free-faker-mcp

View on GitHub

Free MCP server for generating fake data, powered by mcp-grpc-gateway

0 stars GoOthers Updated Jun 21, 2026

Documentation

faker-mcp

A free, open-source MCP server that generates fake data using faker-go. Powered by mcp-grpc-gateway.

Hosted endpoint: `https://free.cadenya.com/faker-mcp`

Why?

This is more of a proof of concept for mcp-grpc-gateway than it is a valuable MCP server. However there are times when using fake data in an LLMs conversation can be useful to generate company names, addresses, etc. Can LLMs do that? Sure. But that's not the point.

It is hosted for free by Cadenya, an Agent Runtime.

Tools

The footprint of tools is very low (not every faker category is loaded into context, that would be a waste of input tokens).

Tool	Description
`GetFakerOptions`	Lists supported fake data generators. Use `filter` to narrow by name, category, or description.
`GenerateFake`	Generates one fake data value by option name and optional arguments.
`GenerateCurseWord`	Generates one PG-13 curse word from a small built-in list.

The service builds its catalog from the exported faker-go API at startup. It includes every reflected method that can be called with JSON-friendly scalar arguments and returned as text or JSON. Example faker names: `person.name`, `internet.email`, `company.name`, `address.city`, `lorem.sentence`, `faker.int_between`, `uuid.v4`, `color.hex`.

Usage

Claude Code

bash

claude mcp add faker --transport http https://free.cadenya.com/faker-mcp

Codex

bash

codex mcp add faker --url https://free.cadenya.com/faker-mcp

Claude Desktop

Add to your MCP configuration:

json

{
  "mcpServers": {
    "faker": {
      "type": "streamable-http",
      "url": "https://free.cadenya.com/faker-mcp"
    }
  }
}

curl

bash

# Initialize
curl -sS https://free.cadenya.com/faker-mcp \
  -H 'Content-Type: application/json' \
  -H 'Accept: application/json, text/event-stream' \
  -d '{"jsonrpc":"2.0","id":1,"method":"initialize","params":{"protocolVersion":"2025-06-18","capabilities":{},"clientInfo":{"name":"curl","version":"1.0"}}}'

# List tools
curl -sS https://free.cadenya.com/faker-mcp \
  -H 'Content-Type: application/json' \
  -H 'Accept: application/json, text/event-stream' \
  -d '{"jsonrpc":"2.0","id":2,"method":"tools/list","params":{}}'

# Generate fake data
curl -sS https://free.cadenya.com/faker-mcp \
  -H 'Content-Type: application/json' \
  -H 'Accept: application/json, text/event-stream' \
  -d '{"jsonrpc":"2.0","id":3,"method":"tools/call","params":{"name":"GenerateFake","arguments":{"name":"internet.email"}}}'

# Generate a PG-13 curse word
curl -sS https://free.cadenya.com/faker-mcp \
  -H 'Content-Type: application/json' \
  -H 'Accept: application/json, text/event-stream' \
  -d '{"jsonrpc":"2.0","id":4,"method":"tools/call","params":{"name":"GenerateCurseWord","arguments":{}}}'

Run Locally

bash

docker compose up --build

The MCP endpoint is available at `http://localhost:8080/faker-mcp`.

Development

Prerequisites

Go 1.24+
buf (for proto regeneration)
Docker (for local testing)

Build

bash

go build -o faker-mcp .

Test

bash

go test ./...

Regenerate Protos

bash

buf generate

Deployment

This project uses Kustomize manifests designed for ArgoCD:

bash

# Preview production manifests
kubectl kustomize k8s/overlays/production

# Apply directly (prefer ArgoCD for production)
kubectl apply -k k8s/overlays/production

The production overlay deploys to `free.cadenya.com/faker-mcp` with 2 replicas.

Architecture

code

┌─────────────────────────────────────────────┐
│ Pod                                         │
│                                             │
│  ┌──────────────┐    ┌───────────────────┐  │
│  │ faker-mcp    │    │ mcp-grpc-gateway  │  │
│  │ (gRPC :50051)│◄───│ (HTTP :8080)      │  │
│  └──────────────┘    └───────────────────┘  │
│                              │              │
└──────────────────────────────┼──────────────┘
                               │
                         Ingress (free.cadenya.com/faker-mcp)

The faker gRPC service and the MCP gateway run as a sidecar pair. The gateway uses gRPC reflection to discover the service schema and exposes it as MCP tools over HTTP.

License

MIT

Frequently asked questions

What is free-faker-mcp?

free-faker-mcp is Free MCP server for generating fake data, powered by mcp-grpc-gateway

How do I install free-faker-mcp?

Open the GitHub repository and follow its README. Most MCP servers are added to your client's MCP config, then called by your agent.

Is free-faker-mcp open source?

Yes — it is hosted on GitHub at https://github.com/cadenya/free-faker-mcp.

Related MCP tools

kubeshark

eBPF-powered network observability for Kubernetes. Indexes L4/L7 traffic with full K8s context, decrypts TLS without keys. Queryable by AI agents via MCP and humans via dashboard.

12,068 Go

kubernetesgolangrest+17

go-whatsapp-web-multidevice

GOWA - WhatsApp REST API with support for UI, Multi Account, Webhooks, and MCP, and Chatwoot. Built with Golang for efficient memory use.

4,717 Go

whatsappwhatsapp-apiwhatsapp-api-go+9

radar

The missing open-source Kubernetes UI with a built-in MCP server for AI agents. See what's broken, why, and what changed. Issues, Topology, event timeline, Helm, GitOps, live service traffic, and cluster audits - all in one Go binary.

3,246 Go

argocdcloud-nativegitops+17

mcp-language-server

mcp-language-server gives MCP enabled clients access semantic tools like get definition, references, rename, and diagnostics.

1,587 Go

ailanguage-server-protocolmcp+2

terraform-mcp-server

The Terraform MCP Server provides seamless integration with Terraform ecosystem, enabling advanced automation and interaction capabilities for Infrastructure as Code (IaC) development.

1,522 Go

matlab-mcp-server

Run MATLAB® using AI applications with the official MATLAB MCP Server from MathWorks®. This MCP server for MATLAB supports a wide range of coding agents like Claude Code® and Visual Studio® Code.

1,461 Go

engineering-toolsmatlabmcp-server+2

Run your own MCP server? See who uses it and what to fix.

Measure it with TrackMCP