Blender integration through the Model Context Protocol
Nothing to run from here
FreeCAD is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
93/100
trust score
9k
downloads a day
local
runs on your machine
102k
downloads in 30d
What it does
Control FreeCAD from MCP clients: create and edit models, run Python and FEM analyses.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user neka-nat-freecad-mcp '--' uvx freecad-mcp
# 2 — ask your agent for something these tools do
# create_document, create_object, edit_object and 14 more
FreeCAD costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
NNAll 1 server
neka-nat1 server
1 category
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. This one runs on your machine: your client starts FreeCAD as a process under your own user, with your files and your network, so the tool surface below is what it can do to your computer rather than to a server somewhere else. Its scan result is on the Security tab — read the surface before you approve it.
Claude Codedeclared by this listing
This is a public server: you run it yourself and this marketplace is not in the path. You need uv (docs.astral.sh/uv): uvx comes with it. Claude Code registers it in one command; --scope user makes it available in every project. The '--' is in quotes so that PowerShell passes it on.
claude mcp add --scope user neka-nat-freecad-mcp '--' uvx freecad-mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
Free on mcprush, and it runs from its publisher’s own package: this marketplace is not in the path, so there is no key of ours to hold and no card to add.
What it writes
One config entry your client uses to start the process locally. A local server runs with your file system and your network, which is why it is priced without metering.
What you approve
17 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
Read from its source code. A server that builds its tool list when it starts can list more tools than this.
Create a new document in FreeCAD.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| name | string | yes | The name of the document to create. |
Create a new object in FreeCAD.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| doc_name | string | yes | The name of the document to create the object in. |
| obj_type | string | yes | The type of the object to create (e.g. 'Part::Box', 'Part::Cylinder', 'Part::Cut', 'PartDesign::Body', etc.). |
| obj_name | string | yes | The name of the object to create. |
| analysis_name | string | no | — |
| obj_properties | object | no | The properties of the object to create. |
| include_screenshot | boolean | no | Whether to return a screenshot of the model (default True). Set to False to save tokens when visual feedback is not needed, e.g. for intermediate steps in a longer sequence of changes. |
| view_name | no | The view orientation of the returned screenshot (default "Isometric"). Pick the view that best shows the change being made. |
Edit an object in FreeCAD.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| doc_name | string | yes | The name of the document to edit the object in. |
| obj_name | string | yes | The name of the object to edit. |
| obj_properties | object | yes | The properties of the object to edit. |
| include_screenshot | boolean | no | Whether to return a screenshot of the model (default True). Set to False to save tokens when visual feedback is not needed, e.g. for intermediate steps in a longer sequence of changes. |
| view_name | no | The view orientation of the returned screenshot (default "Isometric"). Pick the view that best shows the change being made. |
Delete an object in FreeCAD.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| doc_name | string | yes | The name of the document to delete the object from. |
| obj_name | string | yes | The name of the object to delete. |
| include_screenshot | boolean | no | Whether to return a screenshot of the model (default True). Set to False to save tokens when visual feedback is not needed, e.g. for intermediate steps in a longer sequence of changes. |
| view_name | no | The view orientation of the returned screenshot (default "Isometric"). Pick the view that best shows the change being made. |
Execute Python code in FreeCAD without waiting for completion.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| code | string | yes | Background-safe Python code to execute. Use commit(fn) for all document and view writes. |
Run a FreeCAD Python script in a separate headless freecadcmd process.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| code | string | yes | Complete Python script for freecadcmd. |
| timeout | number | no | Positive finite seconds to wait before killing the process (default 600). Partial output is preserved on timeout. |
Report the state of background jobs started by execute_code_async.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| job_id | string | no | The id returned by execute_code_async. Empty lists all running jobs and up to 20 recently completed jobs. |
Execute arbitrary Python code in FreeCAD.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| code | string | yes | The Python code to execute. |
| include_screenshot | boolean | no | Whether to return a screenshot of the model (default True). Set to False to save tokens when the code does not change the model's appearance, e.g. analytical or computational scripts whose result is p |
| view_name | no | The view orientation of the returned screenshot (default "Isometric"). Pick the view that best shows the change being made. | |
| timeout | number | no | Positive finite seconds for each of the queue and GUI execution budgets, overriding the 90 s default for this call (capped at 1800). Raise it for slow work that must run on the GUI thread, such as imp |
Get a screenshot of the active view.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| view_name | yes | The name of the view to get the screenshot of. | |
| width | integer | no | The width of the screenshot in pixels. If not specified, uses the viewport width. |
| height | integer | no | The height of the screenshot in pixels. If not specified, uses the viewport height. |
| focus_object | string | no | The name of the object to focus on. If not specified, fits all objects in the view. |
Insert a part from the parts library addon.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| relative_path | string | yes | The relative path of the part to insert. |
| include_screenshot | boolean | no | Whether to return a screenshot of the model (default True). Set to False to save tokens when visual feedback is not needed, e.g. for intermediate steps in a longer sequence of changes. |
| view_name | no | The view orientation of the returned screenshot (default "Isometric"). Pick the view that best shows the change being made. |
Get all objects in a document.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| doc_name | string | yes | The name of the document to get the objects from. |
| include_screenshot | boolean | no | Whether to return a screenshot of the document (default True). Set to False to save tokens when only the object data is needed. |
| view_name | no | The view orientation of the returned screenshot (default "Isometric"). |
Get an object from a document.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| doc_name | string | yes | The name of the document to get the object from. |
| obj_name | string | yes | The name of the object to get. |
| include_screenshot | boolean | no | Whether to return a screenshot of the document (default True). Set to False to save tokens when only the object data is needed. |
| view_name | no | The view orientation of the returned screenshot (default "Isometric"). |
Get the list of parts in the parts library addon.
Takes no parameters.
Close and re-open a document to pick up external file changes.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| doc_name | string | yes | The name of the open document to reload. Must match the name shown by `list_documents`. |
Get the list of open documents in FreeCAD.
Takes no parameters.
Get RPC and FreeCAD GUI-dispatch health.
Takes no parameters.
Run the CalculiX solver on an existing Fem::FemAnalysis container and return summary results.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| doc_name | string | yes | Name of the FreeCAD document. |
| analysis_name | string | yes | Name of the Fem::AnalysisPython object. |
| timeout | integer | no | Seconds to wait for the solver (default 600). |
| include_screenshot | boolean | no | Whether to return a screenshot of the model (default True). Set to False to save tokens when only the numeric results are needed. |
| view_name | no | The view orientation of the returned screenshot (default "Isometric"). |
Free
$0 forever
- Every tool, no call limit
- No card, and mcprush charges nothing for it
- Source published under MIT
- Runs on your machine — nothing of it reaches our gateway
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install FreeCAD or to call it, at any volume.
Call allowance · this installenforced at the gateway
Monthly allowance, in calls
—
—
Alert at 80% · then the tool returns a normal MCP error
Used this month: —
ATrust score 93 / 100
Release 0.1.31 · scanned 13 Nov 2026
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
Threat score100
Client score93
Findings3 threat · 10 capability
Capabilityhigh
Coveragesource
Verificationrepo
Surface digest259ae2c8bdabf1af58c718257b9cdf6798e7cfb0cd0194f04521598b75fcc0b7
Score vectorthreat 100 → client 93
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | high | capability blast radius (high) — client exposure if the model is manipulated | −6 |
| verification-discount | repo | publisher verification (public source) — no provenance, but the source is public and inspectable | −1 |
| coverage-honesty | source | inspection depth (source) — how much of the target the scan could see | −0 |
score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
Tool surfaceread
Implementation sourceread
Package metadataread
Live transportnot available
Tools were statically extracted from the published source (17 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>".
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. high is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| create_document | no tags | |
| create_object | no tags | |
| edit_object | no tags | |
| delete_object | no tags | |
| execute_code_async | untrusted-inputcode-exec | untrusted-input: keyword "fetch"; code-exec: keyword "execute code" in tool name |
| execute_code_headless | code-exec | code-exec: keyword "execute code" in tool name |
| get_async_status | no tags | |
| execute_code | code-exec | code-exec: keyword "execute code" in tool name |
| get_view | no tags | |
| insert_part_from_library | no tags | |
| get_objects | no tags | |
| get_object | no tags | |
| get_parts_list | no tags | |
| reload_document | no tags | |
| list_documents | no tags | |
| get_rpc_status | no tags | |
| run_fem_analysis | no tags |
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
flow-1
Untrusted input can drive an external action even though no sensitive source is exposed.
Supply chain and provenance
Integrityfirst-seen
Surface digest259ae2c8bdabf1af
Scanned2026-11-13
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
Always latest — the install command names no version, so it installs the newest release when it runs; the current release on file is 0.1.31. Pin a release below and the command asks for exactly that one.
0.1.31
undated
latestNo release note was published with this version.
—
no reviews yet
Who can review
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Sign in to write one
Any signed-in account that does not publish FreeCAD can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
No reviews yet
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.