Mykg MCP Server
mykg
PyPI
v0.4.6
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.
AI workflow that turns documents into a confidence-scored knowledge graph with an induced RDFS/OWL ontology
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 7
high Shell/command execution in server code (src/mykg/cli.py)MTC-SRC-002
In the server's implementation (`src/mykg/cli.py:1560`): 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: proc = subprocess.run( cmd, check=False, ti
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/mykg/cli.py
high Shell/command execution in server code (src/mykg/fetch_web.py)MTC-SRC-002
In the server's implementation (`src/mykg/fetch_web.py:115`): 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: }.git" try: subprocess.run( ["git", "clone", "--depth", str(depth), url, str(dest)],
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/mykg/fetch_web.py
high Shell/command execution in server code (src/mykg/llm/claude_cli_adapter.py)MTC-SRC-002
In the server's implementation (`src/mykg/llm/claude_cli_adapter.py:74`): 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: proc = subprocess.run( cmd, input=user, capture_output=
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/mykg/llm/claude_cli_adapter.py
high Shell/command execution in server code (src/mykg/steps/step_preprocess.py)MTC-SRC-002
In the server's implementation (`src/mykg/steps/step_preprocess.py:397`): 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: proc = subprocess.run( cmd, check=False, timeout=_cfg.P
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/mykg/steps/step_preprocess.py
high Shell/command execution in server code (src/mykg/uv_venv.py)MTC-SRC-002
In the server's implementation (`src/mykg/uv_venv.py:29`): 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: proc = subprocess.run( cmd, check=False, 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/mykg/uv_venv.py
low Shell/command execution in packaging/dev tooling (scripts/live_test_grow_schema.py)MTC-SRC-002
In a packaging/dev/install script (shipped, but not the server runtime) (`scripts/live_test_grow_schema.py:101`): 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: ".join(cmd)) proc = subprocess.run(cmd, cwd=str(REPO_ROOT)) return proc.returncode def _tail_run_log(session_r
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 scripts/live_test_grow_schema.py
low Shell/command execution in packaging/dev tooling (tests/test_llm_adapters.py)MTC-SRC-002
In a packaging/dev/install script (shipped, but not the server runtime) (`tests/test_llm_adapters.py:3901`): 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: ed: committed = subprocess.run( ["git", "show", f"HEAD:{rel}"], cwd=repo_root,
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 tests/test_llm_adapters.py
Tools 15
Each tool and what it can reach — statically extracted from the published source.
mykg_find_pathno sensitive capabilitymykg_get_neighborsno sensitive capabilitymykg_get_nodeno sensitive capabilitymykg_get_schemano sensitive capabilitymykg_get_sourceno sensitive capabilitymykg_get_statsno sensitive capabilitymykg_hub_nodesno sensitive capabilitymykg_list_node_typesno sensitive capabilitymykg_list_sessionsno sensitive capabilitymykg_orphan_nodesno sensitive capability
Show 5 more tools ↓
mykg_query_graphno sensitive capabilitymykg_query_subgraphno sensitive capabilitymykg_read_noteno sensitive capabilitymykg_reloadno sensitive capabilitymykg_search_nodesno sensitive capability
What this scan could not see
- Tools were statically extracted from the published source (15 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 7
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 |
|---|---|---|---|---|
v0.4.6 latest |
A 92/100 | 7 | 1.13.0 | 2026-09-04 |
v0.4.3 |
A 92/100 | 6 | 1.13.0 | 2026-08-31 |
v0.4.2 |
A 92/100 | 6 | 1.13.0 | 2026-08-25 |
v0.3.31 |
A 92/100 | 6 | 1.12.1 | 2026-08-01 |
v0.3.29 |
A 92/100 | 6 | 1.12.1 | 2026-07-29 |
Show 2 more versions ↓
v0.3.28 |
A 92/100 | 6 | 1.12.1 | 2026-07-27 |
v0.3.26 |
A 92/100 | 6 | 1.9.0 | 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 mykg --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.