Skip to main content
Glama

visum_launch_project

Open a Visum project file to enable structured sequential thinking for breaking down complex problems into manageable steps.

Instructions

⚠️ DEPRECATED: Use 'project_open' tool instead. This tool is obsolete and slower than the new TCP-based project_open tool.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
projectPathYesFull path to the Visum project file (.ver)

Implementation Reference

  • The handler function for the 'visum_launch_project' tool. It executes VisumPy code to load a specific Visum project (.ver file), retrieves basic network statistics, and returns formatted success or error messages.
      async ({ projectPath }) => {
        try {
          const result = await visumController.executeVisumAnalysis(
            `# Load specific Visum project
    import time
    try:
        start_time = time.time()
        visum.LoadVersion(r"${projectPath}")
        load_time = time.time() - start_time
        
        # Get basic network info
        num_nodes = visum.Net.Nodes.Count
        num_links = visum.Net.Links.Count  
        num_zones = visum.Net.Zones.Count
        
        result = {
            'project_path': r"${projectPath}",
            'loaded_successfully': True,
            'load_time_seconds': round(load_time, 3),
            'network_summary': {
                'nodes': num_nodes,
                'links': num_links, 
                'zones': num_zones
            }
        }
    except Exception as e:
        result = {
            'project_path': r"${projectPath}",
            'loaded_successfully': False,
            'error': str(e)
        }`,
            `Loading Visum project: ${projectPath}`
          );
    
          if (result.success && result.result?.loaded_successfully) {
            const info = result.result;
            return {
              content: [
                {
                  type: "text",
                  text: `✅ **Progetto Visum Caricato**\n\n` +
                        `**Progetto:** \`${info.project_path}\`\n` +
                        `**Tempo di Caricamento:** ${info.load_time_seconds}s\n\n` +
                        `**Statistiche Rete:**\n` +
                        `• **Nodi:** ${info.network_summary?.nodes?.toLocaleString() || 'N/A'}\n` +
                        `• **Link:** ${info.network_summary?.links?.toLocaleString() || 'N/A'}\n` +
                        `• **Zone:** ${info.network_summary?.zones?.toLocaleString() || 'N/A'}\n\n` +
                        `**Performance:**\n` +
                        `• **Tempo Esecuzione:** ${result.executionTimeMs?.toFixed(3) || 'N/A'}ms\n\n` +
                        `*Progetto pronto per l'analisi della rete*`
                }
              ]
            };
          } else {
            return {
              content: [
                {
                  type: "text",
                  text: `❌ **Errore Caricamento Progetto**\n\n` +
                        `**Progetto:** \`${projectPath}\`\n` +
                        `**Errore:** ${result.result?.error || result.error || 'Errore sconosciuto'}\n\n` +
                        `*Verificare che il percorso del file sia corretto e che il progetto sia valido*`
                }
              ]
            };
          }
        } catch (error) {
          return {
            content: [
              {
                type: "text",
                text: `❌ **Errore durante il caricamento:**\n\n${error instanceof Error ? error.message : String(error)}`
              }
            ]
          };
        }
      }
  • Zod input schema for the tool, requiring the full path to the Visum project file.
      projectPath: z.string().describe("Full path to the Visum project file (.ver)")
    },
  • Registration of the 'visum_launch_project' tool using McpServer's server.tool() method. Marked as deprecated in favor of 'project_open'.
    server.tool(
      "visum_launch_project",
      "⚠️ DEPRECATED: Use 'project_open' tool instead. This tool is obsolete and slower than the new TCP-based project_open tool.",
      {
        projectPath: z.string().describe("Full path to the Visum project file (.ver)")
      },
      async ({ projectPath }) => {
        try {
          const result = await visumController.executeVisumAnalysis(
            `# Load specific Visum project
    import time
    try:
        start_time = time.time()
        visum.LoadVersion(r"${projectPath}")
        load_time = time.time() - start_time
        
