Navvi (fellowship-dev) MCP Server
navvi
PyPI
v3.21.0
Published by fellowship-dev — 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.
Give your AI agent a real browser identity — MCP server with persistent personas, anti-detection browser, and credential vault.
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 5
high Shell/command execution in server code (container/navvi-server.py)MTC-SRC-002
In the server's implementation (`container/navvi-server.py:79`): 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: lly, then force subprocess.run(["pkill", "-TERM", "camoufox-bin"], timeout=3, capture_output=True) for _
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 container/navvi-server.py
high Shell/command execution in server code (src/navvi/__init__.py)MTC-SRC-002
In the server's implementation (`src/navvi/__init__.py:356`): 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: result = subprocess.run( cmd, shell=True, capture_output=True, text=True, timeout=timeout
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/navvi/__init__.py
high Shell/command execution in server code (src/navvi/flows.py)MTC-SRC-002
In the server's implementation (`src/navvi/flows.py:251`): 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: result = subprocess.run( [claude_path, "-p", prompt], capture_output=True,
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/navvi/flows.py
high Shell/command execution in server code (src/navvi/recaptcha.py)MTC-SRC-002
In the server's implementation (`src/navvi/recaptcha.py:236`): 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: NT")} result = subprocess.run( ["claude", "-p", prompt, "--allowedTools", "Read"], env=
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/navvi/recaptcha.py
high Shell/command execution in server code (src/navvi/vision.py)MTC-SRC-002
In the server's implementation (`src/navvi/vision.py:213`): 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: } result = subprocess.run( ["claude", "-p", prompt, "--allowedTools", "Read"], env=
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/navvi/vision.py
Tools 31
Each tool and what it can reach — statically extracted from the published source.
navvi_browseingests untrusted inputnavvi_accountno sensitive capabilitynavvi_atomicno sensitive capabilitynavvi_clickno sensitive capabilitynavvi_contextno sensitive capabilitynavvi_credsno sensitive capabilitynavvi_dragno sensitive capabilitynavvi_fillno sensitive capabilitynavvi_findno sensitive capabilitynavvi_flowno sensitive capability
Show 21 more tools ↓
navvi_holdno sensitive capabilitynavvi_listno sensitive capabilitynavvi_loginno sensitive capabilitynavvi_milestoneno sensitive capabilitynavvi_mousedownno sensitive capabilitynavvi_mousemoveno sensitive capabilitynavvi_mouseupno sensitive capabilitynavvi_openno sensitive capabilitynavvi_personano sensitive capabilitynavvi_pressno sensitive capabilitynavvi_record_gifno sensitive capabilitynavvi_record_startno sensitive capabilitynavvi_record_stopno sensitive capabilitynavvi_screenshotno sensitive capabilitynavvi_scrollno sensitive capabilitynavvi_startno sensitive capabilitynavvi_statusno sensitive capabilitynavvi_stopno sensitive capabilitynavvi_tabno sensitive capabilitynavvi_urlno sensitive capabilitynavvi_vncno sensitive capability
What this scan could not see
- Tools were statically extracted from the published source (31 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 |
|---|---|---|---|---|
v3.21.0 latest |
A 93/100 | 5 | 1.13.0 | 2026-08-25 |
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 navvi --online --registry pypiOther implementations of Navvi 1
Independent packages implementing the same tool, scanned with the same engine. Compare all 2 side by side →
More in Browser Automation
Model Context Protocol (MCP) server that integrates AgentQL data extraction capabilities.
Screenshot any URL or HTML as PNG/JPEG/WebP from your AI agent. Full-page, clean, no install.
MCP server for aria51 accessibility scanner
Bridge any browser web app to Claude Code via MCP
Browserbase’s official MCP server: cloud headless browsers for agents, with sessions and screenshots.
MCP server for AI web browser automation using Browserbase and Stagehand