Stresix

com.stresixPublished by stresix.comOfficial publisherv1.0.0Updated Oct 30, 2026

Load test your app on a real server from your agent. Get p95, errors and what ran out first.

VerifiedStreamable HTTPWeb executableCloud & InfrastructureDeveloper ToolsData & Analytics

Overview

AI-generated overview

Stresix runs cloud load tests on your app from an AI agent and returns p95 latency, error rates and what ran out first.

What you can do
  • Inspect a target: read a GitHub repository's port, env vars, framework, database needs and branches, or check a Docker image reference, and list connected GitHub repos.
  • Start, monitor and stop load tests: launch a run against a repo or image, poll its status, view the timeline, and stop a waiting or running run.
  • Read results: get the full report with verdict, users held, p95, errors, resource limits and recommended server size, and list past runs.
  • Manage the account: check credits, free-run availability and pricing, create a checkout link for credit packs, redeem a promo code, set the server you already host on, and send feedback on a report.
When to use it
Useful before a launch or capacity decision, when you want an agent to load test a repository or Docker image and summarize bottlenecks without writing k6 scripts. Also handy for checking whether an existing server size is enough.
Requirements
Remote MCP endpoint over Streamable HTTP; nothing to install. A Stresix account (GitHub, Google or email sign-in) and an API key created under Settings, Keys for agents, sent as an Authorization bearer header. Connecting GitHub is optional for private repositories; public repos work without it.
Before you install
Paid runs cost credits (Standard 1, Massive 3); the free Lite run is once per person. The README says a paid run requires a price-and-balance reply and an explicit confirm_spend: true after asking the user, and that keys cannot buy credits or change the account. Stopping a run mid-load is not refunded, and deleting a run permanently removes its report and measurements. The API key is shown once and should be kept secret; revoke it in Settings if exposed. Env vars passed for the app to boot may…

Installation

In SourceWeft

  1. Open Stresix in the dashboard and add it to a workspace.
  2. Connect Authorization token credentials. They are stored privately and never shown on public pages.
  3. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/com.stresix%2Fstresix/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "stresix": {
      "type": "http",
      "url": "https://stresix.com/mcp",
      "headers": {
        "Authorization": "Bearer <YOUR_TOKEN>"
      }
    }
  }
}

README

Stresix MCP server

Load test your app from Claude Code, Cursor or any MCP client before you launch.

Tell your agent "load test this app before I launch". Stresix builds your GitHub repo or Docker image on a fresh cloud server, ramps simulated users at it from a second server in the same datacenter, and hands the report back to the agent: what ran out first, p95 latency, error rate and what server size to run it on. No k6 script to write.

The server is hosted at https://stresix.com/mcp (MCP over Streamable HTTP). Nothing to install.

Setup

  1. Sign in at stresix.com with GitHub, Google or email.
  2. Open Settings, then Keys for agents, and create a key. It is shown once.
  3. Add the server to your client.

Claude Code

sh
claude mcp add --transport http stresix https://stresix.com/mcp \  --header "Authorization: Bearer YOUR_STRESIX_KEY"

Cursor (~/.cursor/mcp.json, or .cursor/mcp.json in a project)

json
{  "mcpServers": {    "stresix": {      "url": "https://stresix.com/mcp",      "headers": { "Authorization": "Bearer YOUR_STRESIX_KEY" }    }  }}

Windsurf (~/.codeium/windsurf/mcp_config.json)

json
{  "mcpServers": {    "stresix": {      "serverUrl": "https://stresix.com/mcp",      "headers": { "Authorization": "Bearer YOUR_STRESIX_KEY" }    }  }}

VS Code (.vscode/mcp.json)

json
{  "servers": {    "stresix": {      "type": "http",      "url": "https://stresix.com/mcp",      "headers": { "Authorization": "Bearer YOUR_STRESIX_KEY" }    }  }}

Tools

ToolWhat it does
start_load_testBuilds and load tests a GitHub repo URL or Docker image. Takes the port, up to 10 GET paths, a branch, env vars the app needs to boot and the run size.
get_test_statusBuilding, starting servers, or running with live users, requests per second, p95 and error rate.
get_test_reportThe verdict when the run is done: users held, p95, error rate, what ran out first, what to change and the server size to pick.

Pricing

RunLoadTarget serverCost
Lite500 users, 4 minutes2 vCPU / 4 GBFree once per person
Standard2,500 users, 10 minutes4 vCPU / 8 GB1 credit
Massive10,000 users, 15 minutes8 vCPU / 16 GB3 credits

Credits come in packs: $10 for 5, $40 for 25.

