Stresix MCP server
com.stresix/stresixstresix.comstreamable-httpv1.0.0Scanned
Load test your app on a real server from your agent. Get p95, errors and what ran out first.
14 tools: 2 can delete or cancel things, 1 do something that can't be undone, 4 change things and 7 only read.
- Reads private data · 3
- Reads text others write · 5
- Can send data out · 1
- No findings
Sign-in required, no OAuth metadata. Remote posture
Anlyon alternative
7 of these tools change something. Run those as governed actions.
Declare what an action changes, and Anlyon puts it under a shared limit, binds every approval to the exact request, and grades the outcome. It works on any HTTPS API you can describe as an action.
Anlyon Radar does not run, proxy or govern this MCP server. A tool your own code calls directly is not routed through Anlyon and is not governed by it.
Import an OpenAPI spec →What the Stresix MCP server can do
The Stresix MCP server is published by stresix.com, a domain the MCP Registry verified. It has 14 tools. It can delete or cancel things (2 tools: stop_load_test and delete_load_test), do things that cannot be undone, such as sending, paying or publishing (send_feedback) and create or change data (4 tools: start_load_test, set_current_server, buy_credits and redeem_code). 7 tools only read.
3 tools read private data (get_test_report, inspect_target and list_github_repos); 5 tools bring in text other people can write (start_load_test, get_test_report, inspect_target and 2 more); 1 tool can send data out of your system (send_feedback). On its own it has all three parts of a prompt-injection exfiltration path: private data, text others write, and a way out.
None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.
Last scanned Oct 21, 2026, version 1.0.0.
Tools
Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.
14 tools
Deletes or cancels 2Claude Code: deny
delete_load_testDeletes a run and its report and measurements for good.No findings
Why it is in this group
- The name "delete_load_test" says "delete": a word for removing or ending something.
- The server marks it destructive (destructiveHint: true).
Description, as the server wrote it Deletes a run and its report and measurements for good. A running run has to be stopped first. Ask the user first.
Annotations the server declares
- title: Delete a load test
- readOnlyHint: false
- destructiveHint: true
- idempotentHint: true
- openWorldHint: false
stop_load_testStops a run that is waiting or running and deletes its servers.No findings
Why it is in this group
- The name "stop_load_test" says "stop": a word for a change.
- The server marks it destructive (destructiveHint: true).
Description, as the server wrote it 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.
Annotations the server declares
- title: Stop a load test
- readOnlyHint: false
- destructiveHint: true
- idempotentHint: true
- openWorldHint: false
Can't be undone 1Claude Code: ask
send_feedbackTells Stresix whether a finished run's report was useful, with an optional note.Can send data outNo findings
Why it is in this group
- The name "send_feedback" says "send": a word for sending, and what is sent cannot be taken back.
What it can reach
- outboundThe name "send_feedback" says "send": it sends or publishes something to other people.
Description, as the server wrote it 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.
Annotations the server declares
- title: Send feedback on a report
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
Changes things 4Claude Code: ask
buy_creditsMakes a checkout link for a credit pack: Starter is 5 credits for $10, Pro is 25 credits for $40.Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it 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.
Annotations the server declares
- title: Get a checkout link for credits
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
redeem_codeAdds the credits of a promo code to the account.No findings
Why it is in this group
- The description's first verb is "add": a word for a change.
- The input takes a statement or command to run (input.code), which can change anything it can reach.
Description, as the server wrote it Adds the credits of a promo code to the account. Only use a code the user gave you.
Annotations the server declares
- title: Redeem a promo code
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: false
set_current_serverTells 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.No findings
Why it is in this group
- The name "set_current_server" says "set": a word for a change.
Description, as the server wrote it 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.
Annotations the server declares
- title: Set the server to judge against
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
start_load_testLoad tests the user's app on a real cloud server and returns a run id.Reads text others writeNo findings
Why it is in this group
- The name "start_load_test" says "start": a word for a change.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it 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.
Annotations the server declares
- title: Start a load test
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
Only reads 7Show 7 read-only tools
get_accountThe 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.No findings
Why it is in this group
- The name "get_account" says "get": a word for reading.
Description, as the server wrote it 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.
Annotations the server declares
- title: Credits and account
- readOnlyHint: true
- openWorldHint: false
get_test_reportThe 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 th…Reads private dataReads text others writeNo findings
Why it is in this group
- The name "get_test_report" says "get": a word for reading.
What it can reach
- private-dataThe description's first sentence says "thread": it reads messages.
- untrusted-inputThe description's first sentence says "thread": it reads messages, which other people can write.
Description, as the server wrote it 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.
Annotations the server declares
- title: Read a load test report
- readOnlyHint: true
- openWorldHint: false
get_test_statusWhere a run stands: building, starting servers, running (with live users, requests per second, p95 latency and error rate) or finished.No findings
Why it is in this group
- The name "get_test_status" says "get": a word for reading.
Description, as the server wrote it Where a run stands: building, starting servers, running (with live users, requests per second, p95 latency and error rate) or finished.
Annotations the server declares
- title: Check a load test
- readOnlyHint: true
- openWorldHint: false
get_test_timelineHow a run moved over time: users, requests per second, p95 latency and error rate, averaged into a fixed number of points.No findings
Why it is in this group
- The name "get_test_timeline" says "get": a word for reading.
Description, as the server wrote it 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.
Annotations the server declares
- title: Load test timeline
- readOnlyHint: true
- openWorldHint: false
inspect_targetReads 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.Reads private dataReads text others writeNo findings
Why it is in this group
- The name "inspect_target" says "inspect": a word for reading.
