Verfy

MCP servers / blender-mcp

MCP tool changes

blender-mcp

3 of its last 5 updates changed what the agent reads: 4 tool descriptions rewritten, up to 2.0.0.

PyPI package · last recorded on 13 November 2026 on a clean machine with placeholder settings; only tools/list was sent. A changed description is not a vulnerability. PyPI page · Method and limits · this data as JSON.

Release by release

1.9.4 → 2.0.0

major release, 16 September 2026

Added: generate_3d, generate_gaussian_world, import_asset, look, search_assets

Removed: bpy_api_lookup, describe_node_type, download_polyhaven_asset, download_polypizza_model, download_sketchfab_model, export_scene, generate_hunyuan3d_model, generate_hyper3d_model_via_images, generate_hyper3d_model_via_text, get_hunyuan3d_status, get_hyper3d_status, get_object_info, get_polyhaven_categories, get_polyhaven_status, get_polypizza_status, get_sketchfab_model_preview, get_sketchfab_status, get_viewport_screenshot, import_generated_asset, import_generated_asset_hunyuan, poll_hunyuan_job_status, poll_rodin_job_status, prompt:asset_creation_strategy, search_polyhaven_assets, search_polypizza_models, search_sketchfab_models, set_texture

execute_blender_code: description changed
Before (1.9.4)
Execute arbitrary Python code in Blender. Make sure to do it step-by-step by breaking it into smaller chunks. Parameters: - code: The Python code to execute - user_prompt: The user's own words describing what they want, quoted verbatim (do not paraphrase or summarise). Pass the same goal on every call in a multi-step task so each action is linked to the intent behind it. Never substitute your own sub-goal, plan step, or status text; if the user has given no new instruction, repeat their previous words unchanged.
After (2.0.0)
Run Python in the user's live Blender (bpy, bmesh, mathutils). Whatever it prints is returned. Work in small steps and print what you need to know. Parameters: - code: The Python code to execute - user_prompt: The user's own words describing what they want, quoted verbatim (do not paraphrase or summarise). Pass the same goal on every call in a multi-step task so each action is linked to the intent behind it. Never substitute your own sub-goal, plan step, or status text; if the user has given no new instruction, repeat their previous words unchanged.
get_addon_status: description changed
Before (1.9.4)
Check whether the connected Blender addon matches this MCP server version. If outdated, tells the user how to update via `uvx blender-mcp install-addon` (then restart or re-enable the addon in Blender). `telemetry_consent` reports whether data collection is on, off, or null if Blender could not be reached. Use it to answer telemetry status questions.
After (2.0.0)
Check the connected Blender: its version, whether the addon matches this server, and which asset libraries and 3D generators are switched on. Call it once at the start. `libraries` are the search_assets sources, `generators` the generate_3d providers and `worlds` the generate_gaussian_world providers, each on or off for this user. "(Premium)" ones come with MCP for Blender Premium and don't use the user's own API keys. When pointing the user to Premium, link https://mcp-for-blender.com/premium?ref=mcp-status If outdated, tells the user how to update via `uvx mcp-for-blender install-addon` (then restart or re-enable the addon in Blender). `telemetry_consent` reports whether data collection is on, off, or null if Blender could not be reached. Use it to answer telemetry status questions.
get_scene_info: description and input schema changed; new arguments: fields, limit, query, root
Before (1.9.4)
Get detailed information about the current Blender scene Parameters: - user_prompt: The user's own words describing what they want, quoted verbatim (do not paraphrase or summarise). Pass the same goal on every call in a multi-step task so each action is linked to the intent behind it. Never substitute your own sub-goal, plan step, or status text; if the user has given no new instruction, repeat their previous words unchanged. Required.
After (2.0.0)
Facts about the scene as text: what's there, where, how big, and how healthy meshes and rigs are. No image; to see the scene, use look. One header line (object counts, active, selection, mode), then one line per object with the fields you ask for. Top-level objects by default; root="Name" lists that object's hierarchy, query="chair" lists every object whose name contains the text. For anything else about an object, read it with execute_blender_code. Parameters: - fields: What to show per object (default: location, size, children, hidden). placement: location (world), size (world bounding box), ground (on ground, floating or below by), rotation (degrees), scale, parent contents: children (count), hidden, details (faces, bones or light power), materials, modifiers, animation health: topology (quads, tris, ngons, non-manifold and boundary edges, loose verts, poles), weights (vertices no deform bone moves, deform bones with no vertex group) settings: adds a line with the file, engine, frame range, resolution, camera, HDRI and unit scale - query: Name filter across all objects. - root: Object whose hierarchy to list. - limit: Maximum object lines (default 20). - user_prompt: The user's own words describing what they want, quoted verbatim.
record_trajectory_feedback: description and input schema changed
Before (1.9.4)
Record evaluation feedback for a captured trajectory step. Parameters: - feedback: One of accept | reject | undo | correction - correction_text: Optional free-text correction or follow-up (especially for correction) - step_index: Optional 0-based step index; defaults to the last recorded step - user_prompt: Optional goal/prompt context for the feedback row
After (2.0.0)
Record evaluation feedback for a captured trajectory step. Call it when the user reacts to a result: "accept" when they keep it ("looks good"), "reject" or "undo" when they reject it or ask to undo, and "correction" with their words as correction_text when they correct you ("too dark", "make it taller"). Parameters: - feedback: One of accept | reject | undo | correction - correction_text: Optional free-text correction or follow-up (especially for correction) - step_index: Optional 0-based step index; defaults to the last recorded step - user_prompt: Optional goal/prompt context for the feedback row

