MCP Integration

What it does

When your agent uses it

• Changing tRPC procedures under packages/api
• Adding MCP metadata
• Registering an eager MCP router
• Shaping tool inputs and descriptions

Example prompts

• “/mcp-integration”

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

1. 1Confirm the procedure still enforces its ordinary auth and permission boundary.
2. 2Confirm packages/api/src/mcp.ts eagerly includes the procedure.
3. 3Confirm the generated tool name, description, and JSON schema are unambiguous.
4. 4When validating tool-list or extraction changes, use the focused API MCP spec: bun run test packages/api/src/test/mcp.spec.ts.
5. 5When validating protocol or transport changes, use the focused route spec: bun run test…
6. 6If manually probing /api/mcp/, use a scoped API key and avoid printing credentials or secret-bearing results.

What it can do on your machine

Read from SKILL.md and the folder at commit fc2c15f. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Shell commands in SKILL.md call:

  • bun

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

MCP Integration loads about 1.1k tokens when it runs. Until then it costs about 74 tokens; SKILL.md has 405 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~74

When it runs · the whole SKILL.md, loaded when a task matches

~1.1k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from homarr-labs/homarr at commit fc2c15f, republished under its Apache-2.0 licence (© homarr-labs). 405 words, ~1,062 tokens.

name

mcp-integration

description

Expose Homarr tRPC procedures safely through MCP. Use when adding or changing tRPC procedures under packages/api, adding MCP metadata, registering an eager MCP router, shaping tool inputs and descriptions, or reviewing MCP authorization, sensitive data, and destructive actions.

getAll: protectedProcedure
  .meta({
    mcp: {
      enabled: true,
      description: "List resources the current user can access, including stable IDs used by resource_get",
    },
  })
  .input(z.object({ limit: z.number().int().min(1).max(100).default(50) }))
  .query(async ({ ctx, input }) => {
    // Preserve normal procedure authorization.
  });

remove: permissionRequiredProcedure
  .meta({
    mcp: {
      enabled: true,
      description: "Delete one resource by ID. Requires full access; get the ID from resource_all",
    },
  })
  .input(z.object({ id: z.string() }))
  .mutation(async ({ ctx, input }) => {
    // Perform the permission-scoped action.
  });

import { resourceRouter } from "./router/resource";

export const mcpRouter = createTRPCRouter({
  resource: resourceRouter,
});

© homarr-labs, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file in .agents/skills/mcp-integration of homarr-labs/homarr.

• SKILL.md
• agents/openai.yaml

Open the folder on GitHubat commit fc2c15f