Atlas / MCP servers / gannonh / Memento

MementoSAFE

Name: Memento
Author: gannonh

mcp/gannonh/memento

MCP server by gannonh · claude desktop · cursor · knowledge graph · Audited 2026-10-01

⚑ Report / re-scan Source ↗

Memento MCP: A Knowledge Graph Memory System for LLMs

Verdict

SAFE

Grade

Trust score

89 /100

Exposed tools

20 12r · 4w · 4d

Transport

stdio

License

MIT

Stars

425

Overview

From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.

Scalable, high performance knowledge graph memory system with semantic retrieval, contextual recall, and temporal awareness. Provides any LLM client that supports the model context protocol (e.g., Claude Desktop, Cursor, Github Copilot) with resilient, adaptive, and persistent long-term ontological memory.

[](https://github.com/gannonh/memento-mcp/actions/workflows/memento-mcp.yml) [](https://smithery.ai/server/@gannonh/memento-mcp)

Core Concepts

Entities

Entities are the primary nodes in the knowledge graph. Each entity has:

A unique name (identifier)
An entity type (e.g., "person", "organization", "event")
A list of observations
Vector embeddings (for semantic search)
Complete version history

Example:

{
"name": "John_Smith",
"entityType": "person",
"observations": ["Speaks fluent Spanish"]
}

Relations

Relations define directed connections between entities with enhanced properties:

Strength indicators (0.0-1.0)
Confidence levels (0.0-1.0)
Rich metadata (source, timestamps, tags)
Temporal awareness with version history
Time-based confidence decay

Example:

{
"from": "John_Smith",
"to": "Anthropic",
"relationType": "works_at",
"strength": 0.9,
"confidence": 0.95,
"metadata": {
"source": "linkedin_profile",
"last_verified": "2025-03-21"
}
}

Storage Backend

Memento MCP uses Neo4j as its storage backend, providing a unified solution for both graph storage and vector search capabilities.

Why Neo4j?

Unified Storage: Consolidates both graph and vector storage into a single database
Native Graph Operations: Built specifically for graph traversal and queries
Integrated Vector Search

Read from source at commit 941b81c1fa57OBSERVED · 2026-10-01

Connect

Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.

claude-code

claude mcp add memento-mcp --env EMBEDDING_RATE_LIMIT_TOKENS=${EMBEDDING_RATE_LIMIT_TOKENS} --env NEO4J_PASSWORD=${NEO4J_PASSWORD} --env OPENAI_API_KEY=${OPENAI_API_KEY} -- npx -y @gannonh/[email protected]

claude-desktop

{
  "mcpServers": {
    "memento-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@gannonh/[email protected]"
      ],
      "env": {
        "EMBEDDING_RATE_LIMIT_TOKENS": "${EMBEDDING_RATE_LIMIT_TOKENS}",
        "NEO4J_PASSWORD": "${NEO4J_PASSWORD}",
        "OPENAI_API_KEY": "${OPENAI_API_KEY}"
      }
    }
  }
}

Exposed tools (20)

12 read · 4 write · 4 destructive. Blast radius: 4 tools can delete or overwrite — an agent that can be talked into calling a tool can be talked into calling this one.

Tool	Risk	Description
`add_observations`	write	Add new observations to existing entities in your Memento MCP knowledge graph memory
`create_entities`	write	Create multiple new entities in your Memento MCP knowledge graph memory system
`create_relations`	write	Create multiple new relations between entities in your Memento MCP knowledge graph memory. Relations should be in active voice
`debug_embedding_config`	read	Debug tool to check embedding configuration and status of your Memento MCP knowledge graph memory system
`delete_entities`	destructive	Delete multiple entities and their associated relations from your Memento MCP knowledge graph memory
`delete_observations`	destructive	Delete specific observations from entities in your Memento MCP knowledge graph memory
`delete_relations`	destructive	Delete multiple relations from your Memento MCP knowledge graph memory
`diagnose_vector_search`	read	Diagnostic tool to directly query Neo4j database for entity embeddings, bypassing application abstractions
`force_generate_embedding`	destructive	Forcibly generate and store an embedding for an entity in your Memento MCP knowledge graph memory
`get_decayed_graph`	read	Get your Memento MCP knowledge graph memory with confidence values decayed based on time
`get_entity_embedding`	read	Get the vector embedding for a specific entity from your Memento MCP knowledge graph memory
`get_entity_history`	read	Get the version history of an entity from your Memento MCP knowledge graph memory
`get_graph_at_time`	read	Get your Memento MCP knowledge graph memory as it existed at a specific point in time
`get_relation`	read	Get a specific relation with its enhanced properties from your Memento MCP knowledge graph memory
`get_relation_history`	read	Get the version history of a relation from your Memento MCP knowledge graph memory
`open_nodes`	read	Open specific nodes in your Memento MCP knowledge graph memory by their names
`read_graph`	read	Read the entire Memento MCP knowledge graph memory system
`search_nodes`	read	Search for nodes in your Memento MCP knowledge graph memory based on a query
`semantic_search`	read	Search for entities semantically using vector embeddings and similarity in your Memento MCP knowledge graph memory
`update_relation`	write	Update an existing relation with enhanced properties in your Memento MCP knowledge graph memory

Trust audit

SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.

Layer	What it checks	Result
L0	Provenance & inventory	PASS
L1	Static analysis of the code	PASS
L2	Instruction surface (what it tells the agent)	PASS
L3	Class-specific surface	WARN
L4	Behavioural (sandbox)	SKIPPED

What the source does

Filesystem: declared (1 observation(s))
Network: declared (2 observation(s))
Shell: none-observed
Dependencies: not all pinned
Secrets in source: none-found

Findings (12)

MEDIUMFilesystem / path · mcp.destructive_tools · CWE-22, CWE-59

delete_entities, delete_observations, delete_relations, force_generate_embedding

Why it matters. 4 tool(s) can delete or overwrite

Fix. prefer a read-only mode or scoped tokens; the page states the blast radius

LOWInventory / provenance · inv.hidden_file · CWE-1104

.gitmodules

.gitmodules

Why it matters. hidden member outside the usual dotfiles

Fix. review its purpose

LOWInsecure crypto · crypto.weak_hash · CWE-327, CWE-338

src/embeddings/EmbeddingJobManager.ts:713

return crypto.createHash('md5').update(text).digest('hex');

LOWInformation disclosure · disclose.log_secret · CWE-209, CWE-532

src/embeddings/__vitest__/EmbeddingServiceIntegration.test.ts:23

console.log(`API key available: ${apiKey ? 'true' : 'false'}`);