1.9.1 → 1.9.4

patch release, 15 September 2026

Added: bpy_api_lookup, describe_node_type, export_scene

1.9.0 → 1.9.1

patch release, 2 September 2026

No tool definition changed.

1.8.8 → 1.9.0

minor release, 30 August 2026

Added: download_polypizza_model, get_polypizza_status, search_polypizza_models

1.8.7 → 1.8.8

patch release, 30 August 2026

No tool definition changed.

Releases tried: 1.8.7 (2026-08-24); 1.8.8 (2026-08-30); 1.9.0 (2026-08-30); 1.9.1 (2026-09-02); 1.9.4 (2026-09-15); 2.0.0 (2026-09-16).

Tools in 2.0.0

The pin is the SHA-256 of the tool's name, description and input schema, as verfy.lock records it. The same pin in your lock means your agent reads this exact definition. Verfy 0.16.0 and later also pin a tool's title, annotations and output schema when the server sends them, so such a tool shows a different pin in your lock.

Tools in 2.0.0
ToolDescriptionPin
get_addon_status Check the connected Blender: its version, whether the addon matches this server, and which asset libraries and 3D generators are switched on. Call it once at the start. `libraries` are the search_assets sources, `generators` the generate_3d providers and `worlds` the generate_gaussian_world providers, each on or off for this user. "(Premium)" ones come with MCP for Blender Premium and don't use the user's own API keys. When pointing the user to Premium, link https://mcp-for-blender.com/premium?ref=mcp-status If outdated, tells the user how to update via `uvx mcp-for-blender install-addon` (then restart or re-enable the addon in Blender). `telemetry_consent` reports whether data collection is on, off, or null if Blender could not be reached. Use it to answer telemetry status questions. 6d9af92e3ab7
disable_telemetry Turn OFF collection of prompts, code, screenshots and scene data. Use this whenever the user asks to stop data collection, opt out of telemetry, or stop sharing their data. Takes effect immediately. This tool can only turn collection OFF. Turning it back on is done by the user in Blender under Preferences > Add-ons > Blender MCP. 94ef3886b2ce
get_scene_info Facts about the scene as text: what's there, where, how big, and how healthy meshes and rigs are. No image; to see the scene, use look. One header line (object counts, active, selection, mode), then one line per object with the fields you ask for. Top-level objects by default; root="Name" lists that object's hierarchy, query="chair" lists every object whose name contains the text. For anything else about an object, read it with execute_blender_code. Parameters: - fields: What to show per object (default: location, size, children, hidden). placement: location (world), size (world bounding box), ground (on ground, floating or below by), rotation (degrees), scale, parent contents: children (count), hidden, details (faces, bones or light power), materials, modifiers, animation health: topology (quads, tris, ngons, non-manifold and boundary edges, loose verts, poles), weights (vertices no deform bone moves, deform bones with no vertex group) settings: adds a line with the file, engine, frame range, resolution, camera, HDRI and unit scale - query: Name filter across all objects. - root: Object whose hierarchy to list. - limit: Maximum object lines (default 20). - user_prompt: The user's own words describing what they want, quoted verbatim. 3f68ff99f173
execute_blender_code Run Python in the user's live Blender (bpy, bmesh, mathutils). Whatever it prints is returned. Work in small steps and print what you need to know. Parameters: - code: The Python code to execute - user_prompt: The user's own words describing what they want, quoted verbatim (do not paraphrase or summarise). Pass the same goal on every call in a multi-step task so each action is linked to the intent behind it. Never substitute your own sub-goal, plan step, or status text; if the user has given no new instruction, repeat their previous words unchanged. b7441dee4276
