Enables interaction with Autodesk Civil 3D software, allowing AI to retrieve drawing data, query Civil 3D object types, manage selected objects, create COGO points, and generate line segments. Requires the Civil 3D MCP plugin to execute commands within the Civil 3D application.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Civil3D MCP Server create a new COGO point at coordinates X=1000, Y=2000, elevation=50"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
An MCP server that enables AI assistants to write and execute C# code directly inside Autodesk Civil 3D. Instead of fixed tools, the AI generates code that runs with full API access.
┌─────────────────┐ stdio ┌──────────────────┐ TCP/JSON-RPC ┌──────────────────┐
│ AI Assistant │ ◄────────────► │ MCP Server (TS) │ ◄──────────────────► │ Civil 3D Plugin │
│ (Claude, Cline) │ │ 3 meta-tools │ port 8080 │ Roslyn Engine │
└─────────────────┘ └──────────────────┘ └──────────────────┘
│ │
Skills Library C# Code Execution
(.skill.md files) (full Civil 3D API)Related MCP server: Civil 3D MCP Server
Tool | Purpose | Safety |
| Execute C# code with write access (transaction committed) | ⚠️ Modifies drawing |
| Execute C# code read-only (no commit) | ✅ No side effects |
| Browse/search/read code skill templates | ✅ Metadata only |
AI reads a skill → Gets a documented C# code template
AI adapts the code → Fills in parameters, combines patterns
AI sends code → Via civil3d_execute or civil3d_query
Roslyn compiles + runs → Inside Civil 3D with full API access
Results return as JSON → Back to the AI
User: "What surfaces are in my drawing?"
AI: Uses civil3d_query with:
var surfaces = new List<object>();
foreach (ObjectId id in CivilDoc.GetSurfaceIds()) {
var s = Transaction.GetObject(id, OpenMode.ForRead) as TinSurface;
surfaces.Add(new { s.Name, s.Layer });
}
return surfaces;
Result: [{ "Name": "EG", "Layer": "C-TOPO-EG" }, ...]Skills are documented C# code templates in skills/:
skills/
├── surfaces/ # Surface operations
├── alignments/ # Alignment + station/offset
├── points/ # COGO points
├── geometry/ # Lines, polylines, text
├── drawing/ # Drawing info
└── workflows/ # Complex multi-object operationsCode executed via civil3d_execute or civil3d_query has access to:
Global | Type | Description |
|
| Active AutoCAD document |
|
| Active Civil 3D document |
|
| Document database |
|
| Active transaction |
|
| Document editor |
All Civil 3D namespaces are auto-imported.
npm install && npm run build# Copy DLLs from Civil 3D to C_References/ (see C_References/README.md)
cd plugin/Civil3dMcpPlugin
dotnet buildNETLOAD → select Civil3dMcpPlugin.dll
C3DMCPSTATUS → verify running{
"mcpServers": {
"civil3d": {
"command": "node",
"args": ["/path/to/civil3d-mcp/build/index.js"]
}
}
}Variable | Default | Description |
|
| Plugin host |
|
| Plugin port |
|
| Execution timeout (ms) |
|
| Log level |
The Roslyn sandbox blocks:
Process execution (Process.Start)
File deletion (File.Delete)
Network requests (HttpClient, Sockets)
Registry access
Dynamic assembly loading
All Civil 3D API operations are allowed.
MIT
Execute C# code in Civil 3D with write access. The code runs inside a committed transaction. Available globals: Document, CivilDoc, Database, Transaction, Editor. All Civil 3D namespaces are auto-imported. Return a value to get results back as JSON. Use this for operations that MODIFY the drawing (create, edit, delete objects).
| Name | Required | Description | Default |
|---|---|---|---|
| code | Yes | C# code to execute. Has access to Document, CivilDoc, Database, Transaction, Editor. Example: var id = TinSurface.Create(Database, "MySurface"); return new { success = true }; | |
| description | No | Brief description of what this code does (for logging/audit trail). |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations, but description covers transaction context, available globals, auto-imports, and JSON return. Good disclosure of execution environment, though lacks error handling details.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Four concise sentences, each providing unique value. Front-loaded with purpose. No wasted words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Comprehensive for a code execution tool: covers purpose, transaction, globals, return format, and modification scope. Absence of output schema mitigated by description of JSON return.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema covers both parameters fully (100% coverage). Description reinforces code purpose with example but adds limited new semantic value beyond schema descriptions.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Clearly states verb 'Execute' and resource 'C# code in Civil 3D'. Distinguishes from siblings by emphasizing write access and modification, contrasting with query tool.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly states when to use: 'for operations that MODIFY the drawing'. Implies not for read-only, but could be more explicit about not using for queries.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Execute C# code in Civil 3D in READ-ONLY mode (no changes saved). Available globals: Document, CivilDoc, Database, Transaction, Editor. All Civil 3D namespaces are auto-imported. Return a value to get results as JSON. Use this for querying data: listing objects, getting properties, analyzing surfaces, etc.
