Navisworks vs Revit MCP
A side-by-side look at the Navisworks and Revit MCP MCP servers: transport, auth, tools, quality signals, and the config to install either one in Claude, Cursor, Windsurf or VS Code.
Verdict: choose Navisworks for architecture & design work over a hosted endpoint; choose Revit MCP for architecture & design as a local process. You can also run both side by side in one mcpServers block.
Which MCP server should you choose?
Choose Navisworks when
- You need dedicated capabilities in the Architecture & Design domain.
- You prefer a remote HTTP/SSE transport.
- You want tools like
nwd_upload, nwd_get_clashes, nwd_export_report.
Choose Revit MCP when
- You need dedicated capabilities in the Architecture & Design domain.
- You prefer a local stdio subprocess transport.
- Its auth model fits you: No auth required.
- You want tools like
add_pipe_cap, adjust_section_datums, align_titleblocks_on_sheets.
Feature & specification comparison
Rows where the two servers differ are marked.
| Spec | ||
|---|---|---|
| Category | Architecture & Design | Architecture & Design |
| Quality signal | 51/100 · Good | 68/100 · Great |
| Install command | Confirmed | Confirmed |
| Transport | Remote HTTP/SSE | Local subprocess (stdio) |
| Auth | Not declared | No auth required |
| Pricing | Not declared | Free |
| Required env vars | None listed | None listed |
| Verified owner | Community listing | Community listing |
| GitHub stars | 0 | 106 |
| Directory activity | 0 views 0 installs 0 upvotes | 7 views 0 installs 0 upvotes |
| Tools | 5 | 167 |
| Full listing | View Navisworks | View Revit MCP |
Tools & capabilities
Navisworks tools 5
nwd_uploadUpload a Navisworks file (.nwd/.nwf/.nwc) to Autodesk Platform Services (APS) Object Storage and start an SVF2 translation job so the model becomes queryable by the other nwd_* tools. When to use: at the start of a coordination workflow — e.g. the GC hands off a federated NWD combining MEP + structural + architectural models and the agent needs to stage it for clash review before issuing an RFI, or when a subcontractor publishes a new NWC model revision that must be ingested for weekly BIM coordination. Always the first call in a session for any new model. When NOT to use: do not call for already-translated models (re-use the returned model_id/URN); do not use for raw Revit .rvt, IFC, or DWG — those go through a different MCP. APS scopes required: data:read data:write data:create bucket:read bucket:create viewables:read. The worker acquires a 2-legged client-credentials token; the caller does not supply one. Rate limits: APS default ~50 req/min per app per endpoint; Model Derivative translation job submission ~60 req/min. NWD bundles can be large (hundreds of MB); the upload PUT and translation can take minutes — translation is asynchronous, poll via nwd_export_report (manifest) with exponential backoff (e.g. 5s, 10s, 30s, 60s) before calling clash/properties tools. Errors the agent should handle: 401 invalid/expired APS token (surface as auth failure — do not retry with same creds); 403 missing scope (report scope gap, do not retry); 404 source file_url unreachable (ask user for a fresh public URL); 409 bucket already exists (handled internally, safe to ignore); 413/422 unsupported Navisworks version — APS Model Derivative supports NWD/NWC from Navisworks 2015 and later (state the unsupported version to the user); 429 rate limited (exponential backoff, retry); 5xx APS upstream (retry once, then surface). Side effects: creates a fresh transient OSS bucket (scanbim-nwd-<timestamp>, 24h TTL) and uploads the file as an object, then POSTs a Model Derivative translation job. NOT idempotent — each call creates a new bucket/URN even for the same file_url. Logs usage to the D1 usage_log table.nwd_get_clashesDetect geometric/logical clashes between two element sets in an already-translated Navisworks model. Uses APS Model Derivative property extraction + same-level proximity heuristics, optionally augmented by VDC rules stored in D1 (table vdc_rules). When to use: when coordinating federated MEP + structural + architectural models for clash review before issuing an RFI; e.g. "find duct vs. beam clashes on Level 3 before the Wed coordination meeting" or "sanity-check the latest MEP revision against structure before releasing for fabrication." Pair with nwd_export_report to produce a deliverable. When NOT to use: do not call on a model whose translation is still "inprogress" — call nwd_export_report first and confirm translation_status == "success"; not a substitute for Navisworks Manage Clash Detective for final sign-off (this is a coordination-stage screen, not a regulatory clash report). APS scopes required: viewables:read data:read (read-only — does not create anything in APS). Rate limits: APS default ~50 req/min per endpoint; Model Derivative metadata/properties endpoints are the bottleneck. Properties response may return 202 "isProcessing" on first call — the worker retries once after 3s. For very large models (>50k elements) the worker caps analysis at 50x50 element cross-compare and 100 reported clashes; re-run with tighter category_a/category_b filters for exhaustive coverage. Errors: 401 APS token expired (transient, retry); 403 missing viewables:read/data:read scope (report, do not retry); 404 URN not found or not translated (prompt user to re-run nwd_upload); 409 not applicable; 422 model translated but property index unavailable — typically means source NW version unsupported or translation partially failed (supported: Navisworks 2015+); 429 rate limit (backoff); 5xx APS upstream (retry once). If properties.data.collection is empty the tool returns clash_count: 0 with a note rather than erroring — the agent should treat that as "model not ready" and retry later. Side effects: none in APS. Reads vdc_rules from D1 when both categories are supplied. Logs usage to D1 usage_log. Idempotent — same inputs on a stable model yield the same clash list.nwd_export_reportBuild a coordination report for a translated Navisworks model: translation status/progress, derivative outputs, available views (2D sheets / 3D viewables), total element count, and a per-category element breakdown. Doubles as the canonical way to poll translation status after nwd_upload. When to use: after nwd_upload to check whether translation has completed before calling clash/object tools; at the end of a coordination session to generate a status snapshot for the weekly BIM report; when auditing a model revision to confirm expected element counts per discipline. When NOT to use: do not use for a per-element property dump — use nwd_list_objects; do not use for clash results — use nwd_get_clashes. APS scopes required: viewables:read data:read bucket:read (read-only). Rate limits: APS default ~50 req/min per endpoint; this tool issues up to 4 sequential APS calls (manifest, metadata, properties — two with retry). When polling for translation completion, backoff: 5s, 10s, 30s, 60s, 120s — Model Derivative NWD translation typically completes in 1-10 min but large federated models can take 20+ min. Errors: 401 APS token expired (retry); 403 missing scope (report); 404 URN not found (model was never uploaded or bucket TTL expired); 409 N/A; 422 translation failed permanently — inspect report.translation_status == "failed" and report.derivatives[].status; 429 rate limit (backoff); 5xx APS upstream (retry once). Property extraction may legitimately 202 "isProcessing" — the tool handles retry and then silently swallows to still return manifest/metadata (element_count will be 0 until properties index is built). Side effects: none. Pure read. Idempotent — report reflects current APS state. Logs usage to D1 usage_log.nwd_get_viewpointsList saved viewpoints / camera positions and top-level view containers for a translated Navisworks model. Pulls the metadata view list and enriches each 3D view with its first two levels of the object tree (viewpoint folders typically live there in NWD files). When to use: when preparing a coordination meeting and you need a quick index of every saved viewpoint (e.g. "Level 3 Mech Room", "Clash - duct vs beam gridline C-4") to drive screenshots or BCF-style issues; when an agent needs to deep-link a 2D sheet or 3D camera into the APS Viewer. When NOT to use: does not return camera matrices (position/target/up vectors) — APS Model Derivative does not expose those from the NWD viewpoint XML; for full camera data the source NWD must be opened in Navisworks Manage. APS scopes required: viewables:read data:read. Rate limits: APS default ~50 req/min; this tool fans out one object-tree call per 3D view (capped implicitly by metadata view count, usually <5). For federated models with many sheets this can approach the per-minute quota — cache the result. Errors: 401 token (retry); 403 scope (report); 404 URN not found / translation incomplete; 409 N/A; 422 model returned empty metadata (returns viewpoint_count:0 rather than throwing — agent should verify translation via nwd_export_report); 429 rate limit (backoff); 5xx APS upstream (retry once). Per-view object-tree failures are swallowed so the overall call still returns the metadata-level view list. Side effects: none. Pure read. Idempotent. Logs usage to D1 usage_log. Results are capped at 100 viewpoint entries.nwd_list_objectsList elements (objects) in the translated Navisworks model with their objectid, name, externalId, and full property bag, optionally filtered by a case-insensitive keyword matched against name and Category. When to use: when answering "how many VAV boxes are on Level 3?", "list every steel column with mark C-*", or any per-element question; when dumping a quick takeoff of a discipline before handing off to an estimator; when an agent needs externalIds to cross-reference with a Revit or ACC issue. When NOT to use: not for clash detection (use nwd_get_clashes); not for camera/viewpoint data (use nwd_get_viewpoints); not for full-model exports — results are capped at 100 objects per call, so use the filter argument to narrow. APS scopes required: viewables:read data:read. Rate limits: APS default ~50 req/min; two Model Derivative calls per invocation (metadata guid + properties). Properties endpoint may 202 "isProcessing" on first call after translation — the worker retries once after 3s. For very large models the properties payload can be tens of MB; expect higher latency. Errors: 401 token (retry); 403 scope (report); 404 URN not found; 409 N/A; 422 property index not yet built — returns object_count:0 (poll via nwd_export_report); 429 rate limit (backoff); 5xx APS upstream (retry once). If property collection is legitimately empty the tool returns success with object_count:0 and an empty objects array. Side effects: none. Pure read. Idempotent. Logs usage to D1 usage_log. Response includes a `note` field when the unfiltered collection exceeds the 100-object cap.
