Hypermnesic
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| OPENAI_API_KEY | No | OpenAI API key for dense embeddings (optional; falls back to lexical-only if not set) | |
| HYPERMNESIC_DEFAULT_CLIENT_SCOPES | No | Default OAuth scopes for new client approvals, e.g. 'read,write' (optional, overrides --default-client-scopes) |
Instructions
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.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| completions | {} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| searchA | Hybrid retrieval over the read-only index: fuses SQLite FTS5 lexical search with sqlite-vec dense (semantic) ranking via reciprocal-rank fusion, degrading gracefully to lexical-only when embeddings are unavailable. Returns ranked hits (source markdown path, heading, fused score, matched channels, a snippet, and git recency) so an agent can recall facts, notes, and decisions from the vault by a natural-language query. |
| hypermnesic_searchA | Hybrid (lexical + dense) search over the read-only index: functionally identical to |
| build_contextA | Pages reachable from a page via body wikilinks (in+out edges). |
| resolveA | Entity resolution: resolve a name to an existing page path (gbrain's |
| thinkA | Thinking-mode: related notes + Socratic prompts + related-but-not-yet-linked pairs. Pass the active note's |
| list_foldersA | Discover the vault's folder taxonomy + writable locations before placing a note: child folders under |
| read_noteA | Read the full markdown content of a single note by its repo-relative path (typically a |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 7 tools
There are two tools that perform identical search functionality (search and hypermnesic_search), creating ambiguity about which to use. Other tools are distinct but the overlap is confusing.
Most tools follow a verb or verb_noun pattern with consistent lowercase underscore naming. The hypermnesic_search is a namespaced alias that deviates from the pattern, but it is still clear.
With 7 tools covering read-only operations like search, read, resolve, list, and context building, the count is well-scoped for a read-focused knowledge vault assistant.
The tool set lacks any write operations such as creating or updating notes. This is a significant gap for a personal knowledge management system, as agents cannot record new information or modify existing notes.