splice-cad/splice-cad-mcp (splice-cad/splice-cad-mcp) is an MCP server listed on the M8ven Trust Index. It scores 50 out of 100, grade D. It declares 28 tools. No publisher has claimed this listing.

D
Caution
50/100

splice-cad/splice-cad-mcp

MCP server for Splice CAD cable assembly and wiring harness design tool. Enables AI agents to search parts, build harness plans, create components with specs, and generate manufacturing documentation.

Caution. Specific findings reduced this grade. They are listed on the page. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.

How we verified

Code Verified⚡ Live Monitored: not connected

Verified is a snapshot. Live keeps it current, and builds your track record.

⚡ Connect GitHub → continuous verification on every pushwhy connect →

Who stands behind it

splice-cad

Source: Glama

Is this your MCP?

Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find. Or connect your repo for our deepest verification, Live Monitored: read-only, revoke anytime. What we access →

Install from

The grade above is for the source repository. Registries can serve a different version, so we mark the ones we were not able to read.

// key findings
🚨
Known vulnerabilities in dependencies: 1 critical, 11 high
Affects packages this MCP installs at runtime. Upgrade or remove the affected dependency.
🔐
You'll be asked for 2 credentials: SPLICE_API_KEY, SPLICE_BRIDGE_SECRET
These are read from process.env at runtime. Make sure you trust where they’ll be sent.
// tools this server exposes28 tools

These names and descriptions are the publisher's own, read from the source code. We print them as written. Our assessment is the findings above, not this list.

generate_assembly

Generate a harness assembly from a plan by selecting which nodes and bundles to include. Returns the created harness ID. The assembly appears in Splice as an editable harness linked to the project.

list_harnesses

List all legacy harnesses owned by the authenticated user. These are standalone harnesses not associated with a project.

create_harness

Create a new legacy harness. Provide the full WorkingHarness JSON with BOM and connection data. Read the harness_schema resource first. Returns the harness with harness_id and revision_id set.

get_harness

Load a legacy harness with its full BOM (hydrated parts) and connection data. Use this to inspect or modify an existing harness.

save_harness

Save (overwrite) a legacy harness. The harness_data must include harness_id and revision_id from the loaded harness. Use get_harness first to load current state, modify it, then save.

get_harness_summary

Get a structured summary of a legacy harness: connectors, wires, cables, connections, and validation warnings. More concise than get_harness.

is_bridge_connected

Check which browser tabs are connected via the WebSocket bridge. Returns connected namespaces — project:<uuid> for plans, harness:<uuid> for assemblies. Use the namespace value with execute_command/get_live_state to target a specific tab.

execute_command

Execute a single command through the live WebSocket bridge. Works for both plan mode (project:* namespace) and assembly/harness mode (harness:* namespace). PREFER execute_commands (plural) for batching — much faster. Canvas updates immediately, action added to undo history.

execute_commands

PREFERRED over execute_command. Execute multiple commands in a single call — much faster than calling execute_command repeatedly. All commands run atomically and undo as one action. Works for both plan (project:*) and assembly (harness:*) namespaces.

undo

Undo the last command in the Splice frontend.

redo

Redo the last undone command in the Splice frontend.

get_live_state

Get or set live frontend state. Reflects all unsaved changes, including for assemblies (harness:* namespace). Use setComponentState to update the Component Creator form fields.

search_connectors

Search the Splice connector parts database. Only use this when the user asks you to find a part in the database, or when you need a sourcePartId for linking. For most cases, prefer creating BOM entries directly with the MPN/manufacturer you already know (from datasheets, user input, or web research)

search_wires

Search the Splice wire parts database. Only use when the user asks to find a wire in the database. For most cases, create wire BOM entries directly with gauge/color you already know. Supports "22 awg red", "18 awg black white stripe".

search_cables

Search the Splice cable parts database. Only use when the user asks to find a cable in the database. For most cases, create cable BOM entries directly. Supports "4 core shielded 20 awg", "belden 2 conductor".

get_part

Get full details for a specific part by ID, including its specification (pin count, gauge, etc.).

create_component

Create a component in the Splice parts database with full specs, images, and pin labels. Use lookup_part first to get image/datasheet URLs. Categories: "connector" (default), "circuit_breaker", "fuse", "relay", "contactor", "switch", "push_button", "motor", "pcb", "power_supply", "battery", "diode",

get_category_templates

Get default properties, specs, and SVG templates for all component categories (fuse, relay, circuit breaker, etc.). Use this to discover what category-specific fields are available when creating components.

lookup_part

Look up a real-world part on DigiKey by MPN. Returns image URL, datasheet URL, specs, and parameters. Use this to enrich components before creating them with create_component.

create_cable

Create a custom multi-conductor cable in the parts database. Use when a cable is not found via search — e.g. from a datasheet. Returns a part ID for BOM entries.

get_plan

Get PlanData for a project. WARNING: Can be very large for complex plans. PREFER get_plan_summary to understand plan state. Use node_ids/link_ids to fetch specific elements instead of the full plan.

save_plan

Save (overwrite) the PlanData JSON for a project. The plan_data must be a complete, valid PlanData object. Read the plan_schema resource first to understand the structure. Use get_plan to fetch the current state before modifying.