Safety

  • A paid run never starts on its own. The tool answers with the price and your balance first, and the agent has to ask you before calling it again with confirm_spend: true.
  • With no credits left, the tool says to top up at stresix.com and starts nothing.
  • Each key can start 4 runs an hour, on top of the account's daily limit, so an agent stuck in a loop cannot spend a balance.
  • Load only ever goes to the app Stresix builds, on its own server in a private network. It cannot be pointed at a live site.
  • A key can start runs and read their status and reports. It cannot buy credits or change the account. Revoke it in Settings and it stops working at once. Only a hash of each key is stored.

Example

You: load test this app before I launch, I'm on a 2 vCPU box

Agent: reads the code, finds the app listens on 3000 and that /, /api/products and /search hit the database, then calls start_load_test with the repo URL

Stresix: Started a Lite run (500 users for 4 minutes against 2 vCPU / 4 GB). This is the free run, nothing was charged.

Agent: polls get_test_status, then calls get_test_report and summarizes what ran out first and what to change.

More at stresix.com/mcp.

Source: README.md at commit 8c9b880

Tools

14

start_load_test

Start a load test

Load tests the user's app on a real cloud server and returns a run id. The target is a public or connected GitHub repository URL, or a Docker image. Lite is free once per person (500 users, 4 minutes). Standard (2,500 users, 10 minutes) costs 1 credit and Massive (10,000 users, 15 minutes) costs 3. A paid run is only started with confirm_spend set to true, and only after the user has agreed to the price. Without a tier it uses the free Lite run when the account still has it.

Parametersenvporttierpathsbranchtargetrequiredrequestsconfirm_spendcurrent_server

get_test_status

Check a load test

Where a run stands: building, starting servers, running (with live users, requests per second, p95 latency and error rate) or finished.

Parameterstest_id

get_test_report

Read a load test report

The full report of a finished run: the verdict, users held, requests per second, p95 latency and errors at each load level, what ran out first, CPU, busiest thread and memory on the server and per service, connections to the database and other dependencies, what the responses were, and which server size to pick or whether the user's own server is enough.

Parameterstest_id

get_test_timeline

Load test timeline

How a run moved over time: users, requests per second, p95 latency and error rate, averaged into a fixed number of points. Works while a run is going and after it ends.

Parameterspointstest_id

list_load_tests

List load tests

The account's runs, newest first: id, status, size, target, requests, when it ran and why it failed if it did.

Parameterslimitstatus

stop_load_test

Stop a load test

Stops a run that is waiting or running and deletes its servers. A run stopped before its servers were up uses no credit. A run stopped while the load is going is not refunded, and its report covers what was measured until then. Ask the user first.

Parameterstest_idrequired

delete_load_test

Delete a load test

Deletes a run and its report and measurements for good. A running run has to be stopped first. Ask the user first.

Parameterstest_idrequired

set_current_server

Set the server to judge against

Tells a run which server the user already hosts the app on, so the report says whether that server is enough, how close to the limit it would be and what to change. Or set recommend to true to go back to a recommended size. The report is recomputed from the stored measurements, no new run needed.

Parametersvcpulabelram_gbtest_idrecommend

send_feedback

Send feedback on a report

Tells Stresix whether a finished run's report was useful, with an optional note. Only send what the user actually said. Sending again replaces the earlier answer.

Parametershelpfulrequiredmessagetest_id

inspect_target

Inspect a repository or image

Reads a repository before testing it: the port it listens on, the environment variables the code reads, the framework, whether it needs a database, and its branches. For a Docker image it only checks the reference. Use it before start_load_test.

Parametersbranchtargetrequired

list_github_repos

List connected GitHub repositories

The GitHub repositories the user gave Stresix access to, including private ones. Public repositories work without connecting GitHub.

Takes no parameters.

get_account

Credits and account

The account's credits, whether the free Lite run is still available, whether GitHub is connected, what each run size costs and the credit packs on sale.

Takes no parameters.

buy_credits

Get a checkout link for credits

Makes a checkout link for a credit pack: Starter is 5 credits for $10, Pro is 25 credits for $40. Nothing is charged by this tool. The user opens the link and pays in their browser, and the credits arrive a minute later. Only call it when the user asked to buy credits.

Parameterspackrequired

redeem_code

Redeem a promo code

Adds the credits of a promo code to the account. Only use a code the user gave you.

Parameterscoderequired

Version history

1
  1. v1.0.0LatestOct 15, 2026

Score

100% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listedRequired15 pts
  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts