Context Mode MCP Server
context-mode
npm
v1.0.169
Published by mksglu — 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.
MCP plugin that saves 98% of your context window. Works with Claude Code, Gemini CLI, VS Code Copilot, OpenCode, and Codex CLI. Sandboxed code execution, FTS5 knowledge base, and intent-driven search.
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 − 10.6 = 89. What the published surface and source actually contain:
| Points | What was found | Category |
|---|---|---|
| −9.5 | Untrusted input concatenated into a command sink ×2 MTC-SRC-009 | injection |
| −1.2 | Package runs install-time scripts MTC-SUP-010 | supply-chain |
2. Client adoption risk — 89 − 11 = 78. 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 21
high Dynamic code execution in server code (cli.bundle.mjs)MTC-SRC-001
In the server's implementation (`cli.bundle.mjs:494`): Evaluating strings as code is the most direct RCE primitive; if any tool input reaches it, the server executes attacker-chosen code. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: ode.process(l,t));let f=new Function(`${qo.default.self}`,`${qo.default.scope}`,l)(this,this.scope.get());if(this.scope.
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 cli.bundle.mjs
high Dynamic code execution in server code (server.bundle.mjs)MTC-SRC-001
In the server's implementation (`server.bundle.mjs:6`): Evaluating strings as code is the most direct RCE primitive; if any tool input reaches it, the server executes attacker-chosen code. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: ode.process(l,t));let m=new Function(`${Wr.default.self}`,`${Wr.default.scope}`,l)(this,this.scope.get());if(this.scope.
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 server.bundle.mjs
high Shell/command execution in server code (bin/statusline.mjs)MTC-SRC-002
In the server's implementation (`bin/statusline.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: ecFileSync } from "node:child_process"; import { ensureWritableStorageDir, resolveDefaultSessionDir, resolveSessio
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/statusline.mjs
high Shell/command execution in server code (build/adapters/codex/index.js)MTC-SRC-002
In the server's implementation (`build/adapters/codex/index.js:16`): 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 { existsSync, readFileSync, writeFileSync, accessSync, copyFileSync, cons
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 build/adapters/codex/index.js
high Shell/command execution in server code (build/adapters/cursor/index.js)MTC-SRC-002
In the server's implementation (`build/adapters/cursor/index.js: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: { execSync } from "node:child_process"; import { resolve, join } from "node:path"; import { homedir } from "node:os"; 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 build/adapters/cursor/index.js
high Shell/command execution in server code (build/adapters/kimi/index.js)MTC-SRC-002
In the server's implementation (`build/adapters/kimi/index.js: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: ecFileSync } from "node:child_process"; import { readFileSync, writeFileSync, accessSync, copyFileSync, constants, mkdir
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 build/adapters/kimi/index.js
high Shell/command execution in server code (build/adapters/pi/mcp-bridge.js)MTC-SRC-002
In the server's implementation (`build/adapters/pi/mcp-bridge.js:25`): 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 { detectRuntimes } from "../../runtime.js"; import { foreignWorkspaceEnv,
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 build/adapters/pi/mcp-bridge.js
high Shell/command execution in server code (build/cli.js)MTC-SRC-002
In the server's implementation (`build/cli.js:18`): 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: deExecFile } from "node:child_process"; import { readFileSync, cpSync, accessSync, existsSync, readdirSync, rmSync, clos
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 build/cli.js
high Shell/command execution in server code (build/db-base.js)MTC-SRC-002
In the server's implementation (`build/db-base.js:36`): 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: 0] : rows[0]; } exec(sql) { // bun:sqlite .exec() is single-statement only. // Split multi-state
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 build/db-base.js
high Shell/command execution in server code (build/executor.js)MTC-SRC-002
In the server's implementation (`build/executor.js:1`): 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 { mkdtempSync, writeFileSync, rmSync, existsSync } from "node:fs"; import
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 build/executor.js
high Shell/command execution in server code (build/lifecycle.js)MTC-SRC-002
In the server's implementation (`build/lifecycle.js:22`): 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"; /** Read grandparent PID via `ps -o ppid= -p $PPID`. Returns NaN on failure or W
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 build/lifecycle.js
high Shell/command execution in server code (build/runtime.js)MTC-SRC-002
In the server's implementation (`build/runtime.js:1`): 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 { existsSync } from "node:fs"; import { JS_RUNTIMES } from "./adapters/ty
