Skip to main content
Glama
max-ramas

RMS Memory MCP

by max-ramas
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Rust
Local

rms_search

Search semantic memory across vault and code corpora, returning a decision envelope that either injects relevant chunks or abstains when confidence is low.

Instructions

Search RMS Memory. Returns a decision envelope: {decision: inject|abstain, reason, injected_ids, results}. corpus=vault (default) searches human Markdown memory; code searches derived semantic code; all ranks each corpus independently and combines them with Reciprocal Rank Fusion, never raw vector distances. Pass projects: [key, …] for read-only cross-project federation (when both project and projects are set, projects wins so injected rules stay compatible); vault/all across multiple projects requires every listed key to have cross_project_vault=true (hard error otherwise — no silent degrade). Weak matches abstain when min_score is set; content is bounded by max_chars.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
limitNoMaximum number of chunks to return. Default is 10.
queryYesThe semantic query string to search for.
corpusNoCorpus to search. Defaults to vault.
projectNoRegistered project key, used when the MCP client did not provide a workspace root. Ignored when `projects` is also set.
projectsNoExplicit list of registered project keys for read-only federated search (max 8 after dedupe). Does not change the active bind. When set together with `project`, this list wins. Vault/all with len>1 requires cross_project_vault=true on every listed key.
max_charsNoMaximum total characters of injected content across results (default 2000). Truncates/drops weaker hits to stay within budget.
min_scoreNoOptional minimum relevance in 0..1 (distance and RRF normalized). If the best hit is weaker, rms_search abstains with an empty results list (fail-closed).
min_confidenceNoOptional minimum confidence threshold (0.0–1.0). Records with NULL confidence are always included. CAUTION: do NOT use high values (e.g. 0.9+) unless you need strict filtering. If zero results, retry without this parameter.
include_contentNoWhether to include full chunk text in results.
include_file_historyNoWhen true, attach the last 3 commits from the derived code_path git-history cache to each code hit (lazy catch-up). Not allowed together with projects: […] federation. Default false.
include_graph_neighborsNoWhen true, attach durable graph neighbors for each hit path. Not allowed together with projects: […] federation. Default false.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv1.2.0
    • addedInput schema / properties / include_graph_neighbors
      Added value: +{
+  "description": "When true, attach durable graph neighbors for each hit path. Not allowed together with projects: […] federation. Default false.",
+  "type": "boolean"
+}
  2. Changed1 schema field changedv1.1.2
    • addedInput schema / properties / include_file_history
      Added value: +{
+  "description": "When true, attach the last 3 commits from the derived code_path git-history cache to each code hit (lazy catch-up). Not allowed together with projects: […] federation. Default false.",
+  "type": "boolean"
+}
  3. First observedv0.1.0

TDQS

A4.4/5.0
Behavior5/5

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

With no annotations, the description carries the full burden and delivers: it discloses the decision envelope (`inject|abstain`, `injected_ids`, `results`), fail-closed abstention when `min_score` is set, hard errors on invalid `cross_project_vault` usage with no silent degrade, RRF combination rather than raw vector distances, and `max_chars` bounding. These are substantive behavioral traits beyond a simple 'search' statement.

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 well organized: purpose and return envelope first, then corpus semantics, then federation constraints, then threshold and bounding behavior. Every clause earns its place, and there is no redundant repetition of schema content.

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?

Despite having 11 parameters and no output schema, the description plus the rich input schema provide enough for an agent to select and invoke the tool correctly. It specifies the return envelope, key failure modes, federation constraints, and result-bounding behavior, leaving no critical invocation gap.

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 coverage is 100%, so the baseline is 3. The description adds meaning beyond the schema by explaining RRF combination for `corpus=all`, the compatibility rationale for `projects` winning over `project`, and the hard-error policy for vault/all federation. These are useful additions, though most individual parameter details already live in the schema.

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 specific verb and resource ('Search RMS Memory') and immediately gives the decision envelope, which makes the tool's role clear. However, it never explicitly differentiates itself from the sibling `rms_code_search` even though `corpus=code` overlaps with that tool, so sibling differentiation is only implicit.

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?

The description gives concrete selection context: `corpus=vault` vs `corpus=code` vs `corpus=all`, when to pass `projects` for read-only cross-project federation, and the precedence rule when both `project` and `projects` are set. It stops short of a 5 because it does not explicitly name alternatives or state when not to use this tool in favor of a sibling.

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