Kicad Mcp Pro (oaslananka) MCP Server
kicad-mcp-pro
PyPI
v3.34.0
Published by oaslananka — 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.
Production-grade MCP server for KiCad EDA—PCB design, DRC, simulation, BOM, DFM, and manufacturing.
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 11
high Shell/command execution in server code (src/kicad_mcp/bridge.py)MTC-SRC-002
In the server's implementation (`src/kicad_mcp/bridge.py:526`): 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: 0000200 proc = subprocess.Popen( args, stdout=subprocess.DEVNULL, stderr=su
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/kicad_mcp/bridge.py
high Shell/command execution in server code (src/kicad_mcp/diagnostics.py)MTC-SRC-002
In the server's implementation (`src/kicad_mcp/diagnostics.py:283`): 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_executable, "-C", str(repo), *args], check=False,
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/kicad_mcp/diagnostics.py
high Shell/command execution in server code (src/kicad_mcp/discovery.py)MTC-SRC-002
In the server's implementation (`src/kicad_mcp/discovery.py:148`): 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( [str(cli_path), "--version"], 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/kicad_mcp/discovery.py
high Shell/command execution in server code (src/kicad_mcp/evals/live_adapters.py)MTC-SRC-002
In the server's implementation (`src/kicad_mcp/evals/live_adapters.py:395`): 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: completed = subprocess.run( list(self._configuration.command), input=request
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/kicad_mcp/evals/live_adapters.py
high Shell/command execution in server code (src/kicad_mcp/evals/reference_agent_runner.py)MTC-SRC-002
In the server's implementation (`src/kicad_mcp/evals/reference_agent_runner.py:690`): 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: ry: completed = subprocess.run( command, input=prompt, cwd=workspace.checkou
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/kicad_mcp/evals/reference_agent_runner.py
high Shell/command execution in server code (src/kicad_mcp/evals/release_policy.py)MTC-SRC-002
In the server's implementation (`src/kicad_mcp/evals/release_policy.py:240`): 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: ble, None) result = subprocess.run( [git, *arguments], cwd=repo_root, check=False, c
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/kicad_mcp/evals/release_policy.py
high Shell/command execution in server code (src/kicad_mcp/server.py)MTC-SRC-002
In the server's implementation (`src/kicad_mcp/server.py:3251`): 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: cmd=cmd) proc = subprocess.Popen( cmd, stdout=sys.stdout, stderr=sys.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 src/kicad_mcp/server.py
high Shell/command execution in server code (src/kicad_mcp/setup.py)MTC-SRC-002
In the server's implementation (`src/kicad_mcp/setup.py:895`): 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( [claude_path, "mcp", "list"], capture_ou
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/kicad_mcp/setup.py
high Shell/command execution in server code (src/kicad_mcp/tools/export_support.py)MTC-SRC-002
In the server's implementation (`src/kicad_mcp/tools/export_support.py:68`): 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( [str(cfg.kicad_cli), *args], cap
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/kicad_mcp/tools/export_support.py
high Shell/command execution in server code (src/kicad_mcp/tools/manufacturing.py)MTC-SRC-002
In the server's implementation (`src/kicad_mcp/tools/manufacturing.py:262`): 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( cmd, capture_output=True, text=T
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/kicad_mcp/tools/manufacturing.py
medium Dynamic module load from a non-literal (src/kicad_mcp/tools/schematic.py)MTC-SRC-005
In the server's implementation (`src/kicad_mcp/tools/schematic.py:2075`): 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: metadata contract = __import__( "kicad_mcp.models.live_preview", fromlist=["LivePreviewPayload"] ).LiveP
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/kicad_mcp/tools/schematic.py
Tools 82
Each tool and what it can reach — statically extracted from the published source.