| Name | Required | Description | Default |
|---|---|---|---|
| code | Yes | C# code to query data. Has access to Document, CivilDoc, Database, Transaction, Editor. Example: var surfaces = new List<object>(); foreach (ObjectId id in CivilDoc.GetSurfaceIds()) { var s = Transaction.GetObject(id, OpenMode.ForRead) as TinSurface; surfaces.Add(new { s.Name, s.Layer }); } return surfaces; |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden. It clearly states READ-ONLY mode and lists available globals (Document, CivilDoc, Database, Transaction, Editor) and notes that all Civil 3D namespaces are auto-imported. It also explains how to return results as JSON. However, it does not mention error handling, performance implications, or any limitations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise with three sentences, each serving a distinct purpose: stating the read-only mode, listing globals, and providing usage guidance. There is no redundant or unnecessary information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's complexity (code execution) and single parameter, the description covers all needed aspects: read-only guarantee, available globals, auto-imported namespaces, and how to return results. No output schema exists, but the description explains the JSON return format. It is complete for safe and correct usage.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
There is only one parameter 'code' with a schema description that includes an example. The description adds value by specifying the available globals and auto-imported namespaces, which are not in the schema. Since schema coverage is 100%, baseline is 3, but the added context justifies a 4.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool executes C# code in Civil 3D in READ-ONLY mode, with a specific verb and resource. It distinguishes from siblings by emphasizing read-only querying vs. execution, and the sibling names (civil3d_execute, civil3d_skills) further clarify the differentiation.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explicitly says 'Use this for querying data: listing objects, getting properties, analyzing surfaces, etc.' This provides clear when-to-use guidance. It does not explicitly state when not to use it, but the READ-ONLY mode and sibling names imply it is not for modifications. A small gap in not naming the alternative directly.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Browse and read Civil 3D code skills (documented C# code templates). Use 'list' to see available skills, 'search' to find by keyword, 'get' to read the full skill with code template. Skills are pre-built C# patterns you can adapt and execute via civil3d_execute or civil3d_query.
| Name | Required | Description | Default |
|---|---|---|---|
| action | Yes | list = show all skills, search = find by keyword, get = read full skill | |
| category | No | Filter by category (surfaces, alignments, points, etc.) | |
| query | No | Search query for 'search' action | |
| skillName | No | Skill name for 'get' action |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must convey behavioral traits. It implies read-only behavior through 'Browse and read' and actions like list/search/get, but does not explicitly state it is non-destructive. The lack of destructive mentions is acceptable for a clearly read-only tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences, no wasted words, and front-loads the purpose. It efficiently covers actions, usage, and relationship to sibling tools.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description adequately covers the tool's purpose and actions, references sibling tools for execution, and mentions that 'get' returns a full code template. However, it lacks details about output format or behavior for empty results, which is acceptable given the tool's simplicity.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so baseline is 3. The description adds context by explaining the three actions and their mapping to parameters, but does not provide significant detail beyond what the schema already describes.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool browses and reads Civil 3D code skills, lists three specific actions (list, search, get), and distinguishes from sibling execution tools by noting that skills can be adapted and executed via civil3d_execute or civil3d_query.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides clear context for using the tool (to find and read skills) and implicitly contrasts with execution tools, but does not explicitly state when not to use it or list alternative tools beyond mentioning civil3d_execute and civil3d_query.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v1.0.0civil3d_executecivil3d_querycivil3d_skillsScored across 3 tools
Each tool has a clearly distinct purpose: civil3d_execute for modifying drawings, civil3d_query for read-only queries, and civil3d_skills for browsing code templates. There is no overlap or ambiguity.
All tools follow a consistent 'civil3d_' prefix pattern with an action word. Two use verbs (execute, query) and one uses a noun (skills), which is a minor inconsistency, but the naming remains predictable and clear.
With 3 tools, the server is well-scoped for its purpose of executing C# code in Civil 3D. Each tool serves a necessary role: write access, read access, and skill templates. No extraneous tools.
The tool set covers the core operations for the meta-domain of code execution (read, write, and reference templates). However, it relies on the agent to write code for specific Civil 3D operations, so domain-specific completeness is limited but acceptable for the stated purpose.
AI Hub for AEC — 50+ 3D formats, clash detection, ACC integration via Autodesk Platform Services.
Connects AI assistants to QCDatabase.AI for everyday construction quality-control work.
Convert Revit files to XKT, IFC, or DWG and query BIM data via natural language.
Give your AI agents the tools to build, manage, and run automation workflows.
