Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@fixsim-mcp Create a FIX 4.4 sandbox session and tell me when my engine logs on."
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.
An MCP server for FIXSIM, the hosted FIX protocol simulator. Add it to Claude, Cursor, VS Code, or ChatGPT and test FIX from a conversation:
"Create a FIX 4.4 test session for me, then tell me when my engine has logged on and show me the first order it sent."
Two tool families live on one endpoint:
Tools | Who | Auth |
| anyone | none. Free, anonymous, 4-hour sessions on the Developer Sandbox |
| FIXSIM customers | your FIXSIM API key, sent as an |
Hosted endpoint: https://mcp.fixsim.com/mcp (read-only variant: https://mcp.fixsim.com/mcp/readonly).
Claude Code
claude mcp add --transport http fixsim https://mcp.fixsim.com/mcp --header "x-api-key: YOUR_FIXSIM_API_KEY"Leave off --header if you only want the free sandbox tools.
Cursor / VS Code (mcp.json)
{
"mcpServers": {
"fixsim": {
"url": "https://mcp.fixsim.com/mcp",
"headers": { "x-api-key": "YOUR_FIXSIM_API_KEY" }
}
}
}Claude.ai / Claude Desktop: Customize → Connectors → Add custom connector → URL https://mcp.fixsim.com/mcp.
Choose authentication None for the sandbox. To use your own instances, add a request header x-api-key
(header support in the connector dialog is rolling out; if you do not see it, use Claude Code or Cursor for now).
Related MCP server: FIX MCP Server
Tool | What it does |
| Provision a free FIX session. Returns host, port, SenderCompID (your tag 49), TargetCompID (tag 56), BeginString, expiry. |
| Is your engine connected? |
| The FIX message log, raw and parsed. Pass |
| Working orders your engine sent in. |
| Play the exchange: |
| Fill every incoming order automatically. |
| Re-fetch the connection card. |
| End the session early. |
Sandbox limits: 100 application messages per session per day, 4-hour sessions, a handful of sessions per caller.
Tool | What it does |
| Instances your key can access. Start here. |
| Sessions on an instance: FIX version, CompIDs, role, logged-in state, sequence numbers. |
| Orders your system sent into FIXSIM, with raw FIX and audit trail. |
| Execution reports FIXSIM sent you (acks, fills, rejects). Filter by ClOrdID. |
| The reverse direction, when FIXSIM is the order sender. |
| Symbols and prices on an instance. |
| Ack, fill, partially fill, reject, cancel, expire… orders your system sent in. |
| Have FIXSIM send you a New Order Single. |
| Have FIXSIM cancel an order it sent. |
| Send any raw FIX message on a session. |
The /mcp/readonly endpoint exposes the same tools but refuses the ones that send.
Every fixsim_* call is checked against the instances your key is entitled to, and is rate-limited per key
(120 calls per minute by default).
Requires .NET 8.
dotnet run --project src/FixSim.Mcp --urls http://localhost:5199Configuration (appsettings.json or environment variables such as FixSim__BaseUrl):
Key | Default | Meaning |
|
| The FIXSIM site whose |
|
| Per-key rate limit at this server |
|
| Register the |
|
| The Developer Sandbox web app |
| empty | Shared secret sent as |
The server is stateless (Streamable HTTP), so it scales horizontally behind any load balancer.
The server is a thin client. fixsim_* tools call the public FIXSIM REST API (/v1/...) with your key; sandbox_*
tools call the Developer Sandbox's session API. Nothing is stored here beyond a one-minute cache of which instances a
key may access. Your API key is forwarded to FIXSIM on each call and never logged.
MIT
This server cannot be deployed
Run, debug, and triage tests from your IDE using natural language, no dashboard switching, no manual data transfers. The TestMu AI (formerly LambdaTest) MCP Server is a single remote server exposing four tool suites: HyperExecute — analyze your project, generate YAML configs and test runner commands, then monitor jobs and sessions. Automation — pull a TestID's details plus command, network, and console logs into one chat for instant root-cause analysis. Includes mobile app upload. SmartUI — explain pixel, layout, DOM, and perceptual changes in a visual regression run, with context-aware React/HTML/CSS fixes. Accessibility — audit any public URL or a local React app against WCAG and get ready-to-apply remediation steps. Connects over https://mcp.lambdatest.com/mcp using OAuth 2.1 — no API keys in your config. One-click install in Cursor; works with Claude, GitHub Copilot, Cline, and any MCP client. Tests execute on the TestMu AI cloud: 3,000+ browsers and 10,000+ real devices.
Trade across 22+ exchanges and brokers from any MCP-capable AI agent, no install required.
Connect AI agents to financial institution origination, analytics, and compliance workflows.
Live multi-asset market data for AI agents with provenance, starter credits, x402, and examples.
