MantisBT MCP Server

Host a copy with our keys and logs.

• MANTIS_BASE_URL — Base URL of the MantisBT REST API, e.g. https://your-mantis.example.com/api/rest
• MANTIS_API_KEY — MantisBT API key (Profile → API Tokens in MantisBT)
• MANTIS_USE_INDEX_PHP — Use /api/rest/index.php/ for MantisBT installations without URL rewriting. Detected automatically when MANTIS_BASE_URL ends with /api/rest/index.php
• MANTIS_CACHE_DIR — Directory for the metadata cache. Defaults to ~/.cache/mantisbt-mcp; each base URL and API key gets its own subdirectory
• MANTIS_CACHE_TTL — Metadata cache TTL in seconds. Default: 3600 (1 hour)
• TRANSPORT — Transport mode. 'stdio' for local use (default), 'http' for remote/team deployments
• PORT — HTTP port when TRANSPORT=http. Default: 3000
• MCP_HTTP_HOST — Bind address when TRANSPORT=http. Default: 127.0.0.1 (local only). Use 0.0.0.0 for Docker/remote.
• MCP_HTTP_TOKEN — Bearer token protecting the /mcp endpoint. Required when TRANSPORT=http; the server refuses to start without it
• MCP_HTTP_MAX_BODY_SIZE — Largest accepted /mcp request body in bytes when TRANSPORT=http. Default: 67108864 (64 MB)
• MANTIS_SEARCH_ENABLED — Enable offline semantic search (requires ~80 MB model download on first use)
• MANTIS_SEARCH_BACKEND — Vector store backend for semantic search. 'vectra' (default, pure JS) or 'sqlite-vec' (faster for >10k issues)
• MANTIS_SEARCH_DIR — Directory for the semantic search index. Defaults to the search subdirectory of the instance cache directory; when set, each base URL and API key gets its own subdirectory
• MANTIS_SEARCH_MODEL — Hugging Face model for embeddings. Default: Xenova/paraphrase-multilingual-MiniLM-L12-v2
• MANTIS_SEARCH_THREADS — ONNX inference threads for the embedding model. Default: 1
• MANTIS_UPLOAD_DIR — If set, restricts file uploads to this directory (path traversal protection)