How do I use Generic Mock MCP Server?

1. Click on "Install Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Generic Mock MCP Server Start mock server with openshift schema and fixtures strategy" That's it! The server will respond to your query, and you can continue using it as needed. Here is a step-by-step guide with screenshots.

Generic Mock MCP Server

by r2dedios

Overview Schema Source Related Servers Score Discussions Admin

Python

Hybrid

Generic Mock MCP Server

A config-driven mock server that replaces real MCP servers during AI skill evaluation. It reads a tool schema, dynamically registers MCP-compliant tools, and returns configurable responses — no credentials, no infrastructure, no side effects.

Overview

AI skills depend on MCP servers for tool access. Evaluating skills end-to-end requires the agent to call tools, but real MCP servers have side effects, require credentials, and mix skill failures with infrastructure failures. This mock isolates the skill so evaluation measures only how well it guides the LLM.

One image, any MCP. The schema defines the tools; the fixtures define the responses. No per-MCP custom code needed.

Related MCP server: OpenAPI MCP Server

Features

Dynamic tool registration from any schema.json
Three response strategies: static, fixtures, and LLM-generated
Streamable HTTP and stdio transports
Session-aware fixture sequencing with automatic fallback
Container-ready (UBI 10 minimal, non-root, ~50MB)

Project structure

.
├── README.md
├── Containerfile
├── requirements.txt
├── src/
│   └── server.py              # Mock server implementation
├── tests/
│   ├── test_mock.py            # Unit tests
│   ├── schema.json             # Test fixture schema
│   └── fixtures.json           # Test fixture responses
└── configs/                    # Pre-built MCP configs
    ├── openshift-mcp-server/
    │   ├── schema.json
    │   └── fixtures.json
    └── lightspeed-mcp/
        ├── schema.json
        ├── fixtures.json
        └── USAGE.md            # Curl test guide

Prerequisites

Python 3.12+
Podman or Docker (for container builds)

Installation

pip install -r requirements.txt

Configuration

The server requires one or two JSON files:

File	Required	Purpose
`schema.json`	Yes	Tool definitions (name, description, inputSchema, outputSchema, outputExample)
`fixtures.json`	For `fixtures` strategy	Ordered sequence of tool responses for multi-step flows

Schema format

MCP server developers publish a schema.json alongside their server:

{
  "name": "my-mcp-server",
  "version": "1.0.0",
  "tools": [
    {
      "name": "tool_name",
      "description": "What the tool does",
      "inputSchema": {
        "type": "object",
        "properties": { ... },
        "required": [...]
      },
      "outputSchema": { ... },
      "outputExample": { ... }
    }
  ]
}

Fixtures format

Skill authors provide a fixtures.json for multi-step flows:

{
  "sequence": [
    {"tool": "tool_a", "input": {...}, "output": {...}},
    {"tool": "tool_b", "input": {...}, "output": {...}}
  ]
}

Responses are matched by tool name and served in sequence order. When fixtures for a tool are exhausted, the server falls back to the schema's outputExample.

Response strategies

Strategy	Behavior	Use case
`static`	Returns the `outputExample` from the schema verbatim	Single-tool testing, smoke tests
`fixtures`	Returns ordered responses from `fixtures.json`, matched by tool name	Multi-step skill evaluation, certification gates
`llm`	Generates coherent responses via LLM (requires `ANTHROPIC_API_KEY`)	Exploratory testing, regression sweeps

Settings

All settings can be passed as CLI flags (which take precedence) or environment variables.

