Claude Mem Lite MCP Server
claude-mem-lite
npm
v5.4.0
Published by sdsrss — no publish provenance, so origin is unverified, but the source is public: the repository link below is self-declared yet readable, so you can inspect the code before adopting it.
Persistent long-term memory for Claude Code via MCP — captures coding decisions, bugfixes, and context across sessions. Hybrid FTS5 + TF-IDF search with episode batching. Single SQLite DB, no external services. A lighter, lower-cost alternative to claude-
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 − 6.3 = 94. What the published surface and source actually contain:
| Points | What was found | Category |
|---|---|---|
| −6.3 | Untrusted input concatenated into a command sink MTC-SRC-009 | injection |
2. Client adoption risk — 94 − 11 = 83. 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 |
|---|---|
| −10 | capability blast radius (critical) — client exposure if the model is manipulated |
| −1 | publisher verification (public source) — no provenance, but the source is public and inspectable |
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 12
high Shell/command execution in server code (haiku-client.mjs)MTC-SRC-002
In the server's implementation (`haiku-client.mjs:8`): 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: FileSync, spawn } from 'child_process'; import { mkdirSync } from 'fs'; import { readFileSync } from 'fs'; import { join
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 haiku-client.mjs
high Shell/command execution in server code (hook-shared.mjs)MTC-SRC-002
In the server's implementation (`hook-shared.mjs:4`): 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: import { spawn } from 'child_process'; import { randomUUID } from 'crypto'; import { join } from 'path'; import { exi
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 hook-shared.mjs
high Shell/command execution in server code (hook-update.mjs)MTC-SRC-002
In the server's implementation (`hook-update.mjs:5`): 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: ecFileSync } from 'node:child_process'; import { readFileSync, writeFileSync, copyFileSync, readdirSync, exist
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 hook-update.mjs
high Shell/command execution in server code (lib/binding-probe.mjs)MTC-SRC-002
In the server's implementation (`lib/binding-probe.mjs:9`): 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: spawnSync } from 'node:child_process'; import { existsSync, renameSync } from 'node:fs'; import { createRequire } from
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 lib/binding-probe.mjs
high Shell/command execution in server code (lib/git-state.mjs)MTC-SRC-002
In the server's implementation (`lib/git-state.mjs:5`): 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: { execFileSync } from 'child_process'; const GIT_TIMEOUT_MS = 1500; // Strip inherited GIT_* env so child `git` opera
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 lib/git-state.mjs
high Shell/command execution in server code (lib/save-enrich.mjs)MTC-SRC-002
In the server's implementation (`lib/save-enrich.mjs:31`): 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: import { spawn } from 'child_process'; import { join, dirname } from 'path'; import { fileURLToPath } from 'url'; impor
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 lib/save-enrich.mjs
high Shell/command execution in server code (mem-cli.mjs)MTC-SRC-002
In the server's implementation (`mem-cli.mjs:76`): 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: ort { spawnSync } from 'child_process'; import { readFileSync, existsSync, readdirSync, statSync } from 'fs'; // v2.41:
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 mem-cli.mjs
medium Untrusted input concatenated into a command sink (hook-update.mjs)MTC-SRC-009
In the server's implementation (`hook-update.mjs:847`): A shell/process command assembled from concatenated or interpolated values is command injection when any part is attacker-influenced — the OWASP canonical RCE flow. Verify what reaches the interpolated value. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: ringify(s); try { execSync(`${q(process.execPath)} ${q(join(targetDir, 'cli.mjs'))} help`, { timeout: 20000,
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 hook-update.mjs
low Shell/command execution in packaging/dev tooling (install.mjs)MTC-SRC-002
In a packaging/dev/install script (shipped, but not the server runtime) (`install.mjs:4`): 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: c, execFileSync } from 'child_process'; import { readFileSync, writeFileSync, existsSync, rmSync, mkdirSync,
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 install.mjs
low Shell/command execution in packaging/dev tooling (scripts/binding-probe-cli.mjs)MTC-SRC-002
In a packaging/dev/install script (shipped, but not the server runtime) (`scripts/binding-probe-cli.mjs:24`): 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: spawnSync } from 'node:child_process'; import { dirname, join } from 'node:path'; import { fileURLToPath, pathToFileURL
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/binding-probe-cli.mjs
low Shell/command execution in packaging/dev tooling (scripts/hook-launcher.mjs)MTC-SRC-002
In a packaging/dev/install script (shipped, but not the server runtime) (`scripts/hook-launcher.mjs:30`): 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: spawnSync } from 'node:child_process'; import { dirname, join, isAbsolute } from 'node:path'; import { fileURLToPath, p
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/hook-launcher.mjs
low Dynamic module load from a non-literal in packaging/dev tooling (scripts/hook-launcher.mjs)MTC-SRC-005
In a packaging/dev/install script (shipped, but not the server runtime) (`scripts/hook-launcher.mjs:179`): Loading a module chosen at runtime (from a variable) can pull in and run attacker-influenced code paths. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: .now()}` : ''); await import(url); } // Two ERR_MODULE_NOT_FOUND shapes reach here (both verified against Node 22): /
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/hook-launcher.mjs
Tools 18
Each tool and what it can reach — statically extracted from the published source.
mem_browseingests untrusted inputmem_compressno sensitive capabilitymem_deferno sensitive capabilitymem_defer_dropno sensitive capabilitymem_defer_listno sensitive capabilitymem_deleteno sensitive capabilitymem_exportno sensitive capabilitymem_fts_checkno sensitive capabilitymem_getno sensitive capabilitymem_maintainno sensitive capability
Show 8 more tools ↓
mem_optimizeno sensitive capabilitymem_recallno sensitive capabilitymem_recentno sensitive capabilitymem_saveno sensitive capabilitymem_searchno sensitive capabilitymem_statsno sensitive capabilitymem_timelineno sensitive capabilitymem_updateno sensitive capability
What this scan could not see
- Tools were statically extracted from the published source (18 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".
Versions 10
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 |
|---|---|---|---|---|
v5.4.0 latest |
B 83/100 | 12 | 1.13.0 | 2026-09-07 |
v4.0.3 |
B 83/100 | 12 | 1.13.0 | 2026-09-06 |
v3.95.0 |
B 83/100 | 12 | 1.13.0 | 2026-09-05 |
v3.92.0 |
B 83/100 | 12 | 1.13.0 | 2026-09-04 |
v3.84.0 |
B 83/100 | 12 | 1.13.0 | 2026-09-01 |
Show 5 more versions ↓
v3.83.0 |
B 83/100 | 12 | 1.13.0 | 2026-08-31 |
v3.79.0 |
B 83/100 | 12 | 1.13.0 | 2026-08-25 |
v3.77.0 |
B 83/100 | 12 | 1.12.1 | 2026-08-24 |
v3.73.0 |
B 83/100 | 12 | 1.12.1 | 2026-08-22 |
v3.72.1 |
B 83/100 | 13 | 1.12.1 | 2026-08-19 |
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 claude-mem-lite --onlineMore in Productivity & Workflow
MCP AgentChat - 让 AI Agent 通过 Telegram 与用户实时交互：发送消息、图片，等待用户回复
A Model Context Protocol (MCP) server for Airthings Air Quality Monitor devices.
MCP server for Anki
TypeScript package for reading and searching Apple Notes on macOS via direct SQLite access. Includes markdown conversion, attachment support, and offers a local MCP server!
Verified biotech catalyst calendar (PDUFA/AdComm/trial readouts) anchored to official sources.
Appointment booking platform letting agents check provider availability and create bookings.