Atlas / MCP servers / 2fst4u / mealie-mcp

mealie-mcpSAFE

mcp/2fst4u/mealie-mcp
Verdict
SAFE
Grade
B
Trust score
89 /100
Exposed tools
1 1r · 0w · 0d
Transport
stdio
License
MIT
Stars
4
01

Overview

From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.

A Model Context Protocol (MCP) server for Mealie, the self-hosted recipe manager, meal planner and shopping-list app.

It exposes every endpoint of the Mealie REST API as an MCP tool, so an LLM (Claude, etc.) can read and manage your recipes, meal plans, shopping lists, cookbooks, households, users and more.

  • 🧩 Broad API coverage, sane baseline — one tool per Mealie endpoint,

trimmed to a safe baseline (~211 of ~259) so clients aren't overwhelmed and risky endpoints aren't reachable.

  • 🔄 Auto-adapts to your Mealie version — on startup it fetches the OpenAPI

schema from your instance, so the tools always match exactly what your server supports. A bundled snapshot is used as a fallback if the fetch fails.

  • 🚀 Zero install — runs straight from npx, ideal for MCPHub, Claude

Desktop, Cursor, and any other MCP client.

  • 🔒 Safe by default — admin/server-ops endpoints are never exposed, plus

read-only mode and per-category include/exclude filtering to narrow further.

  • 🔑 Flexible auth — a static API token, or an OAuth2 client-credentials flow

that fetches and refreshes access tokens for you.

Quick start

You need three things:

  1. Node.js 22+ installed on your machine
  2. The base URL of your Mealie instance, e.g. https://mealie.example.com
  3. A Mealie API token (see Getting an API token)

Run it with npx:

MEALIE_BASE_URL="https://mealie.example.com" \
MEALIE_API_TOKEN="your-long-lived-token" \
npx -y mealie-mcp

The server speaks MCP over stdio, so you normally won't run it by hand — your MCP client launches it for you using the config below.

Client configuration

MCPHub / Claude Desktop / Cursor (generic MCP config)

Add an entry to your client's MCP servers config (for Claude Desktop this is claude_desktop_config.json; MCPHub uses an equivalent mcpServers blo

Read from source at commit 4724583f9a7dOBSERVED · 2026-10-12
Advertisement
02

Connect

Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control.

claude-code
claude mcp add mealie-mcp -- npx -y [email protected]
claude-desktop
{
  "mcpServers": {
    "mealie-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "[email protected]"
      ]
    }
  }
}
03

Exposed tools (1)

1 read · 0 write · 0 destructive.

ToolRiskDescription
test_toolread
04

Trust audit

SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.

LayerWhat it checksResult
L0Provenance & inventoryPASS
L1Static analysis of the codePASS
L2Instruction surface (what it tells the agent)PASS
L3Class-specific surfacePASS
L4Behavioural (sandbox)SKIPPED

What the source does

Filesystem
none-observed
Network
declared (3 observation(s))
Shell
none-observed
Dependencies
not all pinned
Secrets in source
none-found

Findings (2)

LOWFilesystem / path · fs.traversal · CWE-22, CWE-59
test/utils/url.test.ts:3
import { safeUrl } from "../../src/utils/url.js";
LOWSupply chain · supply.unpinned · CWE-829, CWE-1357
package.json
@modelcontextprotocol/sdk, @types/node, tsx, typescript
Why it matters. 4 dependency range(s) float
Fix. pin exact versions or ship a lockfile

Gates applied: no_behavioural_pass.

Audited 2026-10-12 · audit v0.4.1 · source sha 4724583f9a7dfull audit observations/trust-audit/mcp-server/2fst4u__mealie-mcp.json · Report an issue / request a re-scan
05

Audit history

Every audit this server has had. A grade with a past is a grade somebody is still checking.

DateSourceVerdictGradeScoreChange
2026-10-124724583f9a7dSAFEB89first audit
06

Questions

What tools does mealie-mcp expose?

1 in total: 1 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.

Is mealie-mcp safe to connect to an agent?

The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.

What credentials does mealie-mcp need?

No credential environment variables were found in its source, so it appears to need none.

How does mealie-mcp run?

It speaks stdio, so it runs as a local process your client starts. It is published on npm as mealie-mcp at 0.3.7.

How current is this page?

The grade is for one exact copy of the source (4724583f9a7d), read on 2026-10-12. The repository is watched and re-audited when it changes.

Advertisement