{"id":23479539,"url":"https://github.com/amidabuddha/unichat-mcp-server","last_synced_at":"2025-08-27T07:31:26.823Z","repository":{"id":265778674,"uuid":"896627964","full_name":"amidabuddha/unichat-mcp-server","owner":"amidabuddha","description":null,"archived":false,"fork":false,"pushed_at":"2025-07-09T15:09:24.000Z","size":224,"stargazers_count":36,"open_issues_count":1,"forks_count":7,"subscribers_count":2,"default_branch":"main","last_synced_at":"2025-07-09T16:27:28.165Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/amidabuddha.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null}},"created_at":"2024-11-30T21:44:28.000Z","updated_at":"2025-07-09T15:09:27.000Z","dependencies_parsed_at":null,"dependency_job_id":"6cbd9874-d727-4264-aa2a-4b8e3811eb21","html_url":"https://github.com/amidabuddha/unichat-mcp-server","commit_stats":null,"previous_names":["amidabuddha/unichat-mcp-server"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/amidabuddha/unichat-mcp-server","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/amidabuddha%2Funichat-mcp-server","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/amidabuddha%2Funichat-mcp-server/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/amidabuddha%2Funichat-mcp-server/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/amidabuddha%2Funichat-mcp-server/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/amidabuddha","download_url":"https://codeload.github.com/amidabuddha/unichat-mcp-server/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/amidabuddha%2Funichat-mcp-server/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":272304639,"owners_count":24910603,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","status":"online","status_checked_at":"2025-08-27T02:00:09.397Z","response_time":76,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":[],"created_at":"2024-12-24T19:30:09.980Z","updated_at":"2025-08-27T07:31:26.818Z","avatar_url":"https://github.com/amidabuddha.png","language":"Python","funding_links":[],"categories":["LLM Bridges","AI Integration MCP Servers","🤖 AI/ML","MCP 服务器精选列表","Legend","サーバー実装","MCP Servers","Aggregators","APIs and HTTP Requests","Server Implementations","Table of Contents"],"sub_categories":["Trading \u0026 Exchanges","🛠️ 其他实用工具与集成","🛠️ \u003ca name=\"other-tools-and-integrations\"\u003e\u003c/a\u003eOther Tools and Integrations","🛠️ \u003ca name=\"other-tools-and-integrations\"\u003e\u003c/a\u003eその他のツールと統合","🛠️ Other Tools and Integrations","How to Submit","AI Services"],"readme":"# Unichat MCP Server in Python\nAlso available in [TypeScript](https://github.com/amidabuddha/unichat-ts-mcp-server)\n--\n \u003ch4 align=\"center\"\u003e\n  \u003ca href=\"https://mseep.ai/app/amidabuddha-unichat-mcp-server\"\u003e\n  \u003cimg src=\"https://mseep.net/pr/amidabuddha-unichat-mcp-server-badge.png\" alt=\"MseeP.ai Security Assessment Badge\" /\u003e\n  \u003c/a\u003e\n \u003c/h4\u003e\n  \u003ch4 align=\"center\"\u003e\n  \u003ca href=\"https://github.com/amidabuddha/unichat-mcp-server/blob/main/LICENSE.md\"\u003e\n  \u003cimg src=\"https://img.shields.io/github/license/amidabuddha/unichat-mcp-server\" alt=\"Released under the MIT license.\" /\u003e\n  \u003c/a\u003e\n  \u003ca href=\"https://archestra.ai/mcp-catalog/amidabuddha__unichat-mcp-server\"\u003e\n    \u003cimg src=\"https://archestra.ai/mcp-catalog/api/badge/quality/amidabuddha/unichat-mcp-server\" alt=\"Trust Score\" /\u003e\n  \u003c/a\u003e\n  \u003ca href=\"https://smithery.ai/server/unichat-mcp-server\"\u003e\n    \u003cimg src=\"https://smithery.ai/badge/unichat-mcp-server\" alt=\"Smithery Server Installations\" /\u003e\n  \u003c/a\u003e\n\u003c/h4\u003e\n \u003ch4 align=\"center\"\u003e\n  \u003ca href=\"https://mcphub.com/mcp-servers/amidabuddha/unichat-mcp-server\"\u003e\n  \u003cimg src=\"https://img.mcphub.com/_next/image?url=%2Flogo-dark.png\u0026w=48\u0026q=75\" alt=\"Hosted at MCPHub\" /\u003e\n  \u003c/a\u003e\n \u003c/h4\u003e\n\nSend requests to OpenAI, MistralAI, Anthropic, xAI, Google AI, DeepSeek, Alibaba, Inception using MCP protocol via tool or predefined prompts.