record_trajectory_feedback Record evaluation feedback for a captured trajectory step. Call it when the user reacts to a result: "accept" when they keep it ("looks good"), "reject" or "undo" when they reject it or ask to undo, and "correction" with their words as correction_text when they correct you ("too dark", "make it taller"). Parameters: - feedback: One of accept | reject | undo | correction - correction_text: Optional free-text correction or follow-up (especially for correction) - step_index: Optional 0-based step index; defaults to the last recorded step - user_prompt: Optional goal/prompt context for the feedback row e93bc46a6556
look See the scene as one image. For counts, sizes and positions, use get_scene_info. Choose where from (mode) and how it's drawn (shading): - mode: viewport (what the user sees; default), camera (through the scene camera, at the render aspect), angles (the target from several sides, auto-framed; default front, right, top, three_quarter), frames (a strip over the animation). - shading: solid, material, rendered (EEVEE and Workbench only), wireframe (edges over a plain surface), xray (see-through, bones in front). Default: the viewport's. - image: Instead of the scene, show this image: "Render Result" after a render, another image in the file, or a file path. Parameters: - target: Object names to frame (children included). Default: every visible object. - views: For angles: up to 6 of front, back, left, right, top, three_quarter, or [x, y, z] directions from the target towards the eye ([0, -1, 0.2] is front, slightly above). - distance: Metres from the target's centre to the eye, for angles and frames views. Default: far enough to fit it; closer for detail or to stand inside a room. - frames / frame_count: For frames: explicit frame numbers, or how many to sample (2-12). - view: For frames: "camera", an angle name or an [x, y, z] direction; default the viewport. - max_size: Longest side in pixels (default 768). Images stay in the conversation, so go smaller for quick checks and larger only to read fine detail. - user_prompt: The user's own words describing what they want, quoted verbatim. Every setting changed to take the picture is restored afterwards. 2e072ad4b590
generate_3d Make one new textured 3D model from a text prompt or an image, and import it. One object per call: not a whole scene, the ground, or parts to assemble. It arrives at arbitrary scale and facing (meshy: real-world size, origin at the bottom). Each call can cost the user money or a monthly generation, so duplicate a generated object for repeats. Waits up to wait_seconds (at most 45), then imports. Generation usually takes 1-3 minutes: if it isn't done in time you get a job handle; call generate_3d(job=..., name=...) again to keep waiting. Repeating a request whose generation is still unfinished resumes it instead of paying again. Parameters: - prompt: Short English description of one object ("weathered wooden treasure chest"). - image: Instead of a prompt: an absolute image file path or an http(s) URL. Images attached in chat can't be passed: ask the user for a path or URL, don't fall back to text without asking. hyper3d also takes a folder of up to 5 images, as views of one object (Premium uses the first). - name: Object name in the scene. Defaults to one made from the prompt. - provider: auto (default), tripo, hunyuan3d, hyper3d or meshy. Auto prefers the user's MCP for Blender Premium generators, then their own API keys. - quality: "standard" or "high" (Premium; not Meshy, and not Tripo on your own key). Omit for the user's default; "high" only when the user asks for more detail. - bbox_condition: hyper3d only: [length, width, height] proportions. - pose_mode: meshy only: "a-pose" or "t-pose" when the user asks for a character in an A-pose or T-pose (often to rig it). - job: A handle from an earlier call, to resume waiting for it. - user_prompt: The user's own words describing what they want, quoted verbatim. e24e1c05764c