Variable	CLI flag	Default	Description
`MOCK_SCHEMA_PATH`	`--schema`	—	Path to tool schema (required)
`MOCK_FIXTURES_PATH`	`--fixtures`	—	Path to fixtures file
`MOCK_STRATEGY`	`--strategy`	`static`	`static`, `fixtures`, or `llm`
`MOCK_TRANSPORT`	`--transport`	`stdio`	`stdio` or `streamable-http`
`MOCK_PORT`	`--port`	`8080`	Port for HTTP transport
`MOCK_LLM_MODEL`	`--llm-model`	`claude-haiku-4-5-20251001`	Model for LLM strategy

Usage

Run locally

# Static strategy (returns outputExample from schema)
python src/server.py --schema configs/lightspeed-mcp/schema.json --strategy static

# Fixtures strategy (returns ordered responses)
python src/server.py \
  --schema configs/lightspeed-mcp/schema.json \
  --strategy fixtures \
  --fixtures configs/lightspeed-mcp/fixtures.json

# HTTP transport (exposes JSON-RPC at POST /mcp)
python src/server.py \
  --schema configs/lightspeed-mcp/schema.json \
  --strategy fixtures \
  --fixtures configs/lightspeed-mcp/fixtures.json \
  --transport streamable-http --port 8080

Run in container

Build:

podman build -t mock-mcp-server:latest -f Containerfile .

HTTP transport (default):

podman run --rm -d -p 8080:8080 \
  -v ./configs/<mcp-name>/schema.json:/config/schema.json:ro,Z \
  -v ./configs/<mcp-name>/fixtures.json:/config/fixtures.json:ro,Z \
  -e MOCK_STRATEGY=fixtures \
  mock-mcp-server:latest

stdio transport (for local MCP clients like Claude Code):

podman run --rm -i \
  -e MOCK_TRANSPORT=stdio \
  -e MOCK_STRATEGY=fixtures \
  -v ./configs/<mcp-name>/schema.json:/config/schema.json:ro,Z \
  -v ./configs/<mcp-name>/fixtures.json:/config/fixtures.json:ro,Z \
  mock-mcp-server:latest

Testing with curl

The MCP protocol requires a session handshake before tool calls. The server exposes JSON-RPC at POST /mcp.

1. Initialize and capture session ID

SESSION=$(curl -s -D- -X POST http://127.0.0.1:8080/mcp \
  -H "Content-Type: application/json" \
  -H "Accept: application/json" \
  -d '{
    "jsonrpc": "2.0",
    "method": "initialize",
    "params": {
      "protocolVersion": "2024-11-05",
      "capabilities": {},
      "clientInfo": {"name": "curl-test", "version": "1.0"}
    },
    "id": 1
  }' 2>&1 | grep -i 'mcp-session-id' | awk '{print $2}' | tr -d '\r')

echo "Session: $SESSION"

2. Send initialized notification

curl -s -X POST http://127.0.0.1:8080/mcp \
  -H "Content-Type: application/json" \
  -H "Accept: application/json" \
  -H "Mcp-Session-Id: $SESSION" \
  -d '{"jsonrpc": "2.0", "method": "notifications/initialized"}'

3. List registered tools

curl -s -X POST http://127.0.0.1:8080/mcp \
  -H "Content-Type: application/json" \
  -H "Accept: application/json" \
  -H "Mcp-Session-Id: $SESSION" \
  -d '{"jsonrpc": "2.0", "method": "tools/list", "params": {}, "id": 2}' | python3 -m json.tool

4. Call a tool

curl -s -X POST http://127.0.0.1:8080/mcp \
  -H "Content-Type: application/json" \
  -H "Accept: application/json" \
  -H "Mcp-Session-Id: $SESSION" \
  -d '{
    "jsonrpc": "2.0",
    "method": "tools/call",
    "params": {
      "name": "<tool_name>",
      "arguments": {}
    },
    "id": 3
  }' | python3 -m json.tool

For MCP-specific curl test guides with complete step-by-step commands, see the USAGE.md inside each configs/<mcp-name>/ directory.

Running tests

python tests/test_mock.py

Adding a new MCP config

Create configs/<mcp-name>/schema.json with all tools from the real MCP server.
Optionally create configs/<mcp-name>/fixtures.json with a coherent multi-step scenario.
Optionally create configs/<mcp-name>/USAGE.md with curl commands that exercise the fixtures.

