Schema | memocean-mcp

memocean-mcp

Describes the environment variables required to run the server.

Name	Required	Description	Default
`KNN_ENABLED`	No	Enable BGE-m3 KNN vector search	false
`ANTHROPIC_API_KEY`	No	Required only for AI-assisted features above
`MEMOCEAN_DATA_DIR`	No	Data directory (databases, task queue)	~/.memocean
`MEMOCEAN_SKILLS_DIR`	No	Skills markdown directory	MEMOCEAN_VAULT_ROOT/Ocean/Pearl/skills
`MEMOCEAN_USE_GBRAIN`	No	Enable GBrain hybrid search delegate	false
`MEMOCEAN_VAULT_PATH`	No	Ocean subdirectory for full-text search	MEMOCEAN_VAULT_ROOT/Ocean
`MEMOCEAN_VAULT_ROOT`	No	Root of your Obsidian vault	~/Documents/Obsidian Vault
`CHANNELLAB_BOTS_ROOT`	No	Backward-compat: maps to MEMOCEAN_DATA_DIR
`ENABLE_HAIKU_RERANKER`	No	Enable Haiku LLM reranker
`ENABLE_QUERY_EXPANSION`	No	Enable Haiku query expansion (requires ANTHROPIC_API_KEY)
`CHANNELLAB_OCEAN_VAULT_ROOT`	No	Backward-compat: maps to MEMOCEAN_VAULT_ROOT

Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.

This server publishes no instructions, or was last inspected before Glama recorded them.

Server capabilities have not been inspected yet.

Functions exposed to the LLM to take actions

Name	Description
No tools

Interactive templates invoked by user choice

Name	Description
No prompts

Contextual data attached and managed by the client

Name	Description
No resources

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

curl -X GET 'https://glama.ai/api/mcp/v1/servers/ChannelLabAI/memocean'

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