MantisBT MCP server – manage issues, notes, files, tags, and relationships. With semantic search.
io.github.dpesch/mantisbt-mcp-server
Local install
STDIO
2 required env vars
How models use it and what it is built for.
MantisBT MCP server – manage issues, notes, files, tags, and relationships. With semantic search.
Local install — runs as a subprocess.
Configuration this server reads at startup.
Base URL of the MantisBT REST API, e.g. https://your-mantis.example.com/api/rest
MantisBT API key (Profile → API Tokens in MantisBT)
Directory for the metadata cache. Defaults to ~/.cache/mantisbt-mcp
Metadata cache TTL in seconds. Default: 3600 (1 hour)
Transport mode. 'stdio' for local use (default), 'http' for remote/team deployments
HTTP port when TRANSPORT=http. Default: 3000
Bind address when TRANSPORT=http. Default: 127.0.0.1 (local only). Use 0.0.0.0 for Docker/remote.
Optional Bearer token to protect the /mcp endpoint when TRANSPORT=http
Enable offline semantic search (requires ~80 MB model download on first use)
Vector store backend for semantic search. 'vectra' (default, pure JS) or 'sqlite-vec' (faster for >10k issues)
Directory for the semantic search index. Defaults to ~/.cache/mantisbt-mcp/search
Hugging Face model for embeddings. Default: Xenova/paraphrase-multilingual-MiniLM-L12-v2
ONNX inference threads for the embedding model. Default: 1
If set, restricts file uploads to this directory (path traversal protection)
Where to find authoritative docs and source for MantisBT MCP Server.
MCP Playground runs 10,000+ hosted MCP servers — GitHub, Linear, Notion, Stripe, Sentry and more — across Claude, GPT, Gemini, DeepSeek and 30+ AI models. Compare model answers side-by-side, save agent presets, share runs. Zero install.
Open Agent Studio