Totalrecallai MCP Server
totalrecallai
npm
v4.0.2
Published by auriti-labs — 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.
Your AI remembers everything. Persistent cross-session memory for AI coding assistants. Works with Claude Code, Cursor, Windsurf, Cline, and any MCP-compatible editor.
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 − 1.2 = 99. What the published surface and source actually contain:
| Points | What was found | Category |
|---|---|---|
| −1.2 | Package runs install-time scripts MTC-SUP-010 | supply-chain |
2. Client adoption risk — 99 − 7 = 92. 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 |
|---|---|
| −6 | capability blast radius (high) — 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 15
high Shell/command execution in server code (plugin/dist/cli/contextkit.js)MTC-SRC-002
In the server's implementation (`plugin/dist/cli/contextkit.js:2337`): 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: Sync, spawnSync } from "child_process"; import { join as join5, dirname as dirname2 } from "path"; import { existsSync a
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 plugin/dist/cli/contextkit.js
high Shell/command execution in server code (plugin/dist/hooks/agentSpawn.js)MTC-SRC-002
In the server's implementation (`plugin/dist/hooks/agentSpawn.js:1175`): 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: execSync } = __require("child_process"); const gitRoot = execSync("git rev-parse --show-toplevel", { cwd,
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 plugin/dist/hooks/agentSpawn.js
high Shell/command execution in server code (plugin/dist/hooks/kiro-hooks.js)MTC-SRC-002
In the server's implementation (`plugin/dist/hooks/kiro-hooks.js:2619`): 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: execSync } = __require("child_process"); const gitRoot = execSync("git rev-parse --show-toplevel", { cwd:
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 plugin/dist/hooks/kiro-hooks.js
high Shell/command execution in server code (plugin/dist/hooks/postToolUse.js)MTC-SRC-002
In the server's implementation (`plugin/dist/hooks/postToolUse.js:1171`): 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: execSync } = __require("child_process"); const gitRoot = execSync("git rev-parse --show-toplevel", { cwd,
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 plugin/dist/hooks/postToolUse.js
high Shell/command execution in server code (plugin/dist/hooks/stop.js)MTC-SRC-002
In the server's implementation (`plugin/dist/hooks/stop.js:1171`): 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: execSync } = __require("child_process"); const gitRoot = execSync("git rev-parse --show-toplevel", { cwd,
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 plugin/dist/hooks/stop.js
high Shell/command execution in server code (plugin/dist/hooks/userPromptSubmit.js)MTC-SRC-002
In the server's implementation (`plugin/dist/hooks/userPromptSubmit.js:1171`): 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: execSync } = __require("child_process"); const gitRoot = execSync("git rev-parse --show-toplevel", { cwd,
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 plugin/dist/hooks/userPromptSubmit.js
high Shell/command execution in server code (plugin/dist/index.js)MTC-SRC-002
In the server's implementation (`plugin/dist/index.js:2619`): 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: execSync } = __require("child_process"); const gitRoot = execSync("git rev-parse --show-toplevel", { cwd:
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 plugin/dist/index.js
high Shell/command execution in server code (plugin/dist/sdk/index.js)MTC-SRC-002
In the server's implementation (`plugin/dist/sdk/index.js:2619`): 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: execSync } = __require("child_process"); const gitRoot = execSync("git rev-parse --show-toplevel", { cwd:
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 plugin/dist/sdk/index.js
high Shell/command execution in server code (plugin/dist/shared/paths.js)MTC-SRC-002
In the server's implementation (`plugin/dist/shared/paths.js:7`): 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: port { execSync } from "child_process"; import { fileURLToPath } from "url"; function getDirname() { if (typeof __dirn
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 plugin/dist/shared/paths.js
high Shell/command execution in server code (plugin/dist/worker-service.js)MTC-SRC-002
In the server's implementation (`plugin/dist/worker-service.js:385`): 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{let{execSync:e}=eo("child_process");return e("git rev-parse --show-toplevel",{cwd:process.cwd(),encoding:"utf8",stdi
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 plugin/dist/worker-service.js
medium Hardcoded egress to an external endpoint (plugin/dist/hooks/postToolUse.js)MTC-SRC-003
In the server's implementation (`plugin/dist/hooks/postToolUse.js:1194`): A hardcoded outbound call to a fixed external host inside server code is a classic exfiltration/telemetry channel — especially paired with reads of local data. 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(), 1500); await fetch(`http://${host}:${port}/api/notify`, { method: "POST", headers: { "Con
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 plugin/dist/hooks/postToolUse.js
medium Hardcoded egress to an external endpoint (plugin/dist/hooks/stop.js)MTC-SRC-003
In the server's implementation (`plugin/dist/hooks/stop.js:1194`): A hardcoded outbound call to a fixed external host inside server code is a classic exfiltration/telemetry channel — especially paired with reads of local data. 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(), 1500); await fetch(`http://${host}:${port}/api/notify`, { method: "POST", headers: { "Con
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 plugin/dist/hooks/stop.js
medium Hardcoded egress to an external endpoint (plugin/dist/hooks/userPromptSubmit.js)MTC-SRC-003
In the server's implementation (`plugin/dist/hooks/userPromptSubmit.js:1194`): A hardcoded outbound call to a fixed external host inside server code is a classic exfiltration/telemetry channel — especially paired with reads of local data. 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(), 1500); await fetch(`http://${host}:${port}/api/notify`, { method: "POST", headers: { "Con
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 plugin/dist/hooks/userPromptSubmit.js
medium Dynamic module load from a non-literal (plugin/dist/worker-service.js)MTC-SRC-005
In the server's implementation (`plugin/dist/worker-service.js:294`): 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: c function ma(t){return import(t)}var Dt=class{constructor(e,r={}){this.registry=e;this.localPluginsDir=r.localPluginsDi
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 plugin/dist/worker-service.js
low Package runs install-time scripts (postinstall)MTC-SUP-010
"totalrecallai" executes postinstall script(s) at install time. An install hook runs at install time; most are routine build/setup, but review what it does before trusting it.
Evidence: node scripts/postinstall.cjs
Fix: Review the scripts; install with --ignore-scripts where possible and vet what they do.
Location: package totalrecallai
Tools 10
Each tool and what it can reach — statically extracted from the published source.
embedding_statsno sensitive capabilitygenerate_reportno sensitive capabilityget_contextno sensitive capabilityget_observationsno sensitive capabilityresume_sessionno sensitive capabilitysave_memoryno sensitive capabilitysearchno sensitive capabilitysemantic_searchno sensitive capabilitystore_knowledgeno sensitive capabilitytimelineno sensitive capability
What this scan could not see
- Tools were statically extracted from the published source (10 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 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 |
|---|---|---|---|---|
v4.0.2 latest |
A 92/100 | 15 | 1.13.0 | 2026-09-07 |
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 totalrecallai --onlineMore in AI, Memory & Reasoning
FDA device & vehicle recall risk for AI agents: recall history, MAUDE trend, risk score.
Open-source MCP server exposing Agent402.Tools' catalog — 500+ strong: 400+ self-hostable tools + 100 multi-tool skill packs (security-audit, trend-analysis, structured-scrape, decode-blob, forecasting-bake-off) for AI agents — browser, web search & answe
Zero-dependency MCP server that gives AI agents a self-updating project memory in AGENTS.md. Returns merge instructions instead of mutating state, so every change is a reviewable diff.
MCP Apps UI resources and server helpers for n8n
MCP server providing comprehensive access to BookStack knowledge management system
MCP server for tracking achievements with STAR methodology