Schema | Sharpwave

Sharpwave

Describes the environment variables required to run the server.

Name	Required	Description	Default
`OLLAMA_BASE_URL`	No	Local embedding endpoint	http://localhost:11434
`SHARPWAVE_DB_PATH`	No	Full path to a specific database file, overriding DATA_DIR
`OPENROUTER_API_KEY`	No	Enables remote embeddings and generative consolidation
`SHARPWAVE_AGENT_ID`	No	Namespace for separate, isolated memories	default
`SHARPWAVE_DATA_DIR`	No	Where the database lives	~/.sharpwave
`SHARPWAVE_EMBEDDING_MODEL`	No	Embedding model to use, e.g., 'ollama/qwen3-embedding:0.6b'

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.

Features and capabilities supported by this server

Protocol revision2025-11-25

Capability	Details
`tools`	{}

Functions exposed to the LLM to take actions

Name	Description
brain_queryA	Search and recall memories using hybrid FTS + vector + spreading activation. Returns ranked nodes with retrievability and salience scores.
brain_writeA	Store a new memory node. Automatically queues for embedding and PRISM/NEXUS auto-linking.
brain_linkB	Create a typed edge between two existing nodes.
brain_supersedeA	Replace an outdated node with updated content. Closes old edges, writes a supersedes edge, preserving the memory graph's temporal integrity.
brain_statsA	Return brain statistics: node/edge/episode counts, neuromodulator state, consolidation status, embedding coverage.
brain_historyB	Search episode history (raw conversation turns) by keyword.
brain_expandB	Get full detail for a specific node: content, FSRS metrics, encoding context, and source episodes.
brain_reviewA	Apply an FSRS-6 spaced-repetition review to a node. Updates stability, retrievability, and SIGMA calibration.
brain_forgetA	Physically delete a node from the brain. Refuses to delete nodes with active edges unless force=true.
brain_edgesB	Get all active incoming and outgoing edges for a node.

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/EnlightenedRepublic/sharpwave'

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