Skip to main content
Glama

send_code_to_revit

Execute custom C# code in Autodesk Revit to automate BIM workflows, modify project elements, and extend functionality through direct API access.

Instructions

Send C# code to Revit for execution. The code will be inserted into a template with access to the Revit Document and parameters. Your code should be written to work within the Execute method of the template.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
codeYesThe C# code to execute in Revit. This code will be inserted into the Execute method of a template with access to Document and parameters.
parametersNoOptional execution parameters that will be passed to your code

Implementation Reference

  • The asynchronous handler function that implements the core logic of the 'send_code_to_revit' tool. It prepares parameters from the input arguments, uses withRevitConnection to send the command to the Revit client, and formats the response or error as MCP content.
    async (args, extra) => {
      const params = {
        code: args.code,
        parameters: args.parameters || [],
      };
    
      try {
        const response = await withRevitConnection(async (revitClient) => {
          return await revitClient.sendCommand("send_code_to_revit", params);
        });
    
        return {
          content: [
            {
              type: "text",
              text: `Code execution successful!\nResult: ${JSON.stringify(
                response,
                null,
                2
              )}`,
            },
          ],
        };
      } catch (error) {
        return {
          content: [
            {
              type: "text",
              text: `Code execution failed: ${
                error instanceof Error ? error.message : String(error)
              }`,
            },
          ],
        };
      }
    }
  • Zod schema defining the input parameters for the tool: 'code' (required string) and 'parameters' (optional array). Used in server.tool() registration.
    {
      code: z
        .string()
        .describe(
          "The C# code to execute in Revit. This code will be inserted into the Execute method of a template with access to Document and parameters."
        ),
      parameters: z
        .array(z.any())
        .optional()
        .describe(
          "Optional execution parameters that will be passed to your code"
        ),
    },
  • The registration function exported from the tool file. It calls server.tool() to register the 'send_code_to_revit' MCP tool with its name, description, input schema, and handler. This function is dynamically invoked by src/tools/register.ts.
    export function registerSendCodeToRevitTool(server: McpServer) {
      server.tool(
        "send_code_to_revit",
        "Send C# code to Revit for execution. The code will be inserted into a template with access to the Revit Document and parameters. Your code should be written to work within the Execute method of the template.",
        {
          code: z
            .string()
            .describe(
              "The C# code to execute in Revit. This code will be inserted into the Execute method of a template with access to Document and parameters."
            ),
          parameters: z
            .array(z.any())
            .optional()
            .describe(
              "Optional execution parameters that will be passed to your code"
            ),
        },
        async (args, extra) => {
          const params = {
            code: args.code,
            parameters: args.parameters || [],
          };
    
          try {
            const response = await withRevitConnection(async (revitClient) => {
              return await revitClient.sendCommand("send_code_to_revit", params);
            });
    
            return {
              content: [
                {
                  type: "text",
                  text: `Code execution successful!\nResult: ${JSON.stringify(
                    response,
                    null,
                    2
                  )}`,
                },
              ],
            };
          } catch (error) {
            return {
              content: [
                {
                  type: "text",
                  text: `Code execution failed: ${
                    error instanceof Error ? error.message : String(error)
                  }`,
                },
              ],
            };
          }
        }
      );
    }
  • Dynamic registration entrypoint that scans src/tools directory, imports tool modules like send_code_to_revit.ts, discovers and invokes their register* functions to register all MCP tools with the server.
    export async function registerTools(server: McpServer) {
      // 获取当前文件的目录路径
      const __filename = fileURLToPath(import.meta.url);
      const __dirname = path.dirname(__filename);
    
      console.error('[DEBUG] Starting tool registration from directory:', __dirname);
    
      try {
        // 读取tools目录下的所有文件
        const files = fs.readdirSync(__dirname);
        console.error(`[DEBUG] Found ${files.length} files in tools directory`);
    