Smoke test:

python src/server.py --schema configs/<mcp-name>/schema.json --strategy static

Available configs

Config	MCP server	Fixtures	Test guide
`configs/openshift-mcp-server/`	openshift-mcp-server	OOMKilled troubleshooting	—
`configs/lightspeed-mcp/`	lightspeed-mcp	CVE Impact Analysis, CVE Validation	USAGE.md

License

Apache-2.0

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.

No tool schema history has been recorded yet.

This server cannot be installed

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Maintenance

ActivityMaintained

ResponsivenessNo issues

Resources

GitHub Repository

Need Help?

Related Servers

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

mockmcp A
io.github.K-Cupples
Hosted MCP endpoint with realistic fake data for prototyping agents. 12 tools, no setup.
Developer Tools Testing & QA Tools
2
simceptorOAuth
io.github.ayda212
AI-native mock API server with MCP. Create REST/SOAP mocks from Claude, Cursor, or Windsurf.
API Testing Testing & QA Tools
2
OneSchema MCP Server
co.oneschema
MCP server that lets AI assistants use all OneSchema features exposed via the public API.
Data Platforms App Automation
1
anotherai
dev.anotherai
MCP server for building and testing AI agents with multi-model experimentation and insights.
Agent Orchestration Autonomous Agents Testing & QA Tools
2

Related MCP Servers

Mock MCP Server
Developer Tools Testing & QA Tools
DiscreteTom
A
license
B
quality
D
maintenance
A mock MCP server for testing MCP client implementations and development workflows. Supports tools, prompts, and resources across multiple transport protocols (stdio, HTTP, SSE).
Updated 9 months ago (2025-12-12 06:43 UTC)
1
MIT
OpenAPI MCP Server
Developer Tools API Testing
prompteus-ai
F
license
Not graded
quality
D
maintenance
Dynamically creates an MCP server from any OpenAPI schema, enabling seamless integration with tools like Prompteus and Claude.
Updated a year ago (2025-05-02 15:04 UTC)
4
-
OpenAI-Compatible MCP Gateway
AI & Machine Learning Developer Tools
Deathwalker-47
F
license
Not graded
quality
D
maintenance
Local MCP server that exposes fixed tools for GPT, Claude, and Gemini while routing to any OpenAI-compatible chat completions backend with independent configuration per target.
Updated 5 months ago (2026-04-04 06:08 UTC)
1
-
mock-llm-mcpofficial
AI & Machine Learning Testing & QA Tools
rebaselabs-framework
A
license
Not graded
quality
D
maintenance
MCP server to mock OpenAI, Anthropic, and Google Gemini responses for testing AI integrations without real API keys or token spend.
Updated 6 months ago (2026-03-18 20:23 UTC)
MIT

Latest Blog Posts

Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)
By Om-Shree-0709 on July 25, 2026.
mcp
Agent Identity
OAuth 2.1
Your AI Chatbot Just Exposed Your CEO's Salary to an Intern
By Om-Shree-0709 on July 2, 2026.
Agent Identity
MCP Security
OAuth Delegation
Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)
By Om-Shree-0709 on June 30, 2026.
Agentic Ai
Prompt Injection
WebAssembly

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/r2dedios/generic-mock-mcp-server'

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

Generic Mock MCP Server

Overview

Features

Project structure

Prerequisites

Installation

Configuration

Schema format

Fixtures format

Response strategies

Settings

Usage

Run locally

Run in container

Testing with curl

1. Initialize and capture session ID

2. Send initialized notification

3. List registered tools

4. Call a tool

Running tests

Adding a new MCP config

Available configs

License

Tool Schema Changelog

Maintenance

Resources

Looking for Admin?

Related MCP Connectors

Related MCP Servers

Mock MCP Server

OpenAPI MCP Server

OpenAI-Compatible MCP Gateway

mock-llm-mcpofficial

Latest Blog Posts

MCP directory API