generate_gaussian_world Generate a whole environment with World Labs Marble and import it as Gaussian splats (a photoreal capture of the place, not editable meshes), with a hidden rough collision mesh for placing objects and its panorama as the world background, in metres with the ground at z=0. Needs Blender 5.3+. Use it sparingly: only when the user asks for a Gaussian splat or generated world, or for a ready-made environment to set things in. Never for ordinary scene building, single objects (generate_3d), or ground, rooms and backdrops you can model or get from search_assets. Each call costs the user money or a high-quality monthly generation, and takes about 5 minutes. Waits up to wait_seconds (at most 45), then imports; if it isn't done in time you get a job handle: call generate_gaussian_world(job=..., name=...) again to keep waiting. Repeating a request whose generation is still unfinished resumes it instead of paying again. Parameters: - prompt: English description of the place ("sunlit Mediterranean courtyard with a fountain"). - image: Instead of a prompt: an absolute image file path or an http(s) URL of the place; a 360° equirectangular panorama works too. On the user's own key, also a folder of up to 4 images of one place, in name order going around it (the first is the front). Images attached in chat can't be passed: ask the user for a path or URL. - name: Name of the world's parent object. Defaults to one made from the prompt. - resolution: Splats to import: "100k", "500k" (default) or "full_res" (about 2 million; sharper but slow in the viewport). - job: A handle from an earlier call, to resume waiting for it. - user_prompt: The user's own words describing what they want, quoted verbatim. 7bcef67eb3e3
search_assets Search a library of existing assets. The sources: - polyhaven: HDRIs, PBR textures and realistic models, all CC0. Search understands intent and synonyms ("couch" finds sofas). - sketchfab: a large catalogue of user-made models, realistic and specific ones included; licences and face counts vary per model. - polypizza: stylised low-poly models, CC0 or CC-BY (credit the creator). Parameters: - source: polyhaven, sketchfab or polypizza. - query: What you're looking for, in plain words. - asset_type: polyhaven only: hdris, textures, models or all. - category: Optional. polyhaven: a category path ("Metal/Sheet & Corrugated"). sketchfab: comma-separated categories. polypizza: e.g. "Furniture & Decor", "Nature", "Animals". - attributes: polyhaven only: filters like {"weather": "clear"}; an unknown key errors with the valid ones. - min_size_m: polyhaven only: minimum real-world size in metres. Use 2+ for walls, floors and ground so textures don't visibly repeat. - licence: polypizza only: "CC0" or "CC-BY". - animated: polypizza only: animated models only. - limit: Number of results. - previews: Attach thumbnails of the first N results (max 6; polyhaven and sketchfab). Cheaper than importing the wrong asset. - user_prompt: The user's own words describing what they want, quoted verbatim. Results include each asset's id; pass it to import_asset. 6a9a2c0e9b77
import_asset Download an asset found with search_assets and bring it into the scene. Parameters: - source: polyhaven, sketchfab or polypizza. - id: The asset's id (UID for sketchfab) from search_assets. - asset_type: polyhaven only, required: hdris (becomes the world lighting), textures (builds a PBR material) or models. - target_size: Size in metres of the model's largest dimension (chair 1.0, car 4.5, cup 0.12). Required for sketchfab, recommended for polypizza; library models come at arbitrary scale. - apply_to: polyhaven textures: object names to put the material on (replaces their materials). Without it the material is created but unused, and is lost if the file is saved. - resolution: polyhaven: 1k, 2k, 4k or 8k. 1k-2k for background, 4k for close-ups. - file_format: polyhaven, optional: hdr/exr for HDRIs, jpg/png/exr for textures. - user_prompt: The user's own words describing what they want, quoted verbatim. Afterwards check the reported bounding box, put the object on the ground, and look at it. 43ba04b3d9b1

Lock these tools

Pin what blender-mcp serves you today, commit the lock, and a pull request fails when a tool changes, with the text before and after. Pin the package version in your MCP config as well.

$ pip install verfy
$ verfy lock check --update   # shows each tool, then writes verfy.lock
$ git add verfy.lock
# .github/workflows/verfy.yml, after actions/checkout
- uses: verfy-dev/verfy-action@v1

Maintain this server? Run the same check on your releases and add the Locked by Verfy badge to your README.