Magnemo
OfficialServer Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| MAGNEMO_AGENT | Yes | Identifier for the agent using the server. | |
| MAGNEMO_SCOPE | Yes | Comma-separated list of scopes available to the agent. | |
| MAGNEMO_VAULT | Yes | Absolute path to the vault directory. | |
| MAGNEMO_PARTITIONS | Yes | Comma-separated list of partitions available to the agent. |
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 | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| retrieveA | Retrieve canonical (keyholder-approved) memory relevant to a query. Returns a scored, BUDGETED payload: mn:// pointers plus snippet renditions, never raw dumps. Scope is partition-walled; payload size is logged to the Foresight counters. Cite the returned rid when the action resolves. |
| stageA | Stage a memory candidate for KEYHOLDER review. This is the only write verb: the note lands in _staging/ with mandatory provenance and never touches canon. Returns the staged id, its salience, and a duplicate flag. Malformed or paperless (no provenance) notes are refused. |
| bootpackA | The boot pack: Charter first (verbatim, never fabricated), then the Gate Map, YOUR AUTONOMY (this agent's own trust levels), canon digest, open threads, salience-ranked review queue, last handoff, ledger tail. Read it FIRST on every wake. Deterministic: same vault state, same bytes. |
| handoffA | Record a session boundary: appends telemetry (usage %, trigger, what was cut) to the append-only handoffs ledger AND stages a provenance-complete handoff note. The next bootpack inherits it. Doctrine: hand off at ~88-90%, do not ride to the wall. |
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 4 tools
Each tool maps to a distinct lifecycle action: querying approved memory, proposing new memory, loading the boot context, and closing a session. There is no real overlap, since bootpack is a deterministic startup read while retrieve is on-demand canonical lookup.
All four names are lowercase single-word commands, forming a consistent imperative style. They do not follow a verb_noun scheme, but the naming convention is uniform and predictable across the set.
Four tools is tight but appropriate for the server's narrow, well-defined purpose. Each tool has a distinct role and none feels redundant or extraneous.
The toolset covers the full agent-facing memory lifecycle: wake with bootpack, read with retrieve, propose with stage, and close with handoff. Keyholder review appears intentionally external, and the deterministic bootpack plus append-only handoff ledger leaves no obvious dead end.