Local Memory (PyPI) MCP Server
local-memory-mcp
PyPI
v0.25.0
Published by an unidentified publisher — no publish provenance and no public repository, so the publisher could not be verified and the source cannot be independently located.
Structured agent memory with SQLite/FTS5 + optional Qdrant vector search, exposed via MCP
The grade answers one question — how safe is this server for you to adopt — so it is computed in two auditable stages. Nothing below is an opinion or an LLM's guess; every line is a real term the deterministic engine applied, and the same input always yields the same number.
1. Threat score — 100 − 0 = 100. What the published surface and source actually contain:
The deterministic scan raised no scored threat in the surface it inspected — the threat score stayed at 100. Capability observations and advisory notes are recorded but never lower it.
2. Client adoption risk — 100 − 2 = 98. Three small, subtract-only factors that reflect your risk in adopting it — a clean scan proves less on a powerful, unverified or barely-inspectable package, so the grade says so plainly:
| Points | Adoption-risk factor |
|---|---|
| −2 | publisher verification (unlinked) — no provenance/repo link, but the shipped source was fully read |
Capability observations and info notes are shown under Findings but never scored.
Open any row's finding below for the file, line and evidence behind a deduction.
Findings 3
low Shell/command execution in packaging/dev tooling (scripts/connect_agents.py)MTC-SRC-002
In a packaging/dev/install script (shipped, but not the server runtime) (`scripts/connect_agents.py:436`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: return {} proc = subprocess.Popen( ["codex", "app-server", "--listen", "stdio://", "--enable", "hooks"],
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server scripts/connect_agents.py
low Shell/command execution in packaging/dev tooling (scripts/hooks/lmmcp-ingest.py)MTC-SRC-002
In a packaging/dev/install script (shipped, but not the server runtime) (`scripts/hooks/lmmcp-ingest.py:43`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: try: proc = subprocess.Popen( cmd, stdin=subprocess.DEVNULL, stdout=subp
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server scripts/hooks/lmmcp-ingest.py
low Shell/command execution in packaging/dev tooling (tests/test_docs_consistency.py)MTC-SRC-002
In a packaging/dev/install script (shipped, but not the server runtime) (`tests/test_docs_consistency.py:61`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: current(): result = subprocess.run( [sys.executable, str(ROOT / "scripts" / "generate_tools_doc.py"), "--che
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server tests/test_docs_consistency.py
What this scan could not see
- No tools were enumerated, so prompt-injection, capability and toxic-flow analysis had no tool surface to inspect. To grade a package’s real runtime tools, scan the running server: --command "npx -y <package>".
Versions 1
Scan history per published version. The engine is deterministic — the same version always yields the same score, so a changed score means the package itself changed.
| Version | Score | Findings | Engine | Scanned |
|---|---|---|---|---|
v0.25.0 latest |
A 98/100 | 3 | 1.13.0 | 2026-08-25 |
Embed this score
Show this server's live Trust Score in your README, docs or website. The badge is served straight from the registry and updates automatically after every rescan — no API key needed. It links back to this page, so anyone who sees the grade can also read the findings behind it instead of taking a number on faith.
Verify this score yourself
The score above is reproducible: the same package version always yields the same result. Run it locally or over the free API — no account, no LLM, fully deterministic.
npx mcptrustchecker scan local-memory-mcp --online --registry pypiOther implementations of Local Memory 5
Independent packages implementing the same tool, scanned with the same engine. Compare all 6 side by side →
Persistent local memory for any MCP client. SQLite + FTS5 + sqlite-vec hybrid retrieval, bi-temporal asOf queries, contradiction detection, LLM-free reflection. Multilingual embeddings. Knowledge Graph. No cloud, no API keys.
Lightweight memory server with SQLite-based vector search and context tagging.
Local memory service for coding copilot agents.
Local memory server for AI agents using SQLite and MCP
Local Memory MCP Server - AI-powered persistent memory system for Claude Code, Claude Desktop, Gemini, Codex, OpenCode and other MCP-compatible tools
More in Databases
Security scan results for the A5sql MCP server.
Expose AgentsKit tools as an MCP server — use them from Claude Desktop, Cursor, Windsurf, or any MCP host.
MCP server for Aiven cloud data platform - manage PostgreSQL, Kafka, and other services
MCP Server for All-Inkl.com hosting via KAS API
Structured aquarium, marine, terrarium and paludarium data for AI agents.
MCP server that gives your AI agent real vehicle data — specs, representative images, federal recalls, owner complaints, service bulletins, defect investigations, and OBD-II DTC reference — from the CarVector API.