Mealie Mcp

CLI or API | MCP | Agent

Version: 2.3.1

Overview

Mealie Mcp is a production-grade Agent and Model Context Protocol (MCP) server designed to interface directly with Mealie MCP Server for Agentic AI!.

Key Features

• Consolidated Action-Routed MCP Tools: Minimizes token overhead and eliminates tool bloat in LLM contexts by grouping methods into optimized, togglable tool modules.
• Enterprise-Grade Security: Complete support for Eunomia policies, OIDC token delegation, and granular execution context tracking.
• Integrated Graph Agent: Built-in Pydantic AI agent supporting the Agent Control Protocol (ACP) and standard Web interfaces (AG-UI).
• Native Telemetry & Tracing: Out-of-the-box OpenTelemetry exports and native Langfuse tracing.

CLI or API

This agent wraps the Mealie MCP Server for Agentic AI! API. The operator can interact with it programmatically or via its integrated execution entrypoints.

Detailed instructions on how to use the underlying API wrappers, extended schema bindings, and developer SDK references are maintained in docs/index.md.

MCP

This server use dynamic Action-Routed tools to optimize token overhead and maximize IDE compatibility.

Available MCP Tools

Condensed action-routed tools (MCP_TOOL_MODE=condensed)

Verbose 1:1 API-mapped tools (MCP_TOOL_MODE=verbose or both)

18 action-routed tool(s) · 246 verbose 1:1 tool(s). Each is enabled unless its <DOMAIN>TOOL toggle is set false; MCP_TOOL_MODE selects the surface (intent default — the six verb-tools, granular set loaded on demand · condensed action-routed · verbose 1:1 · both). Auto-generated — do not edit.

Detailed tool schemas, parameter shapes, and validation constraints are preserved in docs/usage.md.

Dynamic Tool Selection & Visibility

This MCP server supports dynamic toolset selection and visibility filtering at runtime. This allows the operator to restrict the set of exposed tools to prevent blowing up the LLM's context window.

The operator can configure tool filtering via multiple input channels:

• CLI Arguments: Pass --tools or --toolsets (or their disabled counterparts --disabled-tools and --disabled-toolsets) during startup.
• Environment Variables: Define standard environment variables:
  • MCP_ENABLED_TOOLS / MCP_DISABLED_TOOLS
  • MCP_ENABLED_TAGS / MCP_DISABLED_TAGS
• HTTP SSE Request Headers: Pass custom headers during transport initialization:
  • x-mcp-enabled-tools / x-mcp-disabled-tools
  • x-mcp-enabled-tags / x-mcp-disabled-tags
• HTTP SSE Request Query Parameters: Append query parameters directly to the operator's transport connection URL:
  • ?tools=tool1,tool2
  • ?tags=tag1

When query strings or parameters are provided, an LLM-free Knowledge Graph resolution layer (using DynamicToolOrchestrator) matches query intents against known tool tags, names, or descriptions, with safe fallback and automated 24-hour background cache refreshing.

MCP Configuration Examples

Install the connector-focused [mcp] extra. Examples use mealie-mcp[mcp] to add FastMCP / FastAPI through agent-connector-sdk[mcp]; the required Agent Utilities core still carries epistemic-graph[full]. The [agent-runtime] extra additionally enables model orchestration.

stdio Transport (local IDEs — Cursor, Claude Desktop, VS Code)

{
  "mcpServers": {
    "mealie-mcp": {
      "command": "uvx",
      "args": [
        "--from",
        "mealie-mcp[mcp]",
        "mealie-mcp"
      ],
      "env": {
        "MCP_TOOL_MODE": "intent",
        "ADMINTOOL": "True",
        "APPTOOL": "True",
        "EXPLORETOOL": "True",
        "GROUPSTOOL": "True",
        "HOUSEHOLDSTOOL": "True",
        "KGTOOL": "True",
        "MEALIE_BASE_URL": "http://localhost:8025",
        "MEALIE_TOKEN": "your_token_here",
        "ORGANIZERTOOL": "True",
        "RECIPESTOOL": "True",
        "SHAREDTOOL": "True",
        "USERSTOOL": "True",
        "UTILSTOOL": "True"
      }
    }
  }
}

Runtime references require an alias-aware launcher such as Arbora. Other launchers must omit those entries and inject the resolved values through their own runtime secret boundary.

