{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_6b4afrytc74c","handle":"siliconflow-mcp-server","url":"https://wellknown.network/agents/siliconflow-mcp-server","links":{"self":"https://wellknown.network/agents/siliconflow-mcp-server/record.json","html":"https://wellknown.network/agents/siliconflow-mcp-server","markdown":"https://wellknown.network/agents/siliconflow-mcp-server/record.md","api":"https://wellknown.network/api/v1/agents/siliconflow-mcp-server","status":"https://wellknown.network/api/v1/agents/siliconflow-mcp-server/status","claim":"https://wellknown.network/agents/siliconflow-mcp-server/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/siliconflow-mcp-server/claim.json","badge":"https://wellknown.network/agents/siliconflow-mcp-server/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/siliconflow-mcp-server/history","tools":"https://wellknown.network/api/v1/agents/siliconflow-mcp-server/tools"},"ard":{"identifier":"urn:air::server:siliconflow-mcp-server","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"siliconflow-mcp-server","summary":"MCP Server for siliconflow","description":"# siliconflow-mcp-server\n\n一个基于 MCP 协议的 SiliconFlow AI API 服务器包，用于集成到支持 MCP 协议的应用程序中。\n\n## 功能特性\n\n- 提供 SiliconFlow 图像生成 API 接口\n- 兼容 MCP 协议，可与 Cursor 等工具无缝集成\n- 简单易用的工具函数\n- 支持通过环境变量配置 API Key\n\n## 安装方法\n\n通过 pip 安装：\n\n```bash\npip install siliconflow_mcp_server\n```\n\n通过 uv 安装：\n\n```bash\nuvx pip install siliconflow_mcp_server\n```\n\n## 使用方法\n\n### 命令行运行\n\n```bash\n# 使用普通方式运行\nsiliconflow-mcp-server\n\n# 使用 uvx 运行\nuvx siliconflow-mcp-server\n```\n\n### 环境变量配置\n\n在使用前，**必须**设置 SiliconFlow API Key 环境变量：\n\n```bash\nexport SILICONFLOW_APIKEY=\"sk-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx\"\n```\n\n你可以从 [SiliconFlow 官网](https://siliconflow.cn) 获取 API Key。\n\n### MCP 配置\n\n在支持 MCP 的应用程序（如 Cursor）中，添加以下配置到 MCP 配置文件中（通常位于 `~/.cursor/mcp.json`）：\n\n```json\n{\n  \"mcpServers\": {\n    \"siliconflow-mcp-server\": {\n      \"command\": \"uvx\",\n      \"args\": [\n        \"siliconflow-mcp-server\"\n      ],\n      \"env\": {\n        \"SILICONFLOW_APIKEY\": \"sk-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx\"\n      }\n    }\n  }\n}\n```\n\n配置完成后，重启支持 MCP 的应用程序（如 Cursor），即可使用 `@siliconflow-mcp-server` 调用相关工具。\n\n## 可用工具\n\n### 图像生成 (generate_image)\n\n使用 SiliconFlow 的 AI 模型生成图像：\n\n```python\n@mcp.tool()\ndef generate_image(prompt: str, width: int, height: int) -> str:\n    \"\"\"\n    根据提示生成图片，返回图片URL\n    \n    参数:\n        prompt: 图片生成的文本提示（必须是英文）\n        width: 生成图片的宽度（像素）\n        height: 生成图片的高度（像素）\n    \n    返回:\n        生成的图片 URL\n    \"\"\"\n```\n\n#### 调用示例\n\n在 Cursor 中，可以这样调用：\n\n```\n@siliconflow-mcp-server generate_image(\"a beautiful landscape with mountains and lakes\", 1024, 1024)\n```\n\n#### 默认参数\n\n- 使用模型: black-forest-labs/FLUX.1-schnell\n- 推理步数: 8\n- 指导缩放: 3.5\n- 批量大小: 1\n\n## 技术说明\n\n本服务器基于 MCP (Model Control Protocol) 协议，通过 `stdio` 传输方式与客户端通信，可以很容易地与支持 MCP 协议的应用程序集成。\n\n## 开发说明\n\n1. 克隆项目\n2. 安装依赖：`pip install -e .`\n3. 开发新功能\n4. 构建：`python -m build`\n5. 发布：`python -m twine upload dist/*`\n\n## 问题排查\n\n- 如果遇到 `ModuleNotFoundError: No module named 'siliconflow_mcp_server'` 错误，请确保已正确安装包\n- 如果使用 uvx 运行遇到问题，可以尝试 `uvx pip install --find-links=dist/ siliconflow_mcp_server`\n\n## 许可证\n\nMIT","publisher":null,"homepage":null,"repository":null,"version":"0.3.6","license":null,"protocols":["mcp"],"tags":["mcp"],"pricing":null,"endpoints":[{"url":"pypi:siliconflow-mcp-server","type":"package_pypi","auth":null,"probeable":false}],"skills":null,"tools":null,"extra":null,"attribution":{"kind":"pypi","name":"pypi","summary":"pypi","version":"pypi","description":"pypi"}},"derived":{"capabilities":[{"slug":"media.image-generation","name":"Image Generation","confidence":0.825,"provenance":"derived"}],"categories":["media"],"language":"en"},"observed":{"status":"unknown","statusReason":"Distributed as a package to run locally; no network endpoint to check.","lastOkAt":null,"lastProbedAt":null,"statusComputedAt":null,"reliability30d":null,"latestObservations":[],"tools":null,"package":{"name":"siliconflow-mcp-server","registry":"pypi","observedAt":"2026-11-04T00:27:39.494Z","publishedAt":"2025-05-08T06:14:36.944312Z","latestVersion":"0.3.6"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"siliconflow-mcp-server","url":"https://pypi.org/project/siliconflow-mcp-server/","firstSeenAt":"2026-09-10T12:22:08.314Z","fetchedAt":"2026-11-04T00:26:51.228Z","normalizedAt":"2026-11-04T00:26:51.228Z"}]},"firstSeenAt":"2026-09-10T12:22:08.314Z","updatedAt":"2026-11-04T00:27:39.494Z"}