Reflect (PyPI) MCP Server
reflect-mcp
PyPI
v0.6.0
Published by an unidentified publisher — no publish provenance and no public repository, so the publisher could not be verified and the source cannot be independently located.
Reflection's autonomous runtime — wake, read prior state, do useful work, write back, sleep.
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 − 8 = 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 |
| −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 11
high Dynamic code execution in server code (reflect_mcp/lib/sanitize.py)MTC-SRC-001
In the server's implementation (`reflect_mcp/lib/sanitize.py:554`): 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: """ Run Layer 2 eval (with cache). Returns (result, from_cache: bool). On API failure returns (result with 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 reflect_mcp/lib/sanitize.py
high Shell/command execution in server code (reflect_mcp/cli/docs.py)MTC-SRC-002
In the server's implementation (`reflect_mcp/cli/docs.py:45`): 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: less") try: subprocess.run([pager, str(doc_path)]) except FileNotFoundError: # Fallback: just pr
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 reflect_mcp/cli/docs.py
high Shell/command execution in server code (reflect_mcp/cli/doctor.py)MTC-SRC-002
In the server's implementation (`reflect_mcp/cli/doctor.py:65`): 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: out = subprocess.run( ["crontab", "-l"], capture_output=True, text
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 reflect_mcp/cli/doctor.py
high Shell/command execution in server code (reflect_mcp/cli/main.py)MTC-SRC-002
In the server's implementation (`reflect_mcp/cli/main.py:1307`): 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: continue r = subprocess.run( ["sudo", "chattr", "+i", str(path)], 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 reflect_mcp/cli/main.py
high Shell/command execution in server code (reflect_mcp/cli/ops/init.py)MTC-SRC-002
In the server's implementation (`reflect_mcp/cli/ops/init.py:447`): 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: None: try: subprocess.run( ["git", "init", str(project_dir)], check=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 reflect_mcp/cli/ops/init.py
high Shell/command execution in server code (reflect_mcp/cli/ops/wake.py)MTC-SRC-002
In the server's implementation (`reflect_mcp/cli/ops/wake.py:199`): 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: pen("w") proc = subprocess.Popen( [sys.executable, "-m", "reflect_mcp.runtime.wake"], en
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 reflect_mcp/cli/ops/wake.py
high Shell/command execution in server code (reflect_mcp/cli/track.py)MTC-SRC-002
In the server's implementation (`reflect_mcp/cli/track.py:273`): 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: _path] try: subprocess.run(cmd) except KeyboardInterrupt: pass def cmd_track_logs(args) -> Non
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 reflect_mcp/cli/track.py
high Shell/command execution in server code (reflect_mcp/cli/tui/dashboard_app.py)MTC-SRC-002
In the server's implementation (`reflect_mcp/cli/tui/dashboard_app.py:1039`): 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: .suspend(): subprocess.run(["less", "-R", tmp_path], check=False) import os as _os try:
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 reflect_mcp/cli/tui/dashboard_app.py
high Shell/command execution in server code (reflect_mcp/cli/tui/inbox_app.py)MTC-SRC-002
In the server's implementation (`reflect_mcp/cli/tui/inbox_app.py:693`): 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: .suspend(): subprocess.run([editor, str(path)]) # v0.4.91 (item 33 escalation): selection-mode toggle.
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 reflect_mcp/cli/tui/inbox_app.py
high Shell/command execution in server code (reflect_mcp/cli/tui/session_view.py)MTC-SRC-002
In the server's implementation (`reflect_mcp/cli/tui/session_view.py:625`): 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( ["reflect", "wake", "start", self._track],
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 reflect_mcp/cli/tui/session_view.py
high Shell/command execution in server code (reflect_mcp/cli/wake.py)MTC-SRC-002
In the server's implementation (`reflect_mcp/cli/wake.py:200`): 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: pen("w") proc = subprocess.Popen( [sys.executable, "-m", "reflect_mcp.runtime.wake"], en
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 reflect_mcp/cli/wake.py
Tools 12
Each tool and what it can reach — statically extracted from the published source.
costno sensitive capabilitydocsno sensitive capabilitydoctorno sensitive capabilityfollowupno sensitive capabilityinboxno sensitive capabilityprojectno sensitive capabilityreflect_doctorno sensitive capabilityreportno sensitive capabilityscheduleno sensitive capabilitytrackno sensitive capability
Show 2 more tools ↓
track_adminno sensitive capabilitywakeno sensitive capability
What this scan could not see
- Tools were statically extracted from the published source (12 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 |
|---|---|---|---|---|
v0.6.0 latest |
A 92/100 | 11 | 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 reflect-mcp --online --registry pypiOther implementations of Reflect 1
Independent packages implementing the same tool, scanned with the same engine. Compare all 2 side by side →
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