mcp-memory-libsql

Provides an MCP server implementing a persistent memory/knowledge store backed by libSQL (local SQLite or remote libSQL). It supports entity CRUD, relation management, and text search (including relevance ranking and fuzzy matching) over stored entity data/observations.

Evaluated Mar 30, 2026 (21d ago)
Repo ↗ Ai Ml mcp memory libsql sqlite knowledge-graph text-search semantic-search vector-search typescript agent-tools
⚙ Agent Friendliness
54
/ 100
Can an agent use this?
🔒 Security
48
/ 100
Is it safe for agents?
⚡ Reliability
32
/ 100
Does it work consistently?

Score Breakdown

⚙ Agent Friendliness

MCP Quality
80
Documentation
70
Error Messages
0
Auth Simplicity
80
Rate Limits
10

🔒 Security

TLS Enforcement
70
Auth Strength
55
Scope Granularity
10
Dep. Hygiene
45
Secret Handling
60

TLS is likely handled by the libSQL client but not explicitly documented here. Remote auth is via a single LIBSQL_AUTH_TOKEN (no fine-grained scopes/authorization model for the MCP API). README does not discuss secret logging, transport security settings, or operational security hardening beyond token usage.

⚡ Reliability

Uptime/SLA
0
Version Stability
55
Breaking Changes
40
Error Recovery
35
AF Security Reliability

Best When

You want to plug a memory/knowledge graph MCP server into an existing MCP client (e.g., Claude Desktop/Cline) and you are comfortable using libSQL as the storage layer (local or Turso/remote).

Avoid When

You need strict authentication/authorization beyond a single database auth token, documented rate-limit semantics, or rigorous documented operational guarantees.

Use Cases

  • LLM agents that need persistent memory across sessions
  • Entity/relation storage for lightweight knowledge-graph use cases
  • Retrieval of relevant prior observations using text search
  • Local-first or hosted libSQL-backed agent memory deployments

Not For

  • High-scale multi-tenant enterprise memory services without additional governance/security controls
  • Use cases requiring a fully specified HTTP/REST API with OpenAPI/SDKs (this is an MCP/stdio server)
  • Compliance regimes that require documented security hardening, audits, and explicit operational SLAs

Interface

REST API
No
GraphQL
No
gRPC
No
MCP Server
Yes
SDK
No
Webhooks
No

Authentication

Methods: LIBSQL_AUTH_TOKEN for remote libSQL
OAuth: No Scopes: No

Authentication described is token-based for remote libSQL via LIBSQL_AUTH_TOKEN. No additional auth/authorization model for the MCP server itself is documented in the provided README.

Pricing

Free tier: No
Requires CC: No

Pricing is not described; depends on libSQL provider usage for remote databases.

Agent Metadata

Pagination
none
Idempotent
False
Retry Guidance
Not documented

Known Gotchas

  • MCP server is used via command/stdio; ensure the MCP client (e.g., Claude Desktop/Cline) is configured correctly to launch it.
  • Remote libSQL requires LIBSQL_AUTH_TOKEN; misconfiguration will likely fail storage connectivity.
  • Default database file is `file:/memory-tool.db` in the current directory—agents may accidentally write to unexpected local paths if env/config isn’t explicit.

Alternatives

Full Evaluation Report

Comprehensive deep-dive: security analysis, reliability audit, agent experience review, cost modeling, competitive positioning, and improvement roadmap for mcp-memory-libsql.

AI-powered analysis · PDF + markdown · Delivered within 30 minutes

$99

Package Brief

Quick verdict, integration guide, cost projections, gotchas with workarounds, and alternatives comparison.

Delivered within 10 minutes

$3

Score Monitoring

Get alerted when this package's AF, security, or reliability scores change significantly. Stay ahead of regressions.

Continuous monitoring

$3/mo

Scores are editorial opinions as of 2026-03-30.

8642
Packages Evaluated
17761
Need Evaluation
586
Need Re-evaluation
Community Powered