Soul
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
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": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| n2_bootB | Boot sequence — loads soul-board handoff, entity/core memory, agent list, and KV-Cache context. |
| n2_work_sessionsC | List unfinished work and completed work with pending Mimir collection; use the exact sessionId to resume. |
| n2_work_startB | Start a work sequence. Registers agent in activeWork on soul-board. |
| n2_work_claimB | Claim file ownership before modifying. Prevents collision with other agents. |
| n2_work_logC | Log file changes during work. Reports created/modified/deleted files with descriptions. |
| n2_context_searchA | Search across Brain memory and Ledger entries for relevant past context. Uses keyword matching with recency weighting. |
| n2_work_endA | End work sequence. Writes immutable ledger entry, updates soul-board handoff, releases file ownership. |
| n2_brain_readB | Read a file from shared memory (data/memory/). Agents share information here. |
| n2_brain_writeB | Write a file to shared memory (data/memory/). Share information between agents. |
| n2_entity_upsertB | Add or update entities (person, hardware, project, concept). Auto-merges attributes if entity exists. |
| n2_entity_searchA | Search entities by keyword or type. Returns matching entities with attributes. |
| n2_core_readB | Read agent-specific core memory. Core memory is always loaded at boot for context injection. |
| n2_core_writeA | Write to agent-specific core memory. Stored permanently, injected at every boot. |
| n2_kv_saveA | Save a durable checkpoint during work or before replying. does not finish active work. |
| n2_kv_loadB | Load the most recent KV-Cache snapshot for a project. Returns compressed context. |
| n2_kv_searchA | Read relevant historical snapshots for one project and agent (defaults to boot identity). Bounded lexical matching with domain aliases and correction precedence; source IDs and matched excerpts, no semantic-only ranking. |
| n2_kv_gcB | Remove old KV-Cache snapshots. Uses config defaults if no args. |
| n2_kv_backupC | Backup KV-Cache data to a portable SQLite DB. Supports incremental backups. |
| n2_kv_restoreC | Restore KV-Cache data from a backup DB. |
| n2_kv_backup_listC | List KV-Cache backup history for a project. |
| n2_mimir_recallB | Read historical reports and reviewed lessons for one project and agent; no learning mutations. |
| n2_mimir_lesson_proposeC | Create a dormant lesson candidate with source experience IDs. No automatic promotion. |
| n2_mimir_lesson_evidenceB | Record application evidence from data/evidence//. Requires soul-evidence/v1 JSON, matching lesson/work identity, completed durable work, method, observation, outcome and applied flag. Checks provenance/integrity, not the truth of authored observations. |
| n2_mimir_lesson_reviewC | Promote only after two distinct completed-work positive applied results, >=80% positive, no negative result, unchanged sources/artifacts and review of all current user corrections. Hold/retire retain history. Supersession is atomic; no executable rules are created. |
| n2_mimir_lessonsB | Inspect scoped lesson state, recorded evidence, correction IDs and review history. Legacy insights are not implicitly verified. |
| n2_mimir_study_startC | Start durable scoped study collection. Returns a sessionId; same-topic sessions stay separate. |
| n2_mimir_study_addC | Append one reported study entry idempotently. Outcome/type are reports, not verified effects or user authority. |
| n2_mimir_study_endB | Freeze and save study reports. Restart-safe retry; no digest, cross-project merge, voting or graduation. |
| n2_mimir_study_sessionsC | Find unfinished durable study collections in one scope. |
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 29 tools
Most tools target distinct subsystems (work lifecycle, brain memory, core memory, entities, KV cache, Mimir study/lessons), but there are several similarly purposed retrieval tools: context_search, kv_search, kv_load, mimir_recall, and entity_search. Descriptions do differentiate them, but an agent must read carefully to pick the right search/recall surface.
Names consistently use an n2_ prefix and snake_case, generally following n2_<domain>_<operation> (e.g. n2_work_start, n2_kv_save, n2_mimir_lesson_review). Minor deviations exist where tools are noun-like rather than verb-led (n2_work_sessions, n2_mimir_lessons, n2_boot), but the overall pattern remains predictable.
The server is large at 29 tools, but it spans several real subsystems rather than duplicating a single workflow. Each subsystem has a small coherent set, though the total surface is heavy enough to increase selection burden.
Core lifecycle coverage is strong for work sessions, KV snapshots, and Mimir studies/lessons, but shared memory and entity management lack delete/list operations and there is no general brain file listing. These are notable gaps, though agents can work around many of them via search and overwrite-style writes.