Kindex MCP Server
kindex
PyPI
v0.29.0
Published by jmcentire — 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 − 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 12
high Tool "remind_exec" exposes command/code executionMTC-CAP-001
Tool "remind_exec" appears to run shell commands or evaluate code (keyword "exec" in tool name). Arbitrary execution driven by model input is one of the most dangerous MCP capabilities; combined with any untrusted input it becomes RCE.
Fix: Sandbox execution, allowlist commands/arguments, and never pass model output to a shell unescaped.
Location: tool remind_exec
high Shell/command execution in server code (src/kindex/actions.py)MTC-SRC-002
In the server's implementation (`src/kindex/actions.py:169`): 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( command, shell=True, capture_output=True, text=True, tim
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/kindex/actions.py
high Shell/command execution in server code (src/kindex/adapters/code.py)MTC-SRC-002
In the server's implementation (`src/kindex/adapters/code.py:36`): 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: r = subprocess.run( ["ctags", "--version"], capture_output=True, text=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/kindex/adapters/code.py
high Shell/command execution in server code (src/kindex/adapters/git_hooks.py)MTC-SRC-002
In the server's implementation (`src/kindex/adapters/git_hooks.py:154`): 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( ["git", "-C", str(repo_path), "log", f"--max-count={limit}",
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/kindex/adapters/git_hooks.py
high Shell/command execution in server code (src/kindex/adapters/github.py)MTC-SRC-002
In the server's implementation (`src/kindex/adapters/github.py:17`): 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(["gh", "auth", "status"], capture_output=True, tex
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/kindex/adapters/github.py
high Shell/command execution in server code (src/kindex/adapters/linear.py)MTC-SRC-002
In the server's implementation (`src/kindex/adapters/linear.py:28`): 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( ["curl", "-s", "-X", "POST", "https://api.linear.app/gr
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/kindex/adapters/linear.py
high Shell/command execution in server code (src/kindex/attention.py)MTC-SRC-002
In the server's implementation (`src/kindex/attention.py:1295`): 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: ts.""" try: subprocess.Popen( [ sys.executable, "-m",
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/kindex/attention.py
high Shell/command execution in server code (src/kindex/cli.py)MTC-SRC-002
In the server's implementation (`src/kindex/cli.py:5065`): 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: ss result = subprocess.run(["crontab", "-l"], capture_output=True, text=True) if result.returnco
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/kindex/cli.py
high Shell/command execution in server code (src/kindex/code_map.py)MTC-SRC-002
In the server's implementation (`src/kindex/code_map.py:37`): 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: r = subprocess.run( ["git", "rev-parse", "HEAD"], cwd=str(directory),
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/kindex/code_map.py
high Shell/command execution in server code (src/kindex/config.py)MTC-SRC-002
In the server's implementation (`src/kindex/config.py:496`): 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: y: result = subprocess.run( command, capture_output=True, text=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 src/kindex/config.py
high Shell/command execution in server code (src/kindex/dream.py)MTC-SRC-002
In the server's implementation (`src/kindex/dream.py:588`): 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: log_fd: proc = subprocess.Popen( cmd, start_new_session=True, stdout=log_fd
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/kindex/dream.py
low Mutating tool "remind_exec" declares no destructiveHintMTC-CAP-005
Tool "remind_exec" can mutate/egress but declares no destructiveHint. Clients that don't default to spec-safe behavior may not prompt before running it.
Fix: Declare accurate annotations, and gate destructive tools on user confirmation regardless.
Location: tool remind_exec
Tools 52
Each tool and what it can reach — statically extracted from the published source.
remind_execruns code / shelladdno sensitive capabilityaskno sensitive capabilitychangelogno sensitive capabilitycontextno sensitive capabilitycoord_attachno sensitive capabilitycoord_endno sensitive capabilitycoord_injectno sensitive capabilitycoord_joinno sensitive capabilitycoord_listno sensitive capability
Show 42 more tools ↓
coord_postno sensitive capabilitycoord_readno sensitive capabilitycoord_startno sensitive capabilitydreamno sensitive capabilityeditno sensitive capabilitygraph_healno sensitive capabilitygraph_mergeno sensitive capabilitygraph_statsno sensitive capabilityingestno sensitive capabilitylearnno sensitive capabilitylinkno sensitive capabilitylist_nodesno sensitive capabilitylock_acquireno sensitive capabilitylock_releaseno sensitive capabilitymode_activateno sensitive capabilitymode_createno sensitive capabilitymode_exportno sensitive capabilitymode_importno sensitive capabilitymode_listno sensitive capabilitymode_seedno sensitive capabilitymode_showno sensitive capabilityremind_checkno sensitive capabilityremind_createno sensitive capabilityremind_doneno sensitive capabilityremind_listno sensitive capabilityremind_snoozeno sensitive capabilitysearchno sensitive capabilityshowno sensitive capabilitystatusno sensitive capabilitysuggestno sensitive capabilitysupersedeno sensitive capabilitytag_resumeno sensitive capabilitytag_startno sensitive capabilitytag_updateno sensitive capabilitytask_addno sensitive capabilitytask_claimno sensitive capabilitytask_doneno sensitive capabilitytask_listno sensitive capabilitytask_releaseno sensitive capabilitywatch_addno sensitive capabilitywatch_listno sensitive capabilitywatch_resolveno sensitive capability
What this scan could not see
- Tools were statically extracted from the published source (52 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 |
|---|---|---|---|---|
v0.29.0 latest |
A 93/100 | 12 | 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 kindex --online --registry pypiMore in Data Science & ML
Security scan results for the 2sio MCP server.
Security scan results for the Add MCP server.
Security scan results for the Ai Archive MCP server.
Security scan results for the Aira Semanticscholar MCP server.
Security scan results for the Auseklis MCP server.
Security scan results for the Brewers Almanack MCP server.