check_power_integrityno sensitive capabilityemc_check_decoupling_placementno sensitive capabilityemc_check_differential_pair_symmetryno sensitive capabilityemc_check_ground_plane_voidsno sensitive capabilityemc_check_high_speed_routing_rulesno sensitive capabilityemc_check_return_path_continuityno sensitive capabilityemc_check_split_plane_crossingno sensitive capabilityemc_check_via_stitchingno sensitive capabilityemc_run_full_complianceno sensitive capabilitykicad_capability_parityno sensitive capability
Show 72 more tools ↓
kicad_get_tools_in_categoryno sensitive capabilitykicad_list_tool_categoriesno sensitive capabilitypcb_add_blind_viano sensitive capabilitypcb_add_circleno sensitive capabilitypcb_add_microviano sensitive capabilitypcb_add_rectangleno sensitive capabilitypcb_add_segmentno sensitive capabilitypcb_add_textno sensitive capabilitypcb_add_tracks_bulkno sensitive capabilitypcb_get_live_edit_stateno sensitive capabilitypcb_highlight_netno sensitive capabilitypcb_refill_zonesno sensitive capabilitypcb_saveno sensitive capabilitypcb_set_board_outlineno sensitive capabilitypcb_set_net_classno sensitive capabilitypdn_calculate_voltage_dropno sensitive capabilitypdn_check_copper_weightno sensitive capabilitypdn_generate_power_planeno sensitive capabilitypdn_recommend_decoupling_capsno sensitive capabilitysch_add_busno sensitive capabilitysch_add_bus_wire_entryno sensitive capabilitysch_add_global_labelno sensitive capabilitysch_add_hierarchical_labelno sensitive capabilitysch_add_labelno sensitive capabilitysch_add_labelsno sensitive capabilitysch_add_no_connectno sensitive capabilitysch_add_pin_labelsno sensitive capabilitysch_add_power_symbolno sensitive capabilitysch_add_sheet_pinno sensitive capabilitysch_add_wireno sensitive capabilitysch_analyze_net_compilationno sensitive capabilitysch_annotateno sensitive capabilitysch_auto_place_symbolsno sensitive capabilitysch_build_circuitno sensitive capabilitysch_check_power_flagsno sensitive capabilitysch_create_sheetno sensitive capabilitysch_delete_labelno sensitive capabilitysch_delete_no_connectno sensitive capabilitysch_delete_sheetno sensitive capabilitysch_delete_symbolno sensitive capabilitysch_delete_wireno sensitive capabilitysch_get_connectivity_graphno sensitive capabilitysch_get_labelsno sensitive capabilitysch_get_net_namesno sensitive capabilitysch_get_pin_positionsno sensitive capabilitysch_get_sheet_infono sensitive capabilitysch_get_wiresno sensitive capabilitysch_import_sheet_pinsno sensitive capabilitysch_list_sheet_pinsno sensitive capabilitysch_list_sheetsno sensitive capabilitysch_modify_labelno sensitive capabilitysch_move_labelno sensitive capabilitysch_move_sheetno sensitive capabilitysch_route_wire_between_pinsno sensitive capabilitysch_spread_sheetsno sensitive capabilitysch_trace_netno sensitive capabilitysch_wire_sheet_pinsno sensitive capabilitysi_analyze_high_speed_channelno sensitive capabilitysi_bind_interfaces_to_net_classesno sensitive capabilitysi_calculate_decoupling_placementno sensitive capabilitysi_calculate_trace_impedanceno sensitive capabilitysi_calculate_trace_width_for_impedanceno sensitive capabilitysi_check_differential_pair_skewno sensitive capabilitysi_check_via_stubno sensitive capabilitysi_generate_stackupno sensitive capabilitysi_get_solver_capabilitiesno sensitive capabilitysi_list_dielectric_materialsno sensitive capabilitysi_synthesize_stackup_for_interfacesno sensitive capabilitysi_validate_length_matchingno sensitive capabilitythermal_calculate_via_countno sensitive capabilitythermal_check_copper_pourno sensitive capabilitythermal_simulate_plane_spreadingno sensitive capability
What this scan could not see
- Tools were statically extracted from the published source (82 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 10
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 |
|---|---|---|---|---|
v3.34.0 latest |
A 93/100 | 11 | 1.13.0 | 2026-09-05 |
v3.33.3 |
A 93/100 | 11 | 1.13.0 | 2026-08-28 |
v3.33.2 |
A 93/100 | 11 | 1.13.0 | 2026-08-27 |
v3.32.0 |
A 93/100 | 11 | 1.13.0 | 2026-08-25 |
v3.31.0 |
A 93/100 | 11 | 1.12.1 | 2026-08-14 |
Show 5 more versions ↓
v3.30.1 |
A 93/100 | 11 | 1.12.1 | 2026-08-05 |
v3.29.2 |
A 93/100 | 11 | 1.12.1 | 2026-07-31 |
v3.29.1 |
A 93/100 | 11 | 1.12.1 | 2026-07-28 |
v3.29.0 |
A 93/100 | 11 | 1.12.1 | 2026-07-27 |
v3.28.0 |
A 93/100 | 11 | 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 kicad-mcp-pro --online --registry pypiOther implementations of Kicad Mcp Pro 1
Independent packages implementing the same tool, scanned with the same engine. Compare all 2 side by side →
More in Other
A Model Context Protocol server implementation for AdGuard Home that enables AI agents to query and manage DNS records, filtering rules and more
Identity oracle and trust layer for autonomous AI agents. Bidirectional KYA and trust scoring.
MCP server with Airtable integration
A free one-minute reset for people, delivered by AI, with no account or personal data.
Access SEC filings efficiently, save time and tokens, and get cited answers.
A smart [MCP](https://modelcontextprotocol.io) server for [AniList](https://anilist.co) that gets your anime/manga taste - not just API calls.