Skip to main content
Glama
danielsimonjr

Enhanced Knowledge Graph Memory Server

by danielsimonjr
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Local

hybrid_search

Retrieve relevant knowledge graph entries with combined semantic, keyword, and metadata matching. Fuses multiple relevance signals to improve recall, with optional graph-aware ranking and neighbor expansion.

Instructions

Search using combined semantic, lexical, and metadata signals. Provides better recall than single-signal search by fusing multiple relevance signals. v3 additive options: graphWeight adds a graph-connectivity (PageRank) channel, expandNeighbors appends one-hop neighbors of top results, explain annotates results with evidence paths from query anchors, lookFor ranks expansion neighbors by a free-text connection description.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
limitNoMaximum results to return (default: 10)
queryYesSearch query text
explainNoAnnotate each result with evidencePaths — graph paths connecting query anchor matches to the result (default: false)
filtersNoSymbolic/metadata filters
lookForNoFree-text description of the desired connection; expansion neighbors are ranked by similarity to it (lookForScore)
weightsNoLayer weights (automatically normalized to sum to 1.0)
graphWeightNoWeight for the graph-connectivity channel (normalized PageRank). 0/omitted = channel disabled (default)
expandNeighborsNoOne-hop neighbor expansion: neighbors of the top-K results are appended with a damped score and re-sorted

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changedv12.7.0
    • addedInput schema / properties / expandNeighbors
      Added value: +{
+  "additionalProperties": false,
+  "description": "One-hop neighbor expansion: neighbors of the top-K results are appended with a damped score and re-sorted",
+  "properties": {
+    "damping": {
+      "description": "Damping factor applied to the parent's combined score (default: 0.3)",
+      "type": "number"
+    },
+    "topK": {
+      "description": "Number of top-ranked results to expand from (default: 10)",
+      "type": "number"
+    }
+  },
+  "type": "object"
+}
    • addedInput schema / properties / explain
      Added value: +{
+  "description": "Annotate each result with evidencePaths — graph paths connecting query anchor matches to the result (default: false)",
+  "type": "boolean"
+}
    • addedInput schema / properties / graphWeight
      Added value: +{
+  "description": "Weight for the graph-connectivity channel (normalized PageRank). 0/omitted = channel disabled (default)",
+  "type": "number"
+}
    • addedInput schema / properties / lookFor
      Added value: +{
+  "description": "Free-text description of the desired connection; expansion neighbors are ranked by similarity to it (lookForScore)",
+  "type": "string"
+}
  2. First observedv11.1.1

TDQS

A4/5.0
Behavior4/5

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

With no annotations, the description carries full burden. It discloses key behaviors: fusion of signals, automatic normalization of weights, and detailed effects of each additive option (e.g., 'graphWeight adds...', 'explain annotates...'). However, it does not mention read-only nature, rate limits, or authorization needs.

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 information-dense without redundancy. It front-loads the core purpose, then lists additive options in a structured manner. Slightly longer than minimal but every sentence adds value.

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?

Given the tool's complexity (8 params, nested objects) and lack of output schema, the description should mention what the results contain. It doesn't describe return format or pagination, leaving the agent to infer. Adequate but incomplete.

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 baseline is 3. The description adds value by explaining that weights are 'automatically normalized to sum to 1.0' and by detailing the v3 additive options (graphWeight, expandNeighbors, explain, lookFor) with their effects, going beyond schema descriptions.

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 clearly states the tool's purpose: 'Search using combined semantic, lexical, and metadata signals.' It distinguishes itself from single-signal searches by promising 'better recall' and lists specific additive options (graphWeight, expandNeighbors, explain, lookFor), differentiating it from sibling search tools.

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

Usage Guidelines3/5

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

The description implies usage for high-recall searches but does not explicitly state when to prefer this over alternatives like semantic_search or boolean_search. No exclusion criteria or when-not-to-use guidance is provided.

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