        // 过滤出.ts或.js文件,但排除index文件和register文件
        const toolFiles = files.filter((file) => (file.endsWith('.ts') || file.endsWith('.js')) && file !== 'index.ts' && file !== 'index.js' && file !== 'register.ts' && file !== 'register.js');
    
        console.error(`[DEBUG] Filtered to ${toolFiles.length} tool files:`, toolFiles);
    
        // 动态导入并注册每个工具
        const registeredTools = [];
    
        for (const file of toolFiles) {
          try {
            console.error(`[DEBUG] Processing tool file: ${file}`);
            // 构建导入路径
            const importPath = `./${file.replace(/\.(ts|js)$/, '.js')}`;
            console.error(`[DEBUG] Import path: ${importPath}`);
    
            // 动态导入模块
            const module = await import(importPath);
            console.error(`[DEBUG] Module imported successfully with keys:`, Object.keys(module));
    
            // 查找并执行注册函数
            const registerFunctionName = Object.keys(module).find((key) => key.startsWith('register') && typeof module[key] === 'function');
    
            if (registerFunctionName) {
              console.error(`[DEBUG] Found register function: ${registerFunctionName}`);
              await module[registerFunctionName](server);
              console.error(`[DEBUG] Registered tool from file: ${file}`);
              registeredTools.push(file);
            } else {
              console.warn(`[DEBUG] WARNING: No register function found in file ${file}. Available exports:`, Object.keys(module));
            }
          } catch (error) {
            console.error(`[DEBUG] ERROR registering tool ${file}:`, error);
          }
        }
    
        console.error(`[DEBUG] Successfully registered ${registeredTools.length} tools:`, registeredTools);
    
        // List all registered tools by tools' names
        try {
          // This is a workaround as we don't have direct access to registry in the type definitions
          const anyServer = server as any;
          if (anyServer.registry && typeof anyServer.registry.getTools === 'function') {
            const registeredToolNames = anyServer.registry.getTools().map((t: any) => t.id);
            console.error(`[DEBUG] Server has ${registeredToolNames.length} registered tools:`, registeredToolNames);
          } else {
            console.error('[DEBUG] Could not access server registry to list tools');
          }
        } catch (err) {
          console.error('[DEBUG] Error trying to list registered tools:', err);
        }
      } catch (error) {
        console.error('[DEBUG] ERROR during tool registration process:', error);
        throw error;
      }
    }

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

B3.1/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of behavioral disclosure. It mentions that code is inserted into a template with access to Document and parameters, but doesn't address critical behaviors like execution safety (e.g., whether code runs in a sandbox, potential for destructive changes), authentication requirements, error handling, or performance implications. The description provides basic context but leaves significant gaps for a tool that executes arbitrary code.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is appropriately sized with two clear sentences that efficiently convey the core functionality. The first sentence states the primary action, and the second provides important contextual constraints about the template structure. There's no redundant information, though it could be slightly more front-loaded with usage context.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool that executes arbitrary C# code in Revit with no annotations and no output schema, the description is insufficiently complete. It doesn't address safety considerations, expected return values, error conditions, or execution environment details that would be crucial for an AI agent to use this tool responsibly. The description covers basic mechanics but misses critical contextual information.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already fully documents both parameters. The description adds minimal value beyond the schema by mentioning the template context and Execute method, but doesn't provide additional syntax examples, parameter format details, or constraints beyond what's in the schema descriptions. This meets the baseline for high schema coverage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the specific action ('Send C# code to Revit for execution'), identifies the resource (Revit), and distinguishes it from sibling tools that perform element manipulation, filtering, or creation operations. It provides a precise verb+resource combination that is unique among the available tools.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives. It doesn't mention prerequisites (e.g., needing an active Revit session), exclusions, or compare it to sibling tools like 'operate_element' or 'ai_element_filter' that might handle different types of operations. Usage is implied only through the tool's purpose.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.