Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add gatling/gatling-ai-extensions --skill gatling-mcpgit clone --depth 1 https://github.com/gatling/gatling-ai-extensionsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/gatling/gatling-ai-extensions/gatling-mcp)<a href="https://agentmods.dev/skills/gatling/gatling-ai-extensions/gatling-mcp"><img src="https://agentmods.dev/badge/skills/gatling/gatling-ai-extensions/gatling-mcp/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/gatling/gatling-ai-extensions/gatling-mcp"><img src="https://agentmods.dev/badge/skills/gatling/gatling-ai-extensions/gatling-mcp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00064 | $0.01727 |
| Opus 5 | $0.00032 | $0.00864 |
| Sonnet 5 | $0.00013 | $0.00345 |
| Haiku 4.5 | $0.00006 | $0.00173 |
Grade A, and why
gatling-mcp scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
Never call the Gatling Enterprise API directly (v1 or v2, via `curl`, a raw HTTP request, or any tool other than these MCP tools), even as a fallback when an MCP tool call fails. Always go through these MCP tools, and re How it starts
The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Gatling MCP
The tool schemas define valid request shapes. Check each tool's own description directly rather than assuming from a sibling (e.g. read vs. write variants of the same resource aren't guaranteed to share a role floor, and a location's listing doesn't expose all of its capabilities).
Never call the Gatling Enterprise API directly (v1 or v2, via curl, a raw HTTP request, or any tool other than these MCP tools), even as a fallback when an MCP tool call fails. Always go through these MCP tools, and report failures to the user instead of working around them.
Tools
There is no packages.create_one / packages.delete_one: packages can only be produced by actually building and uploading an artifact, never through this MCP.
If a build-tool skill/integration for packaging (e.g. one that drives the Enterprise Maven/Gradle/sbt/npm plugin's package goal) is available in the environment, prefer it over telling the user to do this by hand. This holds even if a hypothetical packages.create_one existed, since packaging is fundamentally a build step an API call can't substitute for.
Terminology
- Test: a saved, runnable definition of what to run (
source), where (distribution.loadGenerators), and under what conditions to stop (execution.stopCriteria). Running it produces a run. - Source, on a test, is one of:
build_from_sources:sourceRepositoryId+buildTool(maven,maven-wrapper,gradle,gradle-wrapper,sbt,npm, orcustomwith an explicitcommand/packageFormat) +simulation(fully-qualified class/id), optionalbranch/workingDirectory. Built fresh from git on every run. Prefer one of the named build tools overcustomwhenever the project actually uses one of them.custommeans hand-specifying the build command and output format, which is more error-prone and should be a fallback, not a default.packaged:packageId+simulation. Runs a pre-built artifact as-is.
- Source repository: a registered git remote (
remote.url) a test can build from. Metadata only (name/URL): auth (deploy key, PAT) isn't settable viacreate_one's schema, so private repos likely still need credentials configured through Control Plane Builders. - Package: a pre-built artifact (
_format:jvmorjs) uploaded outside the MCP. - Location, in
distribution.loadGenerators[].locationId: either a plain managed location name (a Gatling-hosted public region, e.g."Europe - Paris") or a private locationid(starts withprl_). Same field, two different ID spaces. A private location'sartifactFormatsmust include the format of what you're running (ajvm-only location can't run ajspackage/build). - Team: the ownership/permission boundary. Every package, source repository, and test belongs to a team; roles are granted per team.
- Roles: granted per team, not globally. Having Configure on one team says nothing about another. At least Read, Configure, and Start appear across these tools as distinct levels; don't assume one implies another