加载中…
MantisBT MCP server – manage issues, notes, files, tags, and relationships. With semantic search.
MantisBT MCP Server 是 ChatHome Skills 收录的 MCP 条目,来源为 Official MCP Registry,质量分 100/100。 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 MantisBT MCP Server 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 @dpesch/mantisbt-mcp-server@1.14.1运行此命令前,请先核对上游源码。
{
"_meta": {
"io.modelcontextprotocol.registry/official": {
"status": "active",
"isLatest": true,
"updatedAt": "2026-10-24T12:49:28.811362Z",
"publishedAt": "2026-10-24T12:49:28.811362Z",
"statusChangedAt": "2026-10-24T12:49:28.811362Z"
}
},
"server": {
"name": "io.github.dpesch/mantisbt-mcp-server",
"title": "MantisBT MCP Server",
"$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
"version": "1.14.1",
"packages": [
{
"version": "1.14.1",
"transport": {
"type": "stdio"
},
"identifier": "@dpesch/mantisbt-mcp-server",
"runtimeHint": "npx",
"registryType": "npm",
"environmentVariables": [
{
"name": "MANTIS_BASE_URL",
"format": "string",
"isRequired": true,
"description": "Base URL of the MantisBT REST API, e.g. https://your-mantis.example.com/api/rest",
"placeholder": "https://your-mantis.example.com/api/rest"
},
{
"name": "MANTIS_API_KEY",
"format": "string",
"isSecret": true,
"isRequired": true,
"description": "MantisBT API key (Profile → API Tokens in MantisBT)"
},
{
"name": "MANTIS_USE_INDEX_PHP",
"format": "boolean",
"default": "false",
"description": "Use /api/rest/index.php/ for MantisBT installations without URL rewriting. Detected automatically when MANTIS_BASE_URL ends with /api/rest/index.php"
},
{
"name": "MANTIS_CACHE_DIR",
"format": "filepath",
"description": "Directory for the metadata cache. Defaults to ~/.cache/mantisbt-mcp"
},
{
"name": "MANTIS_CACHE_TTL",
"format": "number",
"default": "3600",
"description": "Metadata cache TTL in seconds. Default: 3600 (1 hour)"
},
{
"name": "TRANSPORT",
"format": "string",
"choices": [
"stdio",
"http"
],
"default": "stdio",
"description": "Transport mode. 'stdio' for local use (default), 'http' for remote/team deployments"
},
{
"name": "PORT",
"format": "number",
"default": "3000",
"description": "HTTP port when TRANSPORT=http. Default: 3000"
},
{
"name": "MCP_HTTP_HOST",
"format": "string",
"default": "127.0.0.1",
"description": "Bind address when TRANSPORT=http. Default: 127.0.0.1 (local only). Use 0.0.0.0 for Docker/remote."
},
{
"name": "MCP_HTTP_TOKEN",
"format": "string",
"isSecret": true,
"description": "Optional Bearer token to protect the /mcp endpoint when TRANSPORT=http"
},
{
"name": "MANTIS_SEARCH_ENABLED",
"format": "boolean",
"default": "false",
"description": "Enable offline semantic search (requires ~80 MB model download on first use)"
},
{
"name": "MANTIS_SEARCH_BACKEND",
"format": "string",
"choices": [
"vectra",
"sqlite-vec"
],
"default": "vectra",
"description": "Vector store backend for semantic search. 'vectra' (default, pure JS) or 'sqlite-vec' (faster for >10k issues)"
},
{
"name": "MANTIS_SEARCH_DIR",
"format": "filepath",
"description": "Directory for the semantic search index. Defaults to ~/.cache/mantisbt-mcp/search"
},
{
"name": "MANTIS_SEARCH_MODEL",
"format": "string",
"default": "Xenova/paraphrase-multilingual-MiniLM-L12-v2",
"description": "Hugging Face model for embeddings. Default: Xenova/paraphrase-multilingual-MiniLM-L12-v2"
},
{
"name": "MANTIS_SEARCH_THREADS",
"format": "number",
"default": "1",
"description": "ONNX inference threads for the embedding model. Default: 1"
},
{
"name": "MANTIS_UPLOAD_DIR",
"format": "filepath",
"description": "If set, restricts file uploads to this directory (path traversal protection)"
}
]
}
],
"description": "MantisBT MCP server – manage issues, notes, files, tags, and relationships. With semantic search."
}
}