kicad-mcp-pro@4.21.3
CAUTION· not startedPublisher claims: "Production-grade MCP server for KiCad EDA—PCB design, DRC, simulation, BOM, DFM, and manufacturing." Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Coverage
Not started: dependency install failed; the server itself was not observed.- Tested
- the dependency install step · every file read, file written and host contacted by what ran
- Not tested
- server startup · the tool list · tool behavior
What this means for the label: Caution here covers what ran. The server's tools were not exercised with a real credential, so nothing about their behavior is asserted; the credential summary below says what to do with that.
Before you give it your token
- It will ask for
KICAD_API_TOKENKICAD_MCP_AUTH_TOKENConfiguration, not credentials: KICAD_API_SOCKET, KICAD_MCP_DESKTOP_UV, KICAD_MCP_ENABLE_EXPERIMENTAL_TOOLS, KICAD_MCP_HOST, KICAD_MCP_LOCALE, KICAD_MCP_LOG_LEVEL, KICAD_MCP_OPENCODE_CONFIG_VERSION, KICAD_MCP_OPERATING_MODE, KICAD_MCP_PORT, KICAD_MCP_PROJECT_DIR, KICAD_MCP_TELEMETRY_ENABLED, KICAD_MCP_TIMEOUT_MS, KICAD_MCP_TRANSPORT, KICAD_MCP_URL, UV_TOOL_DIR- Where it talks to
- no vendor host named in the codeAlso kicad.org, astral.sh, inspect.ai, buymeacoffee.com, oaslananka.dev — not the publisher's domain; check what for before connecting.
- What we saw when it ran
- no credential files read · no network
- What we could not test
- server startup · the tool list · tool behavior
Connect it with a scoped credential, under the guard, and read the third-party hosts first. The code names kicad.org, astral.sh, inspect.ai, buymeacoffee.com, oaslananka.dev as well as its own vendor. The guard injects KICAD_API_TOKEN, KICAD_MCP_AUTH_TOKEN only into requests to the host you bind (and its subdomains) and refuses the rest.
Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.
What changed since 4.20.4
vet-skills diff kicad-mcp-pro 4.20.4 4.21.3In the sandbox, this version reached for nothing 4.20.4 did not. Compared from the two recorded runs, not from source.
4.20.4 was not run in the sandbox (install failed); the comparison covers what static analysis recorded only.
The guard can hold an update like this until someone approves it (runtime.on_change: hold). A change that only shows with a real credential, or on a path the run did not reach, is not in a trace and so not in this comparison.
Is [email protected] safe to install?
KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios; not started: dependency install failed; the server itself was not observed) on 2026-11-21 and scored it 79/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Access to sensitive file paths; Auto-update or dynamic fetch configuration; Auto-update or dynamic fetch configuration. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 1 s · 2 scenarios · 0 deviationsStatic findings
# No ambient project .env is loaded. Pydantic's dotenv source is inertFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.bool, typer.Option("--watch", help=option_help("Watch source files and hot-reload on changes"))Fix: Pin versions and sources; vendor anything fetched at install time."""Start the server in a subprocess and hot-reload on .py source changes.Fix: Pin versions and sources; vendor anything fetched at install time."""CLI entrypoint; never import a cloned project's .env into os.environ."""Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.result = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.self._server_proc = subprocess.Popen(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.proc = subprocess.Popen(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.result = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.{"mcpServers": {"kicad": {"type": "http", "url": url, "env": env}}},Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.result = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out._HAS_TRAY = _HAS_PIL and _importlib_util.find_spec("pystray") is not NoneFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.result = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.server_proc = subprocess.Popen(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.proc = subprocess.Popen(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.result = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.proc = subprocess.Popen(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.os.execl(sys.executable, sys.executable, "-m", "kicad_mcp.server", *sys.argv[1:]) # noqa: S606Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.result = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.result = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.Cost to the agent
Tokens estimated at four characters each. The tool list is re-read by the agent on every turn, so it is the number to compare between servers that do the same job: ranked across the index.
Known vulnerabilities
Not checked against OSV yet; the weekly check has not reached this version.
What would make this Verified
1 point to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%- Unclaimed publisher≈ +8 on the totalClaim oaslananka: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
- Access to sensitive file paths≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
- Auto-update or dynamic fetch configuration≈ +4 on the totalPin versions and sources; vendor anything fetched at install time.
- Python subprocess execution detected≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
- MCP server using network transport (SSE/HTTP)≈ +2 on the totalNamespace tool names and keep tool descriptions literal; no instructions to the agent inside them.
- Dynamic module loading≈ +1 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.