Skip to main content
Glama
Sign In
RMS Memory MCP

RMS Memory MCP

by max-ramas
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Rust
Local

rms_write

Save architectural decisions, constraints, development rules, or project context to a persistent memory vault so agents retain learned preferences and solved issues across tasks.

Instructions

Save new architectural decisions, constraints, development rules, or project context to the RMS Memory vault. Use this tool PROACTIVELY at the end of a task if you learned a new user preference, solved a tricky bug, or made a new architectural decision.

Input Schema

NameRequiredDescriptionDefault
idNo
modeYesWrite mode.
pathYesRelative path to save the document (e.g., 'decisions/001-db.md').
pinnedNoWhen true, the note bypasses temporal and min_confidence recall gates (status still applies).
sourceNoOptional free-text citation or source reference for this record.
statusNoOptional lifecycle status: active, draft, or superseded.
contentYesThe markdown content to write.
dry_runNoWhen true, classify create/update/noop and return a JSON preview without writing disk or touching the index. Defaults to false.
projectNoProject key (when the client sends no workspace root).
confidenceNoOptional confidence score (0.0–1.0) indicating reliability of this record.
supersedesNoOptional relative vault path of a prior note to soft-supersede (marks it status=superseded and links both sides).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv1.4.3
    • changedInput schema / properties / project / description
      Previous value: -"Registered project key, used when the MCP client did not provide a workspace root."New value: +"Project key (when the client sends no workspace root)."
  2. Changed1 schema field changedv1.1.2
    • addedInput schema / properties / dry_run
      Added value: +{
+  "default": false,
+  "description": "When true, classify create/update/noop and return a JSON preview without writing disk or touching the index. Defaults to false.",
+  "type": "boolean"
+}
  3. First observedv0.1.0

TDQS

B3.4/5.0
Behavior2/5

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

No annotations are supplied, so the description carries the full burden, and it does not disclose the behavior that matters most for a write tool: that 'replace' overwrites existing content, that 'append' mutates in place, that records are indexed, or that supersedes soft-links prior notes. It only characterizes the kind of content to save, not the consequences of saving it.

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?

Two tight sentences: the action and destination come first, the usage trigger second. The capitalized 'PROACTIVELY' is slightly shouty but signals an intended behavior rather than adding filler, so nothing wasteful is present.

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

Completeness3/5

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

For an 11-parameter mutation tool with no annotations and no output schema, the description covers purpose and timing but omits the write-safety story (overwrite risk, dry_run preview value, index side effects) that an agent needs before choosing 'replace'. The rich schema compensates for parameter detail but not for behavioral risk.

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

Parameters3/5

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

Schema description coverage is 91%, so the schema already explains mode, path, pinned, dry_run, supersedes, status, and confidence. The description adds no parameter-level meaning beyond what the schema provides, which is the correct baseline when schema coverage is this high.

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?

States a specific verb ('Save') and a concrete resource set ('architectural decisions, constraints, development rules, or project context') plus the destination ('RMS Memory vault'). It implicitly reads as the write counterpart to rms_read/rms_search, but never names a sibling, so the differentiation is left to inference.

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 explicit when-to-use triggers: 'at the end of a task if you learned a new user preference, solved a tricky bug, or made a new architectural decision,' and pushes proactive use. Missing are exclusions — e.g., when to use rms_checkpoint_save or rms_remind instead — so an agent could still over-write to the vault.

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