Roampal MCP Server
roampal
PyPI
v0.5.9
Published by roampal-ai — 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.
Outcome-based persistent memory for AI coding tools (Claude Code, OpenCode)
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 − 6.3 = 94. What the published surface and source actually contain:
| Points | What was found | Category |
|---|---|---|
| −6.3 | Untrusted input concatenated into a command sink MTC-SRC-009 | injection |
2. Client adoption risk — 94 − 7 = 87. 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 9
high Shell/command execution in server code (roampal/cli.py)MTC-SRC-002
In the server's implementation (`roampal/cli.py:518`): 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( [python_exe, "-c", "import roampal"], capture_output=True, 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 roampal/cli.py
high Shell/command execution in server code (roampal/hooks/stop_hook.py)MTC-SRC-002
In the server's implementation (`roampal/hooks/stop_hook.py:80`): 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( ["netstat", "-ano"], capture_output=True, text=True, timeout=5
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 roampal/hooks/stop_hook.py
high Shell/command execution in server code (roampal/hooks/user_prompt_submit_hook.py)MTC-SRC-002
In the server's implementation (`roampal/hooks/user_prompt_submit_hook.py:80`): 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: t result = subprocess.run( ["netstat", "-ano"], capture_output=True, text=True, timeout=5
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 roampal/hooks/user_prompt_submit_hook.py
high Shell/command execution in server code (roampal/mcp/server.py)MTC-SRC-002
In the server's implementation (`roampal/mcp/server.py:327`): 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: _fastapi_process = subprocess.Popen( cmd, stdout=subprocess.DEVNULL, stderr=
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 roampal/mcp/server.py
high Shell/command execution in server code (roampal/plugins/opencode/roampal.ts)MTC-SRC-002
In the server's implementation (`roampal/plugins/opencode/roampal.ts:598`): 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: spawn } = await import("child_process") const port = ROAMPAL_PORT // 1. Kill whatever is on the port tr
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 roampal/plugins/opencode/roampal.ts
medium Untrusted input concatenated into a command sink (roampal/plugins/opencode/roampal.ts)MTC-SRC-009
In the server's implementation (`roampal/plugins/opencode/roampal.ts:609`): 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: (pid)) { execSync(`taskkill /pid ${pid} /f`, { timeout: 5000, windowsHide: true }) debugLo
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 roampal/plugins/opencode/roampal.ts
medium Dynamic module load from a non-literal (roampal/cli.py)MTC-SRC-005
In the server's implementation (`roampal/cli.py:1957`): 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: : module = __import__(import_name) version = getattr(module, "__version__", "?")
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 roampal/cli.py
low Shell/command execution in packaging/dev tooling (roampal/backend/modules/memory/tests/integration/test_chromadb_integration.py)MTC-SRC-002
In a packaging/dev/install script (shipped, but not the server runtime) (`roampal/backend/modules/memory/tests/integration/test_chromadb_integration.py:681`): 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: 30) ''' child = subprocess.Popen([ sys.executable, "-c", child_code,
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 roampal/backend/modules/memory/tests/integration/test_chromadb_integration.py
low Shell/command execution in packaging/dev tooling (roampal/backend/modules/memory/tests/unit/test_sqlite_wal.py)MTC-SRC-002
In a packaging/dev/install script (shipped, but not the server runtime) (`roampal/backend/modules/memory/tests/unit/test_sqlite_wal.py:196`): 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: us. ''' child = subprocess.Popen([sys.executable, "-c", child_code, str(db_file), str(marker_file)]) 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 roampal/backend/modules/memory/tests/unit/test_sqlite_wal.py
Tools 6
Each tool and what it can reach — statically extracted from the published source.
add_to_memory_bankno sensitive capabilitydelete_memoryno sensitive capabilityrecord_responseno sensitive capabilityscore_memoriesno sensitive capabilitysearch_memoryno sensitive capabilityupdate_memoryno sensitive capability
What this scan could not see
- Tools were statically extracted from the published source (6 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 3
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 |
|---|---|---|---|---|
v0.5.9 latest |
B 87/100 | 9 | 1.13.0 | 2026-08-28 |
v0.5.8 |
B 87/100 | 7 | 1.13.0 | 2026-08-25 |
v0.5.7 |
B 87/100 | 7 | 1.12.1 | 2026-07-27 |
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 roampal --online --registry pypiMore in Data Science & ML
MCP server for 2s.io — 575+ pay-per-call tools for AI agents — ground-truth data, AI gateway, and agent infra (storage, locks, queues, watchers). x402 USDC on Base/Solana, no API keys, upto usage billing, free trials.
ArXiv preprints + Google Scholar papers, with citation counts in one query.
Add MCP servers to your favorite coding agents with a single command.
Help agents automatically write and test stories for your UI components
Model Context Protocol server for AI-Archive platform - enables AI agents to discover, submit, and review research papers
MCP server for Semantic Scholar research workflows with stdio and Streamable HTTP transports.