Local (awareness-sdk) MCP Server
@awareness-sdk/local
npm
v0.11.6
Published by @awareness-sdk — no publish provenance and no public repository, so the publisher could not be verified and the source cannot be independently located.
Local-first AI agent memory system. No account needed.
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 − 12.2 = 88. What the published surface and source actually contain:
| Points | What was found | Category |
|---|---|---|
| −11 | Untrusted input concatenated into a command sink ×3 MTC-SRC-009 | injection |
| −1.2 | Package runs install-time scripts MTC-SUP-010 | supply-chain |
2. Client adoption risk — 88 − 8 = 80. 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 |
| −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 13
high Reads a sensitive credential path or dumps the environment (src/core/scan-defaults.mjs)MTC-SRC-006
In the server's implementation (`src/core/scan-defaults.mjs:134`): Reading private keys / cloud credentials, or serializing the whole environment, is a sensitive-data source that becomes exfiltration when combined with any egress. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: /\.p12$/, /\.pfx$/, /id_rsa/, /id_ed25519/, /id_ecdsa/, /\.htpasswd$/, /token\.json$/, /auth\.json$/, /\.netr
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 src/core/scan-defaults.mjs
high Shell/command execution in server code (bin/awareness-local.mjs)MTC-SRC-002
In the server's implementation (`bin/awareness-local.mjs:17`): 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: rt { spawn } from 'node:child_process'; import fs from 'node:fs'; import path from 'node:path'; import os from 'node:os'
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 bin/awareness-local.mjs
high Shell/command execution in server code (install-transformers.mjs)MTC-SRC-002
In the server's implementation (`install-transformers.mjs:10`): 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'; // Check if @huggingface/transformers is installed try { require.resolve('@hu
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-transformers.mjs
high Shell/command execution in server code (src/core/gitignore-parser.mjs)MTC-SRC-002
In the server's implementation (`src/core/gitignore-parser.mjs:14`): 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 } from 'node:child_process'; import path from 'node:path'; import os from 'node:os'; // --------------------
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 src/core/gitignore-parser.mjs
high Shell/command execution in server code (src/core/workspace-scanner.mjs)MTC-SRC-002
In the server's implementation (`src/core/workspace-scanner.mjs:17`): 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 } from 'node:child_process'; import { loadGitignoreRules } from './gitignore-parser.mjs'; import { isExclude
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 src/core/workspace-scanner.mjs
high Shell/command execution in server code (src/daemon/api-handlers.mjs)MTC-SRC-002
In the server's implementation (`src/daemon/api-handlers.mjs:3`): 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: { execFile } from 'node:child_process'; import { jsonResponse, nowISO, readBody } from './helpers.mjs'; import { apiS
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 src/daemon/api-handlers.mjs
high Shell/command execution in server code (src/daemon/bootstrap.mjs)MTC-SRC-002
In the server's implementation (`src/daemon/bootstrap.mjs:58`): 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: } = await import('node:child_process'); console.log(`[awareness-local] Node.js version changed — auto-rebuilding be
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 src/daemon/bootstrap.mjs
high Shell/command execution in server code (src/daemon/runtime-detect.mjs)MTC-SRC-002
In the server's implementation (`src/daemon/runtime-detect.mjs:10`): 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 } from 'node:child_process'; import { readFileSync, writeFileSync, mkdirSync, existsSync } from 'node:fs'; im
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 src/daemon/runtime-detect.mjs
high Shell/command execution in server code (src/mcp-stdio.mjs)MTC-SRC-002
In the server's implementation (`src/mcp-stdio.mjs:17`): 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: rt { spawn } from 'node:child_process'; import { fileURLToPath } from 'node:url'; import { dirname, join } from 'node:pa
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 src/mcp-stdio.mjs
medium Untrusted input concatenated into a command sink (bin/awareness-local.mjs)MTC-SRC-009
In the server's implementation (`bin/awareness-local.mjs:419`): 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: .platform === 'darwin') exec(`open "${url}"`); else if (process.platform === 'linux') exec(`xdg-open "${url}"`
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 bin/awareness-local.mjs
medium Untrusted input concatenated into a command sink (src/core/workspace-scanner.mjs)MTC-SRC-009
In the server's implementation (`src/core/workspace-scanner.mjs:103`): 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: ry { const output = execSync( `git diff --name-status -M ${lastCommit}..HEAD`, { cwd: projectDir, encodi
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 src/core/workspace-scanner.mjs
medium Untrusted input concatenated into a command sink (src/daemon/runtime-detect.mjs)MTC-SRC-009
In the server's implementation (`src/daemon/runtime-detect.mjs:78`): 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: n null; const out = execSync(`ps -p ${ppid} -o comm=`, { encoding: 'utf8', timeout: 1000 }).trim(); if (!out) re
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 src/daemon/runtime-detect.mjs
low Package runs install-time scripts (postinstall)MTC-SUP-010
"@awareness-sdk/local" 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 install-transformers.mjs
Fix: Review the scripts; install with --ignore-scripts where possible and vet what they do.
Location: package @awareness-sdk/local
Tools 5
Each tool and what it can reach — statically extracted from the published source.
awareness_get_agent_promptno sensitive capabilityawareness_initno sensitive capabilityawareness_lookupno sensitive capabilityawareness_recallno sensitive capabilityawareness_recordno sensitive capability
What this scan could not see
- Tools were statically extracted from the published source (5 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 |
|---|---|---|---|---|
v0.11.6 latest |
B 80/100 | 13 | 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 @awareness-sdk/local --onlineOther implementations of Local 9
Independent packages implementing the same tool, scanned with the same engine. Compare all 10 side by side →
Run Firefly III MCP server locally
TianGong AI MCP Local Server
A local MCP server project
Local MCP Server
Local MCP server for Shopper Context Protocol
Local MCP server for Direxio P2P chat workflows
More 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