Simulate APIs, databases, MCP servers, and user personas.
Deterministic. Offline. Open source.
The Problem
Your agent depends on APIs, databases, and tools. But sandbox testing is slow, inconsistent, and incomplete.
How It Works
Point Mimic at your schema, choose a persona, and generate a fully populated local environment with consistent test data.
Declare APIs, databases, and MCP servers. Mimic reads your real schema.
LLM generates persona blueprints and expands them into realistic rows. Cached for instant reruns.
Push generated data to your configured databases. Atomic, idempotent, and fast.
Start API mocks and MCP servers locally. One server per adapter, auto-configured transport.
Flagship Example
A LangGraph supervisor agent that queries Stripe, Paddle, Chargebee, GoCardless, RevenueCat, Lemon Squeezy, Zuora, and Recurly simultaneously — plus a PostgreSQL product database — through 9 live MCP servers. Ships with a Next.js chat UI.
Architecture
The Blueprint Engine generates a persona, then adapters project that data across every system your agent uses. Same seed = identical output.
Adapters
MCP Servers
10,000+ MCP servers exist in the wild. Almost none have standardized testing infrastructure. Until now.
Our MCP servers mirror real tools — Stripe, Plaid, Paddle, Chargebee, and more. Same tool names. Same schemas.
Replace MIMIC_BASE_URL with real credentials. Your agent code stays exactly the same.
Claude Code, Cursor, VS Code Copilot, or any MCP-compatible runtime.
{
"mcpServers": {
"mimic-jira": {
"command": "npx",
"args": ["-y", "@mimicai/mcp-jira"],
"env": {
"MIMIC_BASE_URL": "http://localhost:4000"
}
},
"mimic-slack": {
"command": "npx",
"args": ["-y", "@mimicai/mcp-slack"],
"env": {
"MIMIC_BASE_URL": "http://localhost:4000"
}
}
}
}
// Swap for production — zero code changes
// "JIRA_API_TOKEN": "real-token-here"
Features
Everything you need to test AI agents in realistic environments.
One persona generates consistent data across databases, APIs, and MCP servers. Same user, matching records everywhere.
Same seed + same persona = identical data every run. No flaky tests.
High-performance database seeding with FK-aware ordering and atomic transactions.
Pre-built personas ship with the package. No LLM calls, no API keys, no internet needed.
Reads Prisma schemas, SQL DDL, or introspects live databases.
CLI, adapters, MCP servers, and personas are Apache 2.0 licensed.
CI/CD
Add three lines to your workflow. Every run produces the same environment.
Same persona + same seed = identical environment in every CI run. No drift between runs.
Local mocks start in under 2 seconds. No external network calls.
Pre-built personas work offline. No API keys or service credentials in CI.
- name: Start Mimic run: | npx @mimicai/cli run npx @mimicai/cli seed npx @mimicai/cli host --background - name: Run agent tests run: npm test env: PLAID_BASE_URL: http://localhost:4000/plaid STRIPE_API_BASE: http://localhost:4000/stripe/v1 - name: Cleanup run: npx @mimicai/cli clean
Pricing
The open-source core works without an account. Pro unlocks custom personas and advanced testing.
Install in 30 seconds. No account required. Pre-built personas ship free. Open source forever.