Reflex Browser MCP Server
reflex-browser
npm
v0.12.2
Published by nitaiaharoni1 — 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.
Token-efficient browser automation for AI agents. Local MCP server + CLI: compressed page snapshots, batched actions, forensic failures.
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 − 7 = 93. 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 8
high Tool "reflex_act" exposes command/code executionMTC-CAP-001
Tool "reflex_act" appears to run shell commands or evaluate code (parameter "eval"). Arbitrary execution driven by model input is one of the most dangerous MCP capabilities; combined with any untrusted input it becomes RCE.
Fix: Sandbox execution, allowlist commands/arguments, and never pass model output to a shell unescaped.
Location: tool reflex_act
high Tool "reflex_eval" exposes command/code executionMTC-CAP-001
Tool "reflex_eval" appears to run shell commands or evaluate code (keyword "eval" in tool name). Arbitrary execution driven by model input is one of the most dangerous MCP capabilities; combined with any untrusted input it becomes RCE.
Fix: Sandbox execution, allowlist commands/arguments, and never pass model output to a shell unescaped.
Location: tool reflex_eval
high Shell/command execution in server code (dist/daemon.js)MTC-SRC-002
In the server's implementation (`dist/daemon.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:Pe}=require("child_process");function Sn(e){if(!e||e<1)return!1;try{return process.kill(e,0),!0}catch(t){retu
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 dist/daemon.js
high Shell/command execution in server code (dist/mcp.js)MTC-SRC-002
In the server's implementation (`dist/mcp.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:le}=require("child_process");function Kt(e){if(!e||e<1)return!1;try{return process.kill(e,0),!0}catch(t){retu
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 dist/mcp.js
high Shell/command execution in server code (dist/reflex.js)MTC-SRC-002
In the server's implementation (`dist/reflex.js:2`): 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: xecFileSync:T}=require("child_process");function Pe(e){if(!e||e<1)return!1;try{return process.kill(e,0),!0}catch(t){retu
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 dist/reflex.js
medium Unconstrained command parameter "eval" on "reflex_act"MTC-CAP-006
Tool "reflex_act" takes a command-shaped parameter "eval" with no enum/pattern constraint. Free-form, model- or attacker-controlled arguments reaching a shell is the command-injection precondition.
Fix: Constrain the parameter (enum/pattern), or build the command from a fixed template with escaped args.
Location: tool reflex_act · inputSchema.properties.eval
low Mutating tool "reflex_act" declares no destructiveHintMTC-CAP-005
Tool "reflex_act" can mutate/egress but declares no destructiveHint. Clients that don't default to spec-safe behavior may not prompt before running it.
Fix: Declare accurate annotations, and gate destructive tools on user confirmation regardless.
Location: tool reflex_act
low Mutating tool "reflex_eval" declares no destructiveHintMTC-CAP-005
Tool "reflex_eval" can mutate/egress but declares no destructiveHint. Clients that don't default to spec-safe behavior may not prompt before running it.
Fix: Declare accurate annotations, and gate destructive tools on user confirmation regardless.
Location: tool reflex_eval
Tools 24
Each tool and what it can reach — statically extracted from the published source.
reflex_actruns code / shellreflex_evalruns code / shelldiagnoseno sensitive capabilitynameno sensitive capabilityone-call-flowno sensitive capabilityReflex getting startedno sensitive capabilityReflex setup checkno sensitive capabilityreflex_authno sensitive capabilityreflex_checkno sensitive capabilityreflex_extractno sensitive capability
Show 14 more tools ↓
reflex_flowno sensitive capabilityreflex_openno sensitive capabilityreflex_readno sensitive capabilityreflex_sessionno sensitive capabilityreflex_shotno sensitive capabilityreflex_tabno sensitive capabilityreflex-browserno sensitive capabilityrerun-flowno sensitive capabilityresearch-pageno sensitive capabilitysave-loginno sensitive capabilitytaskno sensitive capabilityurlno sensitive capabilityvaluesno sensitive capabilitywhatno sensitive capability
What this scan could not see
- Tools were statically extracted from the published source (24 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 5
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 |
|---|---|---|---|---|
v0.12.2 latest |
A 93/100 | 8 | 1.13.0 | 2026-09-09 |
v0.12.0 |
A 93/100 | 8 | 1.13.0 | 2026-09-08 |
v0.11.3 |
A 93/100 | 8 | 1.12.1 | 2026-08-15 |
v0.11.2 |
A 93/100 | 8 | 1.12.1 | 2026-07-27 |
v0.7.2 |
A 93/100 | 8 | 1.10.0 | 2026-07-25 |
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 reflex-browser --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.