Skip to main content
Glama
kirill-sviridov

handoff-mcp

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
HANDOFF_VAULTNoPath to the vault directory. Defaults to ~/.handoff-mcp/vault.
HANDOFF_PROJECTNoProject name for scoping memory.
HANDOFF_EMBEDDERNoEmbedding backend: hashing, local, or openai. Default: hashing.
HANDOFF_SEMANTICNoSet to 1 to enable semantic recall layer. Default: not set (off).
HANDOFF_AUTO_SYNCNoSet to 1 to automatically sync memory across devices.
HANDOFF_LLM_MODELNoSet to enable the consolidate tool (e.g., gpt-4o-mini).
HANDOFF_EMBED_MODELNoModel name for embeddings. Default: Qwen/Qwen3-Embedding-0.6B for local backend.
HANDOFF_EMBED_API_KEYNoAPI key for OpenAI-compatible embedding endpoint.
HANDOFF_EMBED_BASE_URLNoBase URL for OpenAI-compatible embedding endpoint.
HANDOFF_EMBED_TRUST_REMOTE_CODENoSet to 1 to trust remote code for embedding models that require it.

Capabilities

Server capabilities have not been inspected yet.

Tools

Functions exposed to the LLM to take actions

NameDescription

No tools

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/kirill-sviridov/handoff-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server