Skip to main content
Glama
billy12151

memory-arbiter-mcp

by billy12151
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

memory

Store, search, read, and update shared memory for AI coding tools, with built-in conflict arbitration for multi-tool collaboration.

Instructions

Daily memory operations: remember, find, batch_find, read, update, judge, status, help.

Call memory(action="help") to discover accepted fields, judge requirements, value enums, update modes, and action_required paths before relying on a result that requests attention.

update edits in place: <=3 local edits use patches=[{old_text,new_text}] (atomic all-or-nothing, one version bump); full rewrites use new_content; a single small edit may use old_text/new_text.

batch_find runs up to 8 queries in one call and returns one merged index page (dedup by memory_id, matched_query_ids per item).

find is an index page: results carry metadata + content_chars + a bounded outline (offsets usable directly as read span starts), not full content — content_mode (v0.15.10, preview default) is a single-choice enum: "hits" adds hit_spans (vector-matched unit text + span coordinates, never truncated; >=50% coverage upgrades an item to full text), "full" returns whole texts. Score compares only within the page; if the top page misses, reword the query or add tags_filter instead of deep paging. The size block meters the returned page (tokens_estimate + display_hint).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
dataNo
actionNohelp

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.16.5
    • changedOutput schema / (root)
      Previous value: -{
-  "additionalProperties": true,
-  "title": "memoryDictOutput",
-  "type": "object"
-}New value: +null
  2. Addedv0.11.0

TDQS

A4.5/5.0
Behavior5/5

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

With no annotations, the description carries the disclosure burden and succeeds: it reveals that find returns an index page with bounded outline, preview content_mode is default, hit_spans are never truncated, score comparison is page-local, update is atomic with one version bump, and batch_find dedups by memory_id. These are non-obvious behavioral facts beyond the bare schema.

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

Conciseness5/5

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

The description is dense but each sentence contributes a behavioral fact, usage rule, or return-shape note; it is organized by operation with the help escape hatch front-loaded. There is no filler or redundant restatement of the schema.

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

Completeness4/5

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

For a tool with no output schema and only two loose parameters, the description covers update, find, and batch_find thoroughly, and explicitly routes remaining sub-ops through action='help'. It stops short of inline documentation for remember/read/judge/status, which is a reasonable but partial handoff.

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?

The schema has 0% description coverage and only generic action/data parameters. The description compensates by naming valid action values and specifying nested data payloads for updates (patches, new_content, old_text/new_text), find (content_mode, tags_filter, size block), and batch_find (up to 8 queries, merged page).

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

Purpose4/5

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

The description opens with a concrete list of memory operations (remember, find, batch_find, read, update, judge, status, help), which tells the agent what resource and verbs are involved. It does not contrast this tool with the sibling memory_review/memory_govern/memory_repair tools, so differentiation is left implied.

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?

It includes strong operational guidance: use patches for <=3 local edits, new_content for full rewrites, old_text/new_text for a single edit, and reword the query or add tags_filter instead of deep paging when the top find page misses. It also directs the agent to call action='help' before acting on results that request attention, although it never explicitly states when to prefer this tool over its siblings.

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

Deploy Server

Other Tools