Skip to main content
Glama

nucleus_engrams

Store and retrieve persistent memories across AI sessions using engrams, supporting tag-based filtering, full-text search, and relationship mapping.

Instructions

Store, query, and search persistent memory (engrams) that survives across AI sessions, plus health monitoring and context graph visualization. Use this tool when you need to remember something for future sessions, recall past decisions, search the knowledge base, or check system health. Do NOT use for task tracking (use nucleus_tasks), session lifecycle (use nucleus_sessions), or agent coordination (use nucleus_agents). Engrams are the fundamental memory unit — each has content, optional tags for categorization, source attribution, and arbitrary metadata. Actions: 'write_engram' persists new knowledge to .brain/engrams/ (side effect: creates a JSONL entry). 'query_engrams' retrieves engrams filtered by tag, context, or intensity. 'search_engrams' performs full-text search across all stored knowledge. 'health' checks brain directory integrity and returns file counts and sizes. 'version' returns Nucleus version, Python version, and platform info. 'audit_log' shows the decision audit trail with timestamps. 'morning_brief' generates a daily status report with task summaries, session history, and recommendations. 'governance_status' shows current security mode and lock state. 'context_graph' builds a relationship map between related engrams. 'engram_neighbors' traverses the graph from a specific engram. 'pulse_and_polish' analyzes engram quality and suggests improvements. 'fusion_reactor' cross-references multiple engrams to generate insights. 'billing_summary' shows resource usage. All read operations are non-destructive. Prerequisites: .brain directory must exist. Returns JSON with {success: boolean, data: object}. Example: {action: 'write_engram', params: {content: 'Auth uses JWT with 24h expiry', tags: ['architecture', 'auth']}} returns {success: true, data: {key: 'engram_a1b2c3', stored: true}}.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
actionYesSelect the engram or observability action. 'write_engram' persists new knowledge to disk. 'query_engrams' filters by context, tags, or intensity. 'search_engrams' does full-text search. 'health'/'version'/'audit_log'/'governance_status'/'billing_summary' are read-only diagnostics. 'morning_brief' generates a daily summary. 'context_graph'/'engram_neighbors'/'render_graph' map relationships between engrams. 'pulse_and_polish'/'fusion_reactor' are compound analysis operations.
paramsNoAction-specific parameters as key-value pairs. write_engram: {content: string (required, the knowledge to store), tags: string[] (optional, e.g. ['architecture','decision']), source: string (optional, origin attribution like 'code_review'), metadata: object (optional, arbitrary key-value data)}. query_engrams: {query: string (optional, filter text), limit: integer (optional, default 10, max results), tags: string[] (optional, filter by tags)}. search_engrams: {query: string (required, full-text search term), limit: integer (optional, default 10)}. audit_log: {limit: integer (optional, default 20), level: string (optional, 'info'|'warning'|'error')}. context_graph: {engram_id: string (optional, center node ID)}. engram_neighbors: {engram_id: string (required), depth: integer (optional, default 1, traversal depth)}. health/version/morning_brief/governance_status/billing_summary: no parameters needed.
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Despite minimal annotations (all hints false), the description details side effects (e.g., 'write_engram creates a JSONL entry'), states that read operations are non-destructive, and mentions prerequisites (.brain directory must exist). It also enumerates all actions with their effects.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is front-loaded with the core purpose and ends with a concrete example. However, it is somewhat verbose in listing all actions and could be more structured (e.g., bullet points). Each sentence generally earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (13 actions, nested params, no output schema), the description covers all actions, prerequisites, return format, and examples. It is fully complete and leaves no ambiguity for an agent.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Input schema has 100% coverage, but the description adds significant value by explaining action-specific parameters (e.g., write_engram requires content, offers tags/source/metadata), providing examples, and clarifying defaults like limit=10.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description explicitly states 'Store, query, and search persistent memory (engrams)' and distinguishes from sibling tools like nucleus_tasks, nucleus_sessions, and nucleus_agents. It provides a specific verb+resource and clear differentiation.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides explicit when-to-use (e.g., 'remember something for future sessions') and when-not-to-use scenarios with named alternatives, making it easy for an agent to choose correctly.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Latest Blog Posts

MCP directory API

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

curl -X GET 'https://glama.ai/api/mcp/v1/servers/eidetic-works/nucleus-mcp'

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