\nVendor API key required\n\n### Tools\n\nThe server implements one tool:\n- `unichat`: Send a request to unichat\n  - Takes \"messages\" as required string arguments\n  - Returns a response\n\n### Prompts\n\n- `code_review`\n  - Review code for best practices, potential issues, and improvements\n  - Arguments:\n    - `code` (string, required): The code to review\"\n- `document_code`\n  - Generate documentation for code including docstrings and comments\n  - Arguments:\n    - `code` (string, required): The code to comment\"\n- `explain_code`\n  - Explain how a piece of code works in detail\n  - Arguments:\n    - `code` (string, required): The code to explain\"\n- `code_rework`\n  - Apply requested changes to the provided code\n  - Arguments:\n    - `changes` (string, optional): The changes to apply\"\n    - `code` (string, required): The code to rework\"\n\n## Quickstart\n\n### Install\n\n#### Claude Desktop\n\nOn MacOS: `~/Library/Application\\ Support/Claude/claude_desktop_config.json`\nOn Windows: `%APPDATA%/Claude/claude_desktop_config.json`\n\n**Supported Models:**\n\u003e A list of currently supported models to be used as `\"SELECTED_UNICHAT_MODEL\"` may be found [here](https://github.com/amidabuddha/unichat/blob/main/unichat/models.py). Please make sure to add the relevant vendor API key as `\"YOUR_UNICHAT_API_KEY\"`\n\n**Example:**\n```json\n\"env\": {\n  \"UNICHAT_MODEL\": \"gpt-4o-mini\",\n  \"UNICHAT_API_KEY\": \"YOUR_OPENAI_API_KEY\"\n}\n```\nDevelopment/Unpublished Servers Configuration\n```json\n\"mcpServers\": {\n  \"unichat-mcp-server\": {\n    \"command\": \"uv\",\n    \"args\": [\n      \"--directory\",\n      \"{{your source code local directory}}/unichat-mcp-server\",\n      \"run\",\n      \"unichat-mcp-server\"\n    ],\n    \"env\": {\n      \"UNICHAT_MODEL\": \"SELECTED_UNICHAT_MODEL\",\n      \"UNICHAT_API_KEY\": \"YOUR_UNICHAT_API_KEY\"\n    }\n  }\n}\n```\n\nPublished Servers Configuration\n```json\n\"mcpServers\": {\n  \"unichat-mcp-server\": {\n    \"command\": \"uvx\",\n    \"args\": [\n      \"unichat-mcp-server\"\n    ],\n    \"env\": {\n      \"UNICHAT_MODEL\": \"SELECTED_UNICHAT_MODEL\",\n      \"UNICHAT_API_KEY\": \"YOUR_UNICHAT_API_KEY\"\n    }\n  }\n}\n```\n\n### Installing via Smithery\n\nTo install Unichat for Claude Desktop automatically via [Smithery](https://smithery.ai/server/unichat-mcp-server):\n\n```bash\nnpx -y @smithery/cli install unichat-mcp-server --client claude\n```\n\n## Development\n\n### Building and Publishing\n\nTo prepare the package for distribution:\n\n1. Remove older builds:\n```bash\nrm -rf dist\n```\n\n2. Sync dependencies and update lockfile:\n```bash\nuv sync\n```\n\n3. Build package distributions:\n```bash\nuv build\n```\n\nThis will create source and wheel distributions in the `dist/` directory.\n\n4. Publish to PyPI:\n```bash\nuv publish --token {{YOUR_PYPI_API_TOKEN}}\n```\n\n### Debugging\n\nSince MCP servers run over stdio, debugging can be challenging. For the best debugging\nexperience, we strongly recommend using the [MCP Inspector](https://github.com/modelcontextprotocol/inspector).\n\n\nYou can launch the MCP Inspector via [`npm`](https://docs.npmjs.com/downloading-and-installing-node-js-and-npm) with this command:\n\n```bash\nnpx @modelcontextprotocol/inspector uv --directory {{your source code local directory}}/unichat-mcp-server run unichat-mcp-server\n```\n\n\nUpon launching, the Inspector will display a URL that you can access in your browser to begin debugging.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Famidabuddha%2Funichat-mcp-server","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Famidabuddha%2Funichat-mcp-server","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Famidabuddha%2Funichat-mcp-server/lists"}