mantisbt-mcp-server

MantisBT MCP Server

MantisBT MCP server – manage issues, notes, files, tags, and relationships. With semantic search.

stdiocommunityapplication

Transportstdio

Runtimenpx

MANTIS_BASE_URL(str)

Required

Base URL of the MantisBT REST API, e.g. https://your-mantis.example.com/api/rest

MANTIS_API_KEY(str)

RequiredSecret

MantisBT API key (Profile → API Tokens in MantisBT)

MANTIS_CACHE_DIR(file)

Directory for the metadata cache. Defaults to ~/.cache/mantisbt-mcp

MANTIS_CACHE_TTL(num)

Default:3600

Metadata cache TTL in seconds. Default: 3600 (1 hour)

TRANSPORT(str)

Default:stdio

Transport mode. 'stdio' for local use (default), 'http' for remote/team deployments

PORT(num)

Default:3000

HTTP port when TRANSPORT=http. Default: 3000

MCP_HTTP_HOST(str)

Default:127.0.0.1

Bind address when TRANSPORT=http. Default: 127.0.0.1 (local only). Use 0.0.0.0 for Docker/remote.

MCP_HTTP_TOKEN(str)

Secret

Optional Bearer token to protect the /mcp endpoint when TRANSPORT=http

MANTIS_SEARCH_ENABLED(bool)

Default:false

Enable offline semantic search (requires ~80 MB model download on first use)

MANTIS_SEARCH_BACKEND(str)

Default:vectra

Vector store backend for semantic search. 'vectra' (default, pure JS) or 'sqlite-vec' (faster for >10k issues)

MANTIS_SEARCH_DIR(file)

Directory for the semantic search index. Defaults to ~/.cache/mantisbt-mcp/search

MANTIS_SEARCH_MODEL(str)

Default:Xenova/paraphrase-multilingual-MiniLM-L12-v2

Hugging Face model for embeddings. Default: Xenova/paraphrase-multilingual-MiniLM-L12-v2

MANTIS_SEARCH_THREADS(num)

Default:1

ONNX inference threads for the embedding model. Default: 1

MANTIS_UPLOAD_DIR(file)

If set, restricts file uploads to this directory (path traversal protection)