Streamable-HTTP Transport (networked / production)

{
  "mcpServers": {
    "mealie-mcp": {
      "command": "uvx",
      "args": [
        "--from",
        "mealie-mcp[mcp]",
        "mealie-mcp",
        "--transport",
        "streamable-http",
        "--port",
        "8000"
      ],
      "env": {
        "TRANSPORT": "streamable-http",
        "HOST": "127.0.0.1",
        "PORT": "8000",
        "MCP_TOOL_MODE": "intent",
        "ADMINTOOL": "True",
        "APPTOOL": "True",
        "EXPLORETOOL": "True",
        "GROUPSTOOL": "True",
        "HOUSEHOLDSTOOL": "True",
        "KGTOOL": "True",
        "MEALIE_BASE_URL": "http://localhost:8025",
        "MEALIE_TOKEN": "your_token_here",
        "ORGANIZERTOOL": "True",
        "RECIPESTOOL": "True",
        "SHAREDTOOL": "True",
        "USERSTOOL": "True",
        "UTILSTOOL": "True"
      }
    }
  }
}

Alternatively, connect to a pre-deployed Streamable-HTTP instance by url:

{
  "mcpServers": {
    "mealie-mcp": {
      "url": "http://localhost:8000/mealie-mcp/mcp"
    }
  }
}

Run a reviewed container image as a least-privilege stdio child (no listener or published port):

docker run -i --rm \
  --read-only \
  --cap-drop=ALL \
  --security-opt=no-new-privileges \
  --pids-limit=256 \
  --tmpfs /tmp:rw,noexec,nosuid,nodev,size=64m \
  -e TRANSPORT=stdio \
  -e MCP_TOOL_MODE=intent \
  -e ADMINTOOL=True \
  -e APPTOOL=True \
  -e EXPLORETOOL=True \
  -e GROUPSTOOL=True \
  -e HOUSEHOLDSTOOL=True \
  -e KGTOOL=True \
  -e MEALIE_BASE_URL=http://localhost:8025 \
  -e MEALIE_TOKEN=your_token_here \
  -e ORGANIZERTOOL=True \
  -e RECIPESTOOL=True \
  -e SHAREDTOOL=True \
  -e USERSTOOL=True \
  -e UTILSTOOL=True \
  registry.example.invalid/mealie-mcp@sha256:<digest> mealie-mcp

For containerized network HTTP, supply an authenticated TLS ingress (or direct server TLS), exact MCP_ALLOWED_HOSTS, and an exact trusted-proxy CIDR policy through the operator-owned deployment profile. The generator does not emit an unauthenticated non-loopback listener.

Auto-generated from the code-read env surface (MCP_TOOL_MODE + package vars) — do not edit.

Additional Deployment Options

mealie-mcp can run as a local stdio process or container, or behind a remote network boundary. The Deployment guide carries the detailed transport contract.

• Local container — launch a reviewed immutable image as a least-privilege stdio child with no listener or published port.
• Remote URL — connect through an operator-supplied authenticated HTTPS ingress. Keep its URL, outbound identity references, trust profile, and exact MCP_ALLOWED_HOSTS in AgentConfig.

Security & Governance

Built directly upon the enterprise-ready agent-connector-sdk core, standard security parameters are fully supported:

Access Control & Policy Enforcement

• Eunomia Policies: Fine-grained, policy-driven tool authorization. Supports none, local embedded (mcp_policies.json), or centralized remote modes.
• OIDC Token Delegation: Compliant with RFC 8693 token exchange for flowing authenticating user credentials from Web UI / ACP → Agent → MCP.
• Scoped Credentials: Execution context runs restricted to the specific caller identity.

Runtime Security Grid

Environment Variables

Package environment variables

Inherited agent-connector-sdk variables (apply to every connector)

28 package + 16 inherited variable(s). Auto-generated from .env.example + the shared agent-connector-sdk set — do not edit.

Every variable the server reads. A local template is provided inside .env.example — copy it to .env and fill in the operator's endpoint/credentials.

Connection & Credentials

MCP server / transport

Telemetry & governance

Tool toggles

Each action-routed tool can be disabled individually via its toggle env var (set to false). The full list is in the Available MCP Tools table above (e.g. RECIPESTOOL, USERSTOOL, ORGANIZERTOOL, ADMINTOOL).

