "boolean",
"choices": [
"false",
"true"
],
"default": "false",
"description": "Optionally save successful extraction text beside the source PDF."
}
]
}
],
"repository": {
"url": "https://github.com/Jim-Panse/PDF-to-TXT-MCP",
"source": "github"
},
"description": "Extracts PDF text locally, with macOS PDFKit and Vision OCR fallbacks and optional AI retry."
}
}