Poe2 MCP Server
poe2-mcp
PyPI
v1.0.8
Published by hivemindoverlord — 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.
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 − 30.6 = 69. What the published surface and source actually contain:
| Points | What was found | Category |
|---|---|---|
| −23.1 | Obfuscated / encoded payload in server code ×2 MTC-SRC-004 | injection |
| −6.3 | Unsafe deserialization MTC-SRC-007 | permissions |
| −1.2 | Excessive ALL-CAPS emphasis in metadata MTC-INJ-CAPS | injection |
2. Client adoption risk — 69 − 11 = 58. 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 |
| ✓ | inspection depth (source) — how much of the target the scan could see |
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 13
critical Completed toxic-flow trifecta across toolsMTC-FLOW-002
This server (without client built-ins) exposes a complete data-exfiltration chain: analyze_character → get_game_config ⇒ import_poe_ninja_url. Untrusted input is ingested, private data is read, and it can be sent to an external sink — and at least one leg is a direct schema wire (⇒), where a producer's output drops straight into a free-text parameter of the next tool, so the chain needs little agent cooperation. Static analysis proves the primitive exists, not that a specific run will occur.
Fix: Remove one leg of the trifecta: isolate untrusted-input tools from secret-reading tools and from egress tools, or require human approval between them.
Location: flow analyze_character → get_game_config → import_poe_ninja_url
high Obfuscated / encoded payload in server code (src/data/fresh_data_provider.py)MTC-SRC-004
In the server's implementation (`src/data/fresh_data_provider.py:35`): Decoding an encoded blob and executing it is how malicious logic is hidden from human review of the source. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: \xbb\xbb\xbb\xbb\xbb\xbb\xbb\xbb
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/data/fresh_data_provider.py
high Obfuscated / encoded payload in server code (src/parsers/datc64_parser.py)MTC-SRC-004
In the server's implementation (`src/parsers/datc64_parser.py:19`): Decoding an encoded blob and executing it is how malicious logic is hidden from human review of the source. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: \xbb\xbb\xbb\xbb\xbb\xbb\xbb\xbb
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/parsers/datc64_parser.py
high Shell/command execution in server code (src/data/update_manager.py)MTC-SRC-002
In the server's implementation (`src/data/update_manager.py:89`): 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: subprocess.run(
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/data/update_manager.py
high Shell/command execution in server code (src/launcher_helpers.py)MTC-SRC-002
In the server's implementation (`src/launcher_helpers.py:55`): 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: subprocess.run(
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/launcher_helpers.py
medium Unconstrained URL/host parameter "url" on "import_poe_ninja_url"MTC-CAP-007
Tool "import_poe_ninja_url" takes a URL/host parameter "url" with no allowlist/pattern. An outbound-request tool with an unbounded destination enables SSRF and cloud-metadata access (e.g. 169.254.169.254).
Fix: Allowlist destinations or constrain the parameter; block private/link-local addresses server-side.
Location: tool import_poe_ninja_url · inputSchema.properties.url
medium Dynamic module load from a non-literal (launch.py)MTC-SRC-005
In the server's implementation (`launch.py:120`): 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: __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 launch.py
medium Unsafe deserialization (src/api/cache_manager.py)MTC-SRC-007
In the server's implementation (`src/api/cache_manager.py:159`): Deserializing untrusted data with these APIs can execute arbitrary code (a well-known RCE gadget class). This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: pickle.loads(
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/api/cache_manager.py
low Excessive ALL-CAPS emphasis in metadataMTC-INJ-CAPS
A run of shouted words is a common way to give injected instructions false authority.
Evidence: List all mods with optional filtering by generation type (PREFIX, SUFFIX, IMPLICIT, CORRUPTED) and stat keywords.
Location: tool list_all_mods · description
low Unconstrained path parameter "pob_file_path" on "import_pob"MTC-CAP-008
Tool "import_pob" takes a path parameter "pob_file_path" with no constraint. Without a canonicalize-and-contain check (not visible statically), this permits ../ traversal outside the intended root.
Fix: Resolve and verify the path stays within an allowed root; reject traversal sequences.
Location: tool import_pob · inputSchema.properties.pob_file_path
low Unconstrained path parameter "pob_path" on "pob_install_addon"MTC-CAP-008
Tool "pob_install_addon" takes a path parameter "pob_path" with no constraint. Without a canonicalize-and-contain check (not visible statically), this permits ../ traversal outside the intended root.
Fix: Resolve and verify the path stays within an allowed root; reject traversal sequences.
Location: tool pob_install_addon · inputSchema.properties.pob_path
low Unconstrained path parameter "log_path" on "get_live_game_state"MTC-CAP-008
Tool "get_live_game_state" takes a path parameter "log_path" with no constraint. Without a canonicalize-and-contain check (not visible statically), this permits ../ traversal outside the intended root.
Fix: Resolve and verify the path stays within an allowed root; reject traversal sequences.
Location: tool get_live_game_state · inputSchema.properties.log_path
low Unconstrained path parameter "config_path" on "get_game_config"MTC-CAP-008
Tool "get_game_config" takes a path parameter "config_path" with no constraint. Without a canonicalize-and-contain check (not visible statically), this permits ../ traversal outside the intended root.
Fix: Resolve and verify the path stays within an allowed root; reject traversal sequences.
Location: tool get_game_config · inputSchema.properties.config_path
Toxic flows 1
Cross-tool combinations that form a data-exfiltration primitive (untrusted input → sensitive source → external sink).
What this scan could not see
- Tools were statically extracted from the published source (46 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
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 |
|---|---|---|---|---|
v1.0.8 latest |
F 58/100 | 13 | 1.7.0 | 2026-07-23 |
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 poe2-mcp --online --registry pypiMore in Gaming & Entertainment
Security scan results for the Aether MCP server.
Security scan results for the Bedbook MCP server.
Security scan results for the Cpu Game MCP server.
Security scan results for the Endfield MCP server.
Security scan results for the Game Design MCP server.
Security scan results for the Godot MCP server.