Skip to main content
Glama

Deploy Heim Application

deploy_heim_application
Idempotent

Deploy backend applications to a local Heim runtime using the 'heim deploy' command, making them available at http://127.0.0.1:3000 with paths defined in OpenAPI specifications.

Instructions

Runs 'heim deploy' command to deploy an application to a local Heim runtime. Which will make the application availible on http://127.0.0.1:3000 where is the path defined in your OpenAPI specification

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
pathNoAbsolute windows path to the application folder root

Implementation Reference

  • The handler function executes the 'heim deploy' command using child_process.exec.promisify on the provided application path, returning stdout/stderr or an error.
    async (request) => {
      const execPromise = util.promisify(exec);
      try {
        const { stdout, stderr } = await execPromise(
          `heim deploy ${request.path}`
        );
        return {
          content: [
            {
              type: "text",
              text: `stdout:\n${stdout}\nstderr:\n${stderr}`,
            },
          ],
        };
      } catch (err: any) {
        return {
          content: [{ type: "text", text: `Error: ${err.message}` }],
          isError: true,
        };
      }
    }
  • Input schema defining an optional 'path' string parameter for the absolute path to the application folder.
    inputSchema: {
      path: z
        .string()
        .describe("Absolute windows path to the application folder root")
        .optional(),
    },
  • src/tools.ts:98-137 (registration)
    Registers the 'deploy_heim_application' tool with the MCP server, including title, description, input schema, annotations, and handler function.
    server.registerTool(
      "deploy_heim_application",
      {
        title: "Deploy Heim Application",
        description:
          "Runs 'heim deploy' command to deploy an application to a local Heim runtime. Which will make the application availible on http://127.0.0.1:3000<PATH> where <PATH> is the path defined in your OpenAPI specification",
        inputSchema: {
          path: z
            .string()
            .describe("Absolute windows path to the application folder root")
            .optional(),
        },
        annotations: {
          destructiveHint: false,
          readOnlyHint: false,
          idempotentHint: true,
          openWorldHint: false,
        },
      },
      async (request) => {
        const execPromise = util.promisify(exec);
        try {
          const { stdout, stderr } = await execPromise(
            `heim deploy ${request.path}`
          );
          return {
            content: [
              {
                type: "text",
                text: `stdout:\n${stdout}\nstderr:\n${stderr}`,
              },
            ],
          };
        } catch (err: any) {
          return {
            content: [{ type: "text", text: `Error: ${err.message}` }],
            isError: true,
          };
        }
      }
Behavior4/5

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

The description adds valuable behavioral context beyond annotations: it specifies the deployment makes the application available on a specific local URL (http://127.0.0.1:3000<PATH>), which is not covered by annotations. Annotations already indicate it's non-destructive, non-read-only, and idempotent, so the description appropriately focuses on runtime behavior rather than repeating those traits.

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 efficiently structured in two sentences: the first states the core action and target, the second explains the outcome (URL availability). Every phrase adds value without redundancy, making it front-loaded and appropriately concise for the tool's complexity.

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's moderate complexity (single parameter, no output schema), the description covers key aspects: purpose, local vs. cloud distinction, and deployment outcome. However, it lacks details on prerequisites (e.g., required OpenAPI spec), error conditions, or interaction with sibling tools like 'heim_clear', leaving minor gaps in completeness.

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?

With 100% schema description coverage, the input schema fully documents the single parameter ('path'). The description mentions '<PATH>' in the URL context but doesn't add meaningful semantics beyond what the schema provides (e.g., format examples or constraints). 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 ('Runs 'heim deploy' command'), the resource ('deploy an application'), and the target environment ('to a local Heim runtime'). It distinguishes from sibling 'deploy_heim_application_to_cloud' by specifying 'local' deployment, making the purpose unambiguous and differentiated.

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

Usage Guidelines4/5

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

The description provides clear context for when to use this tool (deploying to local runtime) and implicitly distinguishes it from the cloud deployment sibling. However, it lacks explicit guidance on when NOT to use it or alternatives for other scenarios (e.g., vs. 'heim_start' or 'new_heim_application'), which prevents a perfect score.

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/Nor2-io/heim-mcp'

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