get_plan_summary

PREFERRED way to read plan state. Returns components (with positions, pins, connection status, MPN), bundles, conductors, branch points, unconnected pins, and warnings. Much smaller than get_plan — use this first, only fetch full plan if you need raw data for specific elements.

validate_plan

Validate a project's plan for structural issues: orphan nodes, dangling conductors, missing parts, invalid references, mating compatibility, terminal point wiring, and shape/category consistency. Returns structured findings — each with a machine code, severity, involved node/conductor/link/mate IDs,

list_projects

List all projects owned by the authenticated user.

create_project

Create a new Splice project. Returns the project ID and details.

get_project

Get a project with its plan and assembly list.

describe_command
// known CVEs in dependencies1 critical11 high6 medium13 low

Disclosed vulnerabilities in this server's declared npm dependencies (via OSV). Whether each is reachable depends on the installed versions.

criticalvitest@3.2.4GHSA-5xrq-8626-4rwp

When Vitest UI server is listening, arbitrary file can be read and executed

highaxios@1.13.6GHSA-35jp-ww65-95wh

axios Vulnerable to Full Man-in-the-Middle via Prototype Pollution Gadget in `config.proxy`

highaxios@1.13.6GHSA-3g43-6gmg-66jw

axios Vulnerable to Credential Theft and Response Hijacking via Prototype Pollution Gadget in Config Merge

highaxios@1.13.6GHSA-6chq-wfr3-2hj9

Axios: Header Injection via Prototype Pollution

highaxios@1.13.6GHSA-777c-7fjr-54vf

Allocation of Resources Without Limits or Throttling in Axios

Depend on this server? Get alerted when its CVEs change.Watch this server free →
// environment variables
To run this server yourself, you supply these values. They go in your own MCP client configuration and stay on your machine. The secret label means the value is sensitive, not that the server mishandles it.
🔐 secretSPLICE_API_KEYclaude mcp add splice-cad -e SPLICE_API_URL=https://splice-cad.com -e =your-key -- npx @splice-cad/mcp
configSPLICE_API_URLclaude mcp add splice-cad -e =https://splice-cad.com -e SPLICE_API_KEY=your-key -- npx @splice-cad/mcp
configSPLICE_BRIDGE_PORTNo WebSocket bridge port (default: 9876)
🔐 secretSPLICE_BRIDGE_SECRETNo Shared secret for WS auth (auto-generated)
// quality suggestions

Tool annotations

No tools have read-only/destructive annotations

Add readOnlyHint or destructiveHint annotations to every tool so hosts can warn users before invoking.

All four hints declared on every tool

28/28 tools missing one or more hints — generate_assembly (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); list_harnesses (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); create_harness (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +25 more. OpenAI's directory rejects tools where any of the four hints are missing or non-boolean.

For every tool, set all four hints (readOnlyHint, destructiveHint, idempotentHint, openWorldHint) to explicit true/false values that match the handler’s actual behaviour.

Tool test coverage

Only 2/28 tools referenced in tests (7%)

Write tests that reference each tool by name so every tool has at least one test.

No arbitrary install scripts

Has postinstall/preinstall script — runs arbitrary code on npm install

Remove postinstall/preinstall hooks unless they’re essential.

Production dependencies are patched

0 critical, 11 high severity in production deps — axios@1.13.6 (high), axios@1.13.6 (high)

Run npm audit fix, or upgrade the affected packages to a non-vulnerable version.

Dev dependencies

1 critical/high in dev-only deps (does not ship to users)

Upgrade dev dependencies when convenient.

Claim the listing to review these findings one by one and send us a correction where you disagree, straight to the team. Claiming also means we tell you when the grade moves, and reach you first if we find anything urgent.

// full audit trail
The findings above are the summary. The full trail, every check we ran, each deduction, the network hosts observed and the dependency advisories, goes to verified publishers, along with an alert whenever a new one lands. Verified publishers can also review each finding and dispute it in one click. Publisher corrections have sharpened several of our checks this month, because the maintainer knows the codebase better than any scanner.
// improvement guidance — verified publishers only
We have 6 concrete improvements we can share with the publisher of this MCP. Each comes with specific guidance to raise the trust score.
// embed badge in your README
[![M8ven Verified](https://m8ven.ai/badge/mcp/splice-cad/splice-cad-mcp?variant=verified)](https://m8ven.ai/mcp/splice-cad/splice-cad-mcp)
Shows verification status without the grade. Want the grade badge instead? Remove ?variant=verified from the URL.
commit: c54d729c479c68b048d636f82a2063eb6c46049d
code hash: 5c18b2ab49aa6c942761e1417e5e4196dc9f2ae0d5e4460abd825eca2d4f7e4d
view raw JSON →
Check MCPs from inside your assistant
Tool Check · MCP

Vetting this one by hand? Tool Check is an MCP that scores other MCPs. Add it once and ask Claude, ChatGPT, or any MCP client to grade a server, surface CVEs, check the publisher, and suggest safer alternatives — before you install.

https://m8ven.ai/api/mcp/tool-check
check_toolsearch_toolscompare_toolsrecommend_alternativescheck_publisherreport_concern
How to add it →Free · no account needed · works in any MCP client