        # Get basic network info
        num_nodes = visum.Net.Nodes.Count
        num_links = visum.Net.Links.Count  
        num_zones = visum.Net.Zones.Count
        
        result = {
            'project_path': r"${projectPath}",
            'loaded_successfully': True,
            'load_time_seconds': round(load_time, 3),
            'network_summary': {
                'nodes': num_nodes,
                'links': num_links, 
                'zones': num_zones
            }
        }
    except Exception as e:
        result = {
            'project_path': r"${projectPath}",
            'loaded_successfully': False,
            'error': str(e)
        }`,
            `Loading Visum project: ${projectPath}`
          );
    
          if (result.success && result.result?.loaded_successfully) {
            const info = result.result;
            return {
              content: [
                {
                  type: "text",
                  text: `✅ **Progetto Visum Caricato**\n\n` +
                        `**Progetto:** \`${info.project_path}\`\n` +
                        `**Tempo di Caricamento:** ${info.load_time_seconds}s\n\n` +
                        `**Statistiche Rete:**\n` +
                        `• **Nodi:** ${info.network_summary?.nodes?.toLocaleString() || 'N/A'}\n` +
                        `• **Link:** ${info.network_summary?.links?.toLocaleString() || 'N/A'}\n` +
                        `• **Zone:** ${info.network_summary?.zones?.toLocaleString() || 'N/A'}\n\n` +
                        `**Performance:**\n` +
                        `• **Tempo Esecuzione:** ${result.executionTimeMs?.toFixed(3) || 'N/A'}ms\n\n` +
                        `*Progetto pronto per l'analisi della rete*`
                }
              ]
            };
          } else {
            return {
              content: [
                {
                  type: "text",
                  text: `❌ **Errore Caricamento Progetto**\n\n` +
                        `**Progetto:** \`${projectPath}\`\n` +
                        `**Errore:** ${result.result?.error || result.error || 'Errore sconosciuto'}\n\n` +
                        `*Verificare che il percorso del file sia corretto e che il progetto sia valido*`
                }
              ]
            };
          }
        } catch (error) {
          return {
            content: [
              {
                type: "text",
                text: `❌ **Errore durante il caricamento:**\n\n${error instanceof Error ? error.message : String(error)}`
              }
            ]
          };
        }
      }
    );
Behavior4/5

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

No annotations are provided, so the description carries full burden. It discloses key behavioral traits: deprecated status, obsolescence, and slowness compared to the TCP-based alternative. However, it doesn't mention what the tool actually does behaviorally (e.g., whether it opens a file, starts a process, or requires specific permissions), leaving some gaps.

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

Conciseness5/5

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

Two sentences with zero waste: the first declares deprecation and alternative, the second explains why (obsolete and slower). It's front-loaded with critical usage guidance and appropriately sized for a deprecated tool.

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

Completeness4/5

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

Given the tool is deprecated with a clear alternative, the description is complete enough for an agent to avoid it. However, with no annotations and no output schema, it lacks details on what the tool originally did (e.g., return values or side effects), which could be useful for legacy contexts.

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%, with the parameter 'projectPath' fully documented in the schema. The description adds no additional parameter information beyond what the schema provides, so it meets the baseline of 3 for high schema coverage without compensating value.

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

Purpose2/5

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

The description states the tool is deprecated and obsolete, which implies it was used to launch projects, but it doesn't specify what 'launch' entails (e.g., opening, initializing, or starting a project). It distinguishes from sibling 'project_open' by noting obsolescence and slowness, but lacks a clear verb+resource statement for its original purpose.

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

Usage Guidelines5/5

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

Explicitly states 'Use 'project_open' tool instead' and provides clear when-not-to-use guidance (deprecated, obsolete, slower). It names the alternative tool directly, making it unambiguous for the agent to avoid this tool in favor of the sibling.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/multiluca2020/visum-thinker-mcp-server'

If you have feedback or need assistance with the MCP directory API, please join our Discord server