What it can reach
- private-dataThe description's first sentence says "read" and "repository": it reads repositories.
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it 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.
Annotations the server declares
- title: Inspect a repository or image
- readOnlyHint: true
- openWorldHint: true
list_github_reposThe GitHub repositories the user gave Stresix access to, including private ones.Reads private dataReads text others writeNo findings
Why it is in this group
- The name "list_github_repos" says "list": a word for reading.
What it can reach
- private-dataThe name "list_github_repos" says "list" and "repo": it reads repositories.
- private-dataThe description's first sentence says "repository": it reads repositories.
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it The GitHub repositories the user gave Stresix access to, including private ones. Public repositories work without connecting GitHub.
Annotations the server declares
- title: List connected GitHub repositories
- readOnlyHint: true
- openWorldHint: true
list_load_testsThe account's runs, newest first: id, status, size, target, requests, when it ran and why it failed if it did.No findings
Why it is in this group
- The name "list_load_tests" says "list": a word for reading.
Description, as the server wrote it The account's runs, newest first: id, status, size, target, requests, when it ran and why it failed if it did.
Annotations the server declares
- title: List load tests
- readOnlyHint: true
- openWorldHint: false
This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.
Exfil surface
Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.
15 paths in this server alone from private data, through text someone else wrote, to a way out. Denying 1 outbound tool breaks every one.
- Reads private data3
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write5
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out1
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
{
"permissions": {
"deny": [
"mcp__stresix__send_feedback"
]
}
}Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.
Remote posture
What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.
Looked at Nov 20, 2026, 18:47 UTC, unchanged since Oct 29, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- yes
- HTTP status of an anonymous initialize
- 410
- tools/list served without credentials
- no
- Tools that change things, listed without credentials
- 0
- Protocol version
- not observed
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- not observed
- Authorization servers
- not observed
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- not observed
- Client ID metadata documents
- not observed
The probe stopped: initialize answered HTTP 410.
Posture changes
- Oct 29, 2026
- HTTP status of an anonymous initialize: 200 to 410
- tools/list served without credentials: yes to no
- Tools that change things, listed without credentials: 7 to 0
- Protocol version: 2025-06-18 to none
Findings
Matches of fixed checks, with the text they matched.
No check matched anything in these tool definitions. That is not a safety guarantee.
History
Changes to its tool definitions and to its remote endpoint, newest first.
PostureRemote posture changed. HTTP status of an anonymous initialize: 200 -> 410; tools/list served without credentials: yes -> no; Tools that change things, listed without credentials: 7 -> 0 (and 1 more).View diff
- HTTP status of an anonymous initialize: 200 to 410
- tools/list served without credentials: yes to no
- Tools that change things, listed without credentials: 7 to 0
- Protocol version: 2025-06-18 to none
Install
Pinned to version 1.0.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http stresix https://stresix.com/mcp --header 'Authorization: <your-authorization>'claude mcp add --transport http stresix https://stresix.com/mcp --header 'Authorization: <your-authorization>'Run in a terminal.
Claude Code permissions
Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.
{
"permissions": {
"allow": [
"mcp__stresix__get_test_status",
"mcp__stresix__get_test_report",
"mcp__stresix__get_test_timeline",
"mcp__stresix__list_load_tests",
"mcp__stresix__inspect_target",
"mcp__stresix__list_github_repos",
"mcp__stresix__get_account"
],
"ask": [
"mcp__stresix__start_load_test",
"mcp__stresix__set_current_server",
"mcp__stresix__send_feedback",
"mcp__stresix__buy_credits",
"mcp__stresix__redeem_code"
],
"deny": [
"mcp__stresix__stop_load_test",
"mcp__stresix__delete_load_test"
]
}
}Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as stresix. Review it before you use it.
Capability tags behind 6 rules
- mcp__stresix__start_load_test untrusted-input
- mcp__stresix__get_test_report private-data, untrusted-input
- mcp__stresix__send_feedback outbound
- mcp__stresix__inspect_target private-data, untrusted-input
- mcp__stresix__list_github_repos private-data, untrusted-input
- mcp__stresix__buy_credits untrusted-input
Pin
Keep the decision: fail CI when the tools change, follow every change, or show a badge.
Pin in CI
Fail a build when the tools you reviewed are not the tools the server serves today.
curl -s "https://radar.anlyon.com/api/v1/servers/com.stresix/stresix/verify?hash=ea5f9a080a561cd3dc4029cc019a9d8d6f7b3dfd813c9ec4ef0a6d71b8313ce3" | jq -e '.changed == false'Pinned hash ea5f9a080a56, from Oct 21, 2026, 18:36 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/com.stresix/stresix/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/com.stresix/stresix)Source: MCP Registry · repository. Synced Oct 21, 2026, 18:05 UTC.
Stresix MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the Stresix MCP server safe?
- No scan can promise that. What its definitions show: 14 tools, 7 of which can change, send or delete something, and 0 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the Stresix MCP server delete data?
- Yes. 2 tools can delete, cancel or revoke something: stop_load_test and delete_load_test.
Can the Stresix MCP server do things that cannot be undone?
- Yes. 1 tool can send, pay, publish or merge: send_feedback.
What tools does the Stresix MCP server have?
- 14 tools: 2 destructive, 1 irreversible, 4 write, 7 read. stop_load_test, delete_load_test, send_feedback, start_load_test, set_current_server, buy_credits, redeem_code, get_test_status and 6 more.
Does the Stresix MCP server need sign-in or OAuth?
- Its remote endpoint did not answer the last anonymous look.
Does the Stresix MCP server send data to outside services?
- 1 tool can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): send_feedback.
Has the Stresix MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Oct 21, 2026.