Skip to main content
Glama
awwaiid

MCP Server for Alloy Modeling Language

by awwaiid

execute_alloy

Execute Alloy modeling language code to perform formal verification and software modeling, returning structured JSON results for analysis.

Instructions

Execute Alloy modeling language code and return structured JSON results

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
codeYesThe Alloy modeling language code to execute

Implementation Reference

  • Handler function that executes the provided Alloy code using alloy.eval(code), processes the result (success or error), and returns structured content with JSON for success cases and error messages.
      async ({ code }) => {
        try {
          const result = alloy.eval(code);
    
          // Type guard: check if result is an error
          if ('error' in result) {
            return {
              content: [
                {
                  type: "text",
                  text: `Error executing Alloy code: ${result.error}`
                }
              ],
              isError: true
            };
          }
    
          // TypeScript now knows result is AlloySuccessResult
          return {
            content: [
              {
                type: "text",
                text: JSON.stringify(result, null, 2)
              }
            ]
          };
        } catch (error) {
          const errorMessage = error instanceof Error ? error.message : String(error);
          return {
            content: [
              {
                type: "text",
                text: `Error executing Alloy code: ${errorMessage}`
              }
            ],
            isError: true
          };
        }
      }
    );
  • Zod schema defining the input parameter 'code' for the execute_alloy tool.
    {
      code: z.string().describe("The Alloy modeling language code to execute"),
    },
  • src/index.ts:16-60 (registration)
    Registration of the execute_alloy tool using server.tool(), including name, description, input schema, and inline handler function.
      "execute_alloy",
      "Execute Alloy modeling language code and return structured JSON results",
      {
        code: z.string().describe("The Alloy modeling language code to execute"),
      },
      async ({ code }) => {
        try {
          const result = alloy.eval(code);
    
          // Type guard: check if result is an error
          if ('error' in result) {
            return {
              content: [
                {
                  type: "text",
                  text: `Error executing Alloy code: ${result.error}`
                }
              ],
              isError: true
            };
          }
    
          // TypeScript now knows result is AlloySuccessResult
          return {
            content: [
              {
                type: "text",
                text: JSON.stringify(result, null, 2)
              }
            ]
          };
        } catch (error) {
          const errorMessage = error instanceof Error ? error.message : String(error);
          return {
            content: [
              {
                type: "text",
                text: `Error executing Alloy code: ${errorMessage}`
              }
            ],
            isError: true
          };
        }
      }
    );
  • Type definitions for the 'alloy-lang' module, defining interfaces for Alloy results used in the handler for type guarding and processing.
    declare module 'alloy-lang' {
      export interface AlloyInstance {
        messages: unknown[];
        skolems: Record<string, unknown>;
        state: number;
        values: Record<string, unknown>;
      }
    
      export interface AlloySuccessResult {
        duration: number;
        incremental: boolean;
        instances: AlloyInstance[];
        localtime: string;
        loopstate: number;
        sigs: Record<string, unknown>;
        timezone: string;
        utctime: number;
      }
    
      export interface AlloyErrorResult {
        error: string;
      }
    
      export type AlloyResult = AlloySuccessResult | AlloyErrorResult;
    
      export function evalRaw(alloyProgram: string): string;
      export function eval(alloyProgram: string): AlloyResult;
    
      const alloy: {
        evalRaw: typeof evalRaw;
        eval: typeof eval;
      };
    
      export default alloy;
    }
Behavior2/5

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It mentions execution and returning JSON results but fails to describe critical traits like error handling, execution time, resource usage, or security implications. For a code execution tool with zero annotation coverage, this is a significant gap in transparency.

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?

The description is a single, efficient sentence that directly states the tool's function without unnecessary words. It is front-loaded with the core action and outcome, making it easy to parse. Every part of the sentence contributes essential information, earning a perfect score for conciseness.

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?

Given the complexity of code execution and the lack of annotations and output schema, the description is insufficient. It doesn't explain what 'structured JSON results' entail, potential errors, or execution limits. For a tool that could have varied outputs and behaviors, more context is needed to ensure reliable agent usage.

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?

The input schema has 100% description coverage, with the 'code' parameter fully documented. The description adds minimal value beyond the schema by implying the code is executed, but it doesn't provide additional details like syntax examples or constraints. With high schema coverage, the baseline score of 3 is appropriate, as the description doesn't significantly enhance parameter understanding.

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

Purpose4/5

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

The description clearly states the tool's purpose: 'Execute Alloy modeling language code and return structured JSON results.' It specifies the verb ('execute'), resource ('Alloy modeling language code'), and outcome ('return structured JSON results'), making it easy to understand what the tool does. However, with no sibling tools mentioned, there's no opportunity to distinguish from alternatives, preventing a perfect score.

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, such as typical use cases, prerequisites, or limitations. It lacks any context about alternatives or exclusions, leaving the agent with minimal direction beyond the basic purpose. This absence of usage guidelines reduces its effectiveness in tool selection.

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/awwaiid/mcp-server-alloy'

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