Revit MCP tools 167
add_pipe_cap在管件的未連線端安裝管帽或法蘭。自動尋找開放的接頭並連接。adjust_section_datums自動調整剖面視圖的網格線 (Grids) 與樓層線 (Levels) 2D 範圍與氣泡顯示。align_titleblocks_on_sheets批次將多個 sheet 上的 titleblock 移動到同一個 anchor 座標。可用『referenceSheetNumber』指定要拷貝某張 sheet 上 titleblock 的位置，或用『referencePositionMm』直接給絕對座標。anchor 決定要對齊 titleblock bbox 的哪個角（top-left / top-right / bottom-left / bottom-right / center）。建議先 dryRun=true 預覽 delta，確認後再實際執行。觸發條件：使用者提到 titleblock 對齊、圖框對齊、把所有 sheet 圖框對齊到 X、change_element_type 後圖框沒跟著移動、align titleblock、move titleblock to match。align_view_cropbox_to_element將指定視圖的 CropBox 對齊到目標元素（如 Detail Group 圖框）的 BoundingBox。保留原 Z 軸深度與 CropBox Transform。viewId 不指定時使用 active view。analyze_beam_penetration分析特定結構梁上的套管穿孔。回傳精確的幾何數據，如距離柱心長度、梁深度、開孔直徑等。analyze_corridor_width分析走廊寬度。使用 Revit 端的房間邊界線段找出平行牆對，回傳實測寬度、最小寬度與各區段檢討結果。analyze_floor_slopes分析樓板頂面排水坡度：以 Solid→PlanarFace 法向量與 Z 軸夾角計算每片朝上頂面的坡度百分比，回傳每片樓板的 Min/Max 坡度，並可回寫至指定參數（預設 Comments）。未指定 elementIds 時自動收集 Function=Exterior 的樓板。analyze_smoke_detectors偵煙探測器設置分析：掃描當前視圖的探測器、空調出風口（FCU/冷風機）、房間，回傳各探測器的距出風口距離、距牆/樑距離、距天花板距離，以及各房間的探測器數量與樑區格數。供 JS 端進行五項法規判定。analyze_tall_partition_roomsFind rooms on target levels that share or contain TYPE partition walls taller than a threshold. Uses room boundary segment ElementIds so shared room-to-room walls are assigned to both rooms, and can add upward ray evidence from room bottom to floor underside.apply_panel_pattern將面板排列模式套用到帷幕牆。需要類型映射表和排列矩陣。arrange_viewports_on_sheet依指定順序排列圖紙上的視埠（僅限 DraftingView）。支援水平或垂直排列，邊緣對齊（edge-to-edge）。第一個視埠的位置作為錨點。可用 viewNames（view 名稱陣列）或 viewportIds（視埠 ID 陣列）指定順序，二擇一。assign_existing_material將既有材質（透過名稱查找）套用到指定的 Type。不建立新材質。用於復原或批次指派既有材質（例如把 9 個柱子從 'White_MCP' 改回 '鋼 AISI 1015'）。- +155 more on the listing page
Ready-to-paste client configs
Paste either block (or both) into your client config, e.g. claude_desktop_config.json or ~/.cursor/mcp.json. We only show a config when the install command is confirmed.
Navisworks
{
"mcpServers": {
"navisworks": {
"url": "https://navisworks-mcp.itmartin24.workers.dev/mcp"
}
}
}
Revit MCP
{
"mcpServers": {
"revit-mcp": {
"command": "npx",
"args": [
"-y",
"@shuotao/revit-mcp-server"
]
}
}
}
Frequently asked questions
Navisworks is categorized under Architecture & Design and uses a remote HTTP/SSE transport. Revit MCP belongs to Architecture & Design and uses a local stdio subprocess. Pick Navisworks for architecture & design work and Revit MCP for architecture & design.
Copy the mcpServers block from the config section on this page into your client's config (for example claude_desktop_config.json or ~/.cursor/mcp.json), then fully restart the client.
Navisworks has no declared pricing — check the project's own site. Revit MCP is listed as free. Auth: no auth required. If a server needs environment variables such as API keys, define them under the env key in your client's MCP config.
Yes. MCP clients support multiple servers: add navisworks and revit-mcp as separate keys in the same mcpServers object, and your assistant will call tools from either one.
On AllMCPs, Navisworks has a quality signal of 51/100 (Good) with 0 views, 0 installs and 0 GitHub stars. Revit MCP has 68/100 (Great) with 7 views, 0 installs and 106 GitHub stars.