Mnemoverse Memory

memory_graph

Read-onlyIdempotent

Reads the association edges around given concepts: which concepts the memory has linked together, with each link's weight, outcome valence and co-activation count. Use to inspect what a memory store has learned or to explain why a read expanded to a concept. Reads your own graph, or a shared room's when its address is passed as domain; any other domain value has no effect. At depth 2 or 3 the engine drops edges below weight 0.05 unless min_weight is set. Read-only.

Input Schema

TableJSON Schema

Name	Required	Description
`depth`	No	Hops to expand from the seeds (1-3, default 1). At depth 2 or 3, if min_weight is omitted the engine floors edge weight at 0.05 at EVERY hop — including the first — so a hub concept cannot fan out across the whole store before limit applies; pass min_weight explicitly (0 included) to see every edge anyway.
`limit`	No	Max edges to return (1-500, default 100 — mirrors memory_read's top_k bounds).
`seeds`	Yes	Concepts to center the graph on (1-20, each ≤200 chars, non-blank) — e.g. ['deploy', 'staging']. An unrecognised concept simply contributes no edges; it is not an error.
`domain`	No	Read a shared room's graph instead of your own: pass that room's address (e.g. 'xroom:room_01ABC'). Find room addresses with memory_list_rooms. Unlike memory_read, any OTHER value has no effect here — the association store has no domain column, so a plain domain name behaves exactly like omitting this field.
`min_weight`	No	Only include edges at or above this weight (≥ 0). Omit for no floor at depth 1; at depth 2/3 the engine applies its own 0.05 floor when this is omitted (see depth) — pass 0 to see every edge at every depth.

Output Schema

TableJSON Schema

Name	Required	Description
`edges`	Yes	Association edges found within the requested depth.
`nodes`	Yes	Concepts touched by edges below. A seed with no surviving edge (unrecognised concept, or every edge fell below the weight floor) is not listed.
`truncated`	Yes	True when a per-hop server cap or limit cut the walk short — the store may hold more edges than are reported here.
`min_weight_applied`	Yes	The weight floor actually used at every hop: your min_weight when you set one (0 included); otherwise 0.05 from depth 2, or 0 at depth 1.

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedOct 12, 2026

removedInput schema / $schema

Removed value: -"http://json-schema.org/draft-07/schema#"

removedOutput schema / $schema

Removed value: -"http://json-schema.org/draft-07/schema#"

AddedSep 27, 2026

TDQS

A4.4/5.0

Behavior4/5

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

Annotations already cover the safety profile (readOnlyHint, idempotentHint, destructiveHint=false), but the description adds non-obvious behavior: the 0.05 weight floor auto-applied at depth 2/3 unless min_weight is passed, that a non-address domain value is silently a no-op, and that an unrecognised seed is not an error. These are genuine surprises an agent would otherwise hit, though the trailing 'Read-only' merely restates the annotation.

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?

Front-loaded with what the tool returns, then usage, then the domain caveat, then the depth/min_weight caveat — a sensible ordering with no filler sentences. The final 'Read-only.' is redundant against the annotations, the only wasted token.

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?

An output schema exists, so return-shape explanation is unnecessary, and the annotations carry the safety profile. What remains — when to use it, the domain constraint, and the min_weight floor interaction — is fully covered, leaving nothing an agent needs to call it correctly.

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

Parameters4/5

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

Schema description coverage is 100%, so the baseline is 3, but the description adds cross-parameter semantics the schema states only locally: how depth and min_weight interact (0.05 floor at every hop including the first) and that domain must be a room address, unlike memory_read. It does not add anything for seeds or limit, which the schema already documents fully.

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?

States a specific verb and resource ('Reads the association edges around given concepts') and enumerates what each edge carries (weight, outcome valence, co-activation count). This clearly separates it from sibling memory_read, which retrieves memories rather than the link structure between them.

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

Usage Guidelines4/5

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

Gives two concrete use cases: inspecting what a store has learned, and explaining why a read expanded to a concept — the latter implicitly points at memory_read as the upstream operation. It also scopes the domain parameter ('reads your own graph, or a shared room's when its address is passed'). No explicit when-not or named alternative tool, so it falls short of a 5.

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

All Mnemoverse Memory tools Inspect

Try in Browser

Context All Your Agents Can ShareAgents share what they learn, hand off work, and hold it when you switch models. Start with 5 GB free.fulcradynamics.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.