freecad-mcp

Provides a local MCP (Model Context Protocol) server integrated with FreeCAD, allowing an AI client (e.g., Claude Desktop) to create/edit/delete FreeCAD documents and objects, execute FreeCAD Python code, and retrieve views/objects/parts library information. Includes an installation method as a FreeCAD addon and a CLI command to run the MCP server.

Evaluated Mar 30, 2026 (22d ago)
Repo ↗ Ai Ml mcp freecad cad automation desktop-integration python claude-desktop
⚙ Agent Friendliness
50
/ 100
Can an agent use this?
🔒 Security
22
/ 100
Is it safe for agents?
⚡ Reliability
28
/ 100
Does it work consistently?

Score Breakdown

⚙ Agent Friendliness

MCP Quality
78
Documentation
70
Error Messages
0
Auth Simplicity
25
Rate Limits
0

🔒 Security

TLS Enforcement
10
Auth Strength
20
Scope Granularity
10
Dep. Hygiene
50
Secret Handling
30

Security model described relies on localhost by default and optional IP/CIDR allowlisting for remote access. No authentication/authorization mechanisms (e.g., tokens, user identity, scopes) are described. The presence of an `execute_code` tool materially increases risk if the server is exposed or misused. TLS is not mentioned; MCP connections are likely local but may be remote if configured. Dependency hygiene cannot be fully assessed from the provided content; dependencies include `mcp[cli]` and `validators` only per manifest.

⚡ Reliability

Uptime/SLA
0
Version Stability
45
Breaking Changes
30
Error Recovery
35
AF Security Reliability

Best When

You want a developer/desktop-local MCP integration to steer FreeCAD through a small set of tools, especially when you can keep the server bound to localhost or tightly restrict allowed IPs.

Avoid When

You need strong security isolation (e.g., multi-tenant access) or cannot mitigate the risks of remote connections and arbitrary code execution; also avoid when you cannot validate network exposure and operational safeguards.

Use Cases

  • Automating FreeCAD modeling workflows from an LLM (e.g., generate CAD from natural language prompts)
  • Programmatically generating or modifying FreeCAD documents and parts library content
  • Remote/hosted assistance where an operator wants an AI to iterate on CAD changes and provide screenshots
  • Building interactive CAD design agents for prototyping and ideation

Not For

  • Exposing FreeCAD control to the public internet without strong network controls
  • High-security environments without thorough review of tool coverage and the implications of 'execute_code'
  • Use cases that require robust audit trails, approval gates, or strict least-privilege beyond basic IP allowlisting

Interface

REST API
No
GraphQL
No
gRPC
No
MCP Server
Yes
SDK
No
Webhooks
No

Authentication

Methods: None described for MCP client auth; relies on network binding and IP allowlisting
OAuth: No Scopes: No

Documentation indicates remote connections are blocked by default (localhost only) and can be enabled with an IP/CIDR allowlist. No user-level authentication is described for the MCP server itself.

Pricing

Free tier: No
Requires CC: No

No pricing details present; appears to be a self-hosted open-source tool (MIT).

Agent Metadata

Pagination
none
Idempotent
False
Retry Guidance
Not documented

Known Gotchas

  • The tool includes `execute_code`, which can cause broad side effects; agents may need guardrails to avoid destructive operations.
  • Remote connections can be enabled and may bind to 0.0.0.0; ensure Allowed IPs are correctly set to avoid unintended exposure.
  • Auto-start persists via a local settings file; agents running on startup may start FreeCAD-side operations unexpectedly if misconfigured.
  • Network hostname/IP validation is mentioned, but security hinges on correct allowlist entries and restart behavior.

Alternatives

Full Evaluation Report

Comprehensive deep-dive: security analysis, reliability audit, agent experience review, cost modeling, competitive positioning, and improvement roadmap for freecad-mcp.

AI-powered analysis · PDF + markdown · Delivered within 30 minutes

$99

Package Brief

Quick verdict, integration guide, cost projections, gotchas with workarounds, and alternatives comparison.

Delivered within 10 minutes

$3

Score Monitoring

Get alerted when this package's AF, security, or reliability scores change significantly. Stay ahead of regressions.

Continuous monitoring

$3/mo

Scores are editorial opinions as of 2026-03-30.

8642
Packages Evaluated
17761
Need Evaluation
586
Need Re-evaluation
Community Powered