Skip to main content
Glama
stevepridemore

Graph-Memory

by stevepridemore
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Hybrid

Semantic Graph Search

graph_search
Read-only

Find knowledge graph entities by semantic similarity to natural-language queries, even when wording differs from stored names, and optionally include related graph neighbors.

Instructions

Find entities semantically similar to a natural-language query, then optionally expand via graph traversal. Uses local sentence embeddings (bge-small-en, 384-dim) — no external API. Best when the user's wording doesn't match canonical entity names (e.g. "containers" → Docker, "AI tools" → Claude Code/Anthropic SDK). Falls back to graph_query if no embeddings available.

Input Schema

NameRequiredDescriptionDefault
queryYesNatural-language query (any phrasing — synonyms and paraphrases work).
top_kNoHow many semantically similar entities to retrieve as seeds (default 10).
expandNoIf true (default), also return the immediate graph neighbours of each seed.
entity_typesNoRestrict results to these entity types.
min_similarityNoMinimum cosine similarity threshold (default 0.5).
expand_min_weightNoMin edge weight when expanding (default 0.3).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.4.0
    • changedInput schema / properties / entity_types / items / enum
      Previous value: -[
-  "Person",
-  "Project",
-  "Preference",
-  "Concept",
-  "Decision",
-  "Fact",
-  "Event",
-  "Object",
-  "Reasoning"
-]New value: +[
+  "Person",
+  "Organization",
+  "Project",
+  "Feature",
+  "Concept",
+  "Technology",
+  "Decision",
+  "Reasoning",
+  "Preference",
+  "Event",
+  "Fact",
+  "Artifact",
+  "Object",
+  "Resource",
+  "Infrastructure",
+  "Alias",
+  "Location",
+  "Issue",
+  "Task"
+]
  2. Addedv0.2.2
  3. Removedv0.1.4
  4. First observedv1.0.0

TDQS

A4.3/5.0
Behavior4/5

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

Annotations only declare readOnlyHint=true, and the description adds genuinely useful operational context: local bge-small-en 384-dim embeddings, no external API dependency, and fallback behavior. It does not describe return shape or performance characteristics, but the added context is substantive.

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?

Three front-loaded sentences with no filler; the purpose, mechanism, and usage condition all earn their place. Slightly dense but efficiently organized.

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 6-parameter read-only search tool with a fully documented schema and no output schema, the description covers what it does, how it works, and when to prefer it. Only the return structure (seeds plus neighbours) is left implicit, a minor gap.

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 100%, so all six parameters including defaults and ranges are already documented in the schema. The description only restates the optional expansion behavior and adds nothing about entity_types, min_similarity, or expand_min_weight. Baseline 3 applies.

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+resource ('find entities semantically similar to a natural-language query') and adds a secondary behavior ('optionally expand via graph traversal'). It clearly differentiates itself from the sibling graph_query/graph_cypher tools by naming its distinct mechanism (embeddings).

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

Usage Guidelines5/5

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

Explicitly states the best-fit condition ('when the user's wording doesn't match canonical entity names') with concrete examples, and names the alternative route ('falls back to graph_query if no embeddings available'). An agent can select this over siblings without further inference.

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