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 build/runtime.js
medium Untrusted input concatenated into a command sink (build/runtime.js)MTC-SRC-009
In the server's implementation (`build/runtime.js:57`): 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: const out = execSync(`where ${cmd}`, { encoding: "utf-8", stdio: "pipe" }); const hits = out.tri
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server build/runtime.js
medium Untrusted input concatenated into a command sink (hooks/ensure-deps.mjs)MTC-SRC-009
In the server's implementation (`hooks/ensure-deps.mjs:75`): A shell/process command assembled from concatenated or interpolated values is command injection when any part is attacker-influenced — the OWASP canonical RCE flow. Verify what reaches the interpolated value. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: all try { execSync(`${process.platform === "win32" ? "npm.cmd" : "npm"} install ${pkg} --no-package-lock -
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 hooks/ensure-deps.mjs
medium Dynamic module load from a non-literal (bin/statusline.mjs)MTC-SRC-005
In the server's implementation (`bin/statusline.mjs:57`): 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: _analytics = await import(ANALYTICS_URL); } catch { _analytics = null; } return _analytics; } // Test se
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/statusline.mjs
medium Dynamic module load from a non-literal (build/adapters/openclaw/plugin.js)MTC-SRC-005
In the server's implementation (`build/adapters/openclaw/plugin.js:430`): 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: const mod = (await import(diagnosticRuntimeSpecifier)); if (typeof mod?.onDiagnosticEvent === "
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 build/adapters/openclaw/plugin.js
medium Dynamic module load from a non-literal (build/util/plugin-cache-integrity.js)MTC-SRC-005
In the server's implementation (`build/util/plugin-cache-integrity.js:48`): 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: const mod = (await import(url.href)); if (typeof mod?.assertPluginCacheIntegrity === "function") {
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 build/util/plugin-cache-integrity.js
medium Dynamic module load from a non-literal (cli.bundle.mjs)MTC-SRC-005
In the server's implementation (`cli.bundle.mjs:146`): 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: n of t)try{let r=await import(n.href);if(typeof r?.assertPluginCacheIntegrity=="function")return ps=r,ps}catch(r){e=r}r
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 cli.bundle.mjs
medium Dynamic module load from a non-literal (server.bundle.mjs)MTC-SRC-005
In the server's implementation (`server.bundle.mjs:153`): 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: n of t)try{let r=await import(n.href);if(typeof r?.assertPluginCacheIntegrity=="function")return is=r,is}catch(r){e=r}r
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 server.bundle.mjs
medium Dynamic module load from a non-literal (start.mjs)MTC-SRC-005
In the server's implementation (`start.mjs:353`): 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: const mod=await import(nhPath); const fn=mod.normalizeHooksJsonOnly||mod.normalizeHooksOnStartup;
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 start.mjs
low Package runs install-time scripts (postinstall)MTC-SUP-010
"context-mode" 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.mjs
Fix: Review the scripts; install with --ignore-scripts where possible and vet what they do.
Location: package context-mode
Tools 11
Each tool and what it can reach — statically extracted from the published source.
ctx_fetch_and_indexingests untrusted inputctx_searchingests untrusted inputctx_batch_executeno sensitive capabilityctx_doctorno sensitive capabilityctx_executeno sensitive capabilityctx_execute_fileno sensitive capabilityctx_indexno sensitive capabilityctx_insightno sensitive capabilityctx_purgeno sensitive capabilityctx_statsno sensitive capability
Show 1 more tool ↓
ctx_upgradeno sensitive capability
What this scan could not see
- Tools were statically extracted from the published source (11 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 |
|---|---|---|---|---|
v1.0.169 latest |
C 78/100 | 21 | 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 context-mode --onlineMore in Developer Tools
Hotel booking MCP server — 300K+ properties, real confirmation numbers, loyalty programs. Builders monetize every booking via Stripe Connect. The first MCP server that completes real hotel reservations inside AI conversations.
Manage AdGuard Home through AI assistants
Read-only Azure DevOps for MCP clients using only your existing browser session — no PAT, no Azure CLI. Browse work items, pull requests, comments, attachments and Artifacts feeds across every project, repo and feed you can access.
MCP server for Adobe Experience Manager Assets integration development
Servidor MCP para el tiempo oficial de España (API pública OpenData de AEMET). Predicción, observación y avisos como herramientas MCP tipadas.
A standalone MCP stdio bridge for Affinity by Canva's local MCP SSE server.