MCP integration
Ask for a market.
Get one.
Pulse plugs into Claude and any MCP-compatible client, so a millisecond-resolution simulated order book is one sentence away — in the conversation you are already having.
Real output from the Pulse engine — 49 Monte Carlo runs of 700.HK on 2025-09-02, normal against flash crash. This is what comes back when you ask.
A real session, start to finish
One question, four tool calls, and a follow-up that changes the answer — connected live to the Pulse MCP server.
User: If a 3% flash crash hits 700.HK while I’m executing a 100-lot (10,000 share) sell order, would a TWAP or VWAP schedule perform better? Use 25 Monte Carlo runs so the result is more robust, and make sure the order is large enough that the schedules actually play out over the full window rather than finishing instantly.
- pulse – run_simulation (MCP)symbol: "700.HK", scenario: "flash_crash", n_runs: 25exec_algos: TWAP 100 lots over 1h from 10:00; VWAP 100 lots over 1h from 10:00Job a04a8df7 queued · 75 simulations
- pulse – check_job (MCP)75/75 complete
- pulse – get_mid_price_series (MCP)Mid-price path for one representative TWAP run and one VWAP run
- pulse – get_exec_results (MCP)Implementation-shortfall decomposition (slippage, impact, risk, in HK$) for all 25 TWAP runs and all 25 VWAP runs
At this size the schedules actually take the full hour to work through the order. Averaged across all 25 runs, TWAP and VWAP are essentially tied on slippage: impact is now the dominant cost for both, overtaking market risk for the first time — a reversal from smaller orders, where risk swamps impact. VWAP fills a little more of the order, but that edge doesn’t translate into a meaningfully cheaper average execution.
| Algo | Slippage | Impact | Risk | Filled |
|---|---|---|---|---|
| TWAP | HK$8.30 | HK$5.17 | HK$3.14 | 82.4 / 100 lots |
| VWAP | HK$8.32 | HK$5.37 | HK$2.95 | 85.5 / 100 lots |
Basically a coin flip: HK$0.02 apart per lot, well within run-to-run noise. Want me to push to a size where the two schedules are forced to trade very differently through the crash?
User: yes, try 500 lots, still with 25 Monte Carlo runs
- pulse – run_simulation (MCP)symbol: "700.HK", scenario: "flash_crash", n_runs: 25exec_algos: TWAP 500 lots over 1h from 10:00; VWAP 500 lots over 1h from 10:00Job ea6069b4 queued · 75 simulations
- pulse – check_job (MCP)75/75 complete
- pulse – get_mid_price_series (MCP)Mid-price path for one representative TWAP run and one VWAP run
- pulse – get_exec_results (MCP)Implementation-shortfall decomposition (slippage, impact, risk, in HK$) for all 25 TWAP runs and all 25 VWAP runs
Now a real gap opens up, and TWAP wins it. At 500 lots, VWAP is trying to trade in proportion to a volume curve that the crash has just torn up, and it costs VWAP on every dimension: TWAP is HK$2.45 cheaper per lot, has lower impact, and fills more of the order. Spreading evenly through the hour turns out to be more robust than chasing a volume profile that no longer reflects what’s actually happening in the book.
| Algo | Slippage | Impact | Risk | Filled |
|---|---|---|---|---|
| TWAP | HK$20.68 | HK$17.79 | HK$2.89 | 405.8 / 500 lots |
| VWAP | HK$23.13 | HK$20.09 | HK$3.05 | 371.6 / 500 lots |
Not a simple “bigger order, bigger gap” story either: at 100 lots the two algos were tied, and only past that point does TWAP’s flat schedule start to dominate.
Things people actually ask
- Run a flash crash on 700.HK
- How would my VWAP order fill?
- Give me 50 paths to backtest
- Compare TWAP against VWAP
- Does this match real markets?
- What HKEX data do you have?
No SDK to learn
The whole of Pulse — scenarios, execution algos, validation, data discovery — reachable by asking for it. No client library, no endpoint reference, no reading the docs before your first run.
It runs the real thing
These are not canned answers. Your question starts an actual simulation on Pulse's agent-based engine and the results come back into the conversation, ready to interrogate.
Stay where you work
Claude Desktop, or any MCP-compatible client. Pulse shows up as a tool your assistant already knows how to use, alongside everything else you have connected.
Three steps, then it is just conversation
- 01
Connect once
Point your client at the Pulse MCP server and authenticate with your API key. It is a few lines of configuration, once, and then you never think about it again.
- 02
Ask for a market
Describe the market you want in the words you would use to a colleague — a symbol, a day, a scenario, a size. Pulse works out which of its twenty tools to reach for.
- 03
Interrogate the results
Mid price series, execution schedules, fill quality, validation against real stylised facts. Ask a follow-up and it runs again with the parameter changed.
Twenty tools · One connection
Your next simulation starts with a sentence
Free to get started. Connect Pulse to your client and run your first market today.