A-

mcp.kernelcad.com

https://mcp.kernelcad.com/mcp
92/100 · MCP Trust Grade · checked 5h ago · MCP 2025-06-18
Watched since 2026-06-03 — behavioral baseline locked. We re-check this server's tool surface on a schedule; if it adds, removes, or silently rewrites a tool (rug-pull), we record it.

What it offers — 48 tools · Developer Tools

lookup_authoring_skill

Return the kernelcad-authoring SKILL.md body — conventions for writing .kcad.ts scripts (imports, parameters, evaluation contract, common pitfalls). U

evaluate_script

Run a kernelCAD .kcad.ts script and report pass/fail + feature count + diagnostics. Pass either { file: "<path>" } or { code: "<inline source>" }.

list_features

List the features captured by a kernelCAD script — kind, id, params, inputs, transforms count, suppression. Pass either { file } or { code }.

list_assemblies

List assembly intent captured by a kernelCAD script: assemblies, parts, named connectors, fixed connections, joints, and aggregate assembly models. Pa

inspect_assembly

Evaluate a kernelCAD script and return an agent-facing physical assembly inventory: named parts, bboxes, connectors, mates, disconnected solids, mecha

get_shape_info

Run + recompute a script, return volume/surfaceArea/bbox for one feature (default: last). Pass { file?, code?, feature_id? }.

list_topology

List the canonical face names available on a feature (top/bottom/left/right/front/back for box; top/bottom for cylinder; none for sphere or non-primit

get_edges_of

Return the boundary edges of a named canonical face on an un-transformed primitive — index, centroid, length, isClosed. Pass { file?, code?, feature_i

why_did_this_fail

Walk the upstream chain of a failing feature. Returns the diagnostics of the requested feature plus the diagnostics of every upstream feature in topol

set_param_value

Edit a param() default value in a kernelCAD script. Returns the modified code as text plus diagnostics from re-evaluating the result. Caller persists

add_feature

Insert a new feature line into a kernelCAD script before the last top-level return statement. Returns the modified code as text plus diagnostics from

add_nurbs_surface

Insert a nurbsSurface(...) or surfaceFromCurves(...) call into the user's .kcad.ts. The returned Surface is captured but produces no Shape until you c

add_nurbs_curve

Insert a `nurbsCurve(controlPoints, opts?)` declaration into the user's .kcad.ts immediately before the last top-level return. The returned binding ha

add_surface_from_boundary

Insert a `surfaceFromBoundary([c1, c2, c3, c4], opts?)` declaration into the user's .kcad.ts immediately before the last top-level return. Fills the i

add_hermite_g2

Insert a `hermiteG2(a, b)` declaration into the user's .kcad.ts immediately before the last top-level return. Builds a quintic Hermite Curve3D that in

add_path_spline

Insert a `.spline(points, opts?)` call into an existing PathBuilder chain on the named `chain_anchor` variable. The call is injected at the END of the

trace_from_image

Trace pixel-space features from a reference photo into normalized [0..1] waypoints the agent can map to mm via a known scale anchor and feed to path()

add_path_nurbs_segment

Insert a `.nurbsSegment(controlPoints, opts?)` call into an existing PathBuilder chain on the named `chain_anchor` variable. The call is injected at t

+30 more tools

Spec conformance20%100
Security (OWASP MCP)30%100
Reliability / performance20%84
Tool hygiene15%75
Transparency / provenance15%90

Observed behavior

No proxied traffic observed for this host yet. Connect it at /connect and its grade gains a measured Reliability score + per-tool behavioral evidence — the half a static scan can't produce.

Findings

No blocking issues found in the static + spec checks.
Grade another server

We re-grade mcp.kernelcad.com on a schedule and alert your Slack/webhook the moment its tools change or its grade drops — rug-pull insurance for the connection.

Share this report card

A 1200×630 card with the grade + audit — drop it in a post, Slack, or your repo.

MCP Trust report card — mcp.kernelcad.com grade A-
Share on X Open card image

Embed this grade

A live badge — it re-verifies itself and shows current stability. Static scorecards can't. Paste it in your README or site to show users you're independently audited.

MCP Trust Grade A- · wmcp.sh
[![MCP Trust Grade A-](https://wmcp.sh/mcp/grade/mcp.kernelcad.com/badge.svg)](https://wmcp.sh/mcp/grade/mcp.kernelcad.com)
<a href="https://wmcp.sh/mcp/grade/mcp.kernelcad.com"><img src="https://wmcp.sh/mcp/grade/mcp.kernelcad.com/badge.svg" alt="MCP Trust Grade A- · wmcp.sh"></a>

Agents: check this before connecting

Add the wmcp.sh trust oracle as an MCP server and call grade_mcp_server / check_mcp_drift in your agent's pre-connection gate:

https://wmcp.sh/mcp/trust
How this grade is computed. An open, independent rubric — Spec conformance (20%), Security mapped to the OWASP MCP Top 10 (30%), Reliability (20%), Tool hygiene (15%), Transparency (15%) — run by connecting to the server and inspecting its real MCP surface. The grade is free and identical whether or not the operator pays. v1 uses static + spec signals from a single connection; continuous uptime, real latency, and annotation-truthing (declared readOnly vs observed behavior) layer on via the wmcp.sh proxy.