Installation

Pick the extra that matches what the operator want to run:

# Connector-focused MCP server (includes the shared graph engine)
uv pip install "mealie-mcp[mcp]"

# Agent runtime (adds model orchestration to the shared graph engine)
uv pip install "mealie-mcp[agent]"

# Everything (development)
uv pip install "mealie-mcp[all]"      # or: python -m pip install "mealie-mcp[all]"

Container image (:mcp)

docker/Dockerfile builds the connector-focused MCP server image (--target mcp):

docker build --target mcp -t knucklessg1/mealie-mcp:mcp docker/   # connector-focused MCP server

docker/mcp.compose.yml runs the :mcp server. It requires an explicit @sha256 digest-pinned image, plus a read-only root filesystem, dropped capabilities, and a non-root user — resolve the digest for the tag the operator built/pulled rather than deploying a floating tag.

Knowledge-graph database (epistemic-graph)

Both [mcp] and [agent] carry the epistemic-graph engine through the required Agent Utilities core dependency (epistemic-graph[full]). The [mcp] extra keeps the server connector-focused; [agent] also enables model orchestration. Local deployments can use the bundled engine. For production — or to share one knowledge graph across multiple agents — run epistemic-graph as its own database container (or a dedicated shared service) and point the runtime at it instead of embedding it. Deployment recipes (single-node + Raft HA), connection config, and the full database architecture (with diagrams) are documented in the epistemic-graph deployment guide.

Repository Owners

Contribute

Contributions are welcome! Please ensure code quality by running local checks before submitting pull requests:

• Format code using ruff format .
• Lint code using ruff check .
• Validate type-safety with mypy .
• Ran test suites using pytest

Deploy with agent-connector-sdk-deployment

Provision this package with the consolidated agent-connector-sdk-deployment workflow. It selects an installed-package, editable-source, or immutable-container path; records only runtime secret and TLS-profile references in AgentConfig; and runs doctor, registration, policy, observability, and rollback gates. Ask your agent to "deploy mealie-mcp with agent-connector-sdk-deployment".

The repository embeds no deployment profile, credential value, certificate path, or environment-specific endpoint. Supply those at runtime through AgentConfig and the configured secret provider.

Governed capability contract

This package ships a compact canonical skill surface with specialist procedures kept as referenced workflows. The current MCP tools, skill metadata, connector_manifest.yml, ontology, mappings, shapes, fixtures, migrations, tool-schema fingerprints, and certification metadata form one versioned capability contract. Validate them together; do not rely on stale tool names or historical per-task skill wrappers.

Runtime endpoints, credentials, certificate trust, tenant identity, retention, and observability policy are deployment inputs and are never packaged values. See Configuration, trust, and privacy before enabling a network transport, connector ingestion, Arbora delegation, or trace export.

Typed recipe writes

The recipes domain also provides mealie_recipe_create, mealie_recipe_update, mealie_recipe_patch, mealie_recipe_foods, mealie_recipe_units, mealie_recipe_food_create and mealie_recipe_unit_create. These accept JSON objects with discoverable nested schemas. They follow the existing recipes tool visibility policy: directly available in condensed/both mode, and available through granular tool loading when the shared intent surface gates the domain. The existing mealie_recipes(action, params_json) remains compatible.

Creation uses Mealie's native two-stage workflow:

1. Call mealie_recipe_create with {"data":{"name":"Vegetable soup"}}. This makes one POST and returns the recipe slug.

2. Use that slug with mealie_recipe_patch, for example:

   {
     "slug": "vegetable-soup",
     "data": {
       "recipeIngredient": [
         {"quantity": 2, "food": {"name": "carrot"}, "unit": {"name": "cup"},
          "title": "Soup", "note": "diced"}
       ]
     }
   }
   

Search foods/units before creating records; pass existing returned objects or create-record objects into ingredients, rather than bare IDs. Ingredient title is a section heading, not ingredient text. PATCH sends only provided fields and preserves explicit nulls; ingredient lists are replaced as a whole. For PUT, fetch the current recipe via mealie_recipes action get_recipes_slug and edit that full body, since omitted fields can reset on the server. The typed surface rejects malformed nested data before an API call. Server business rules still apply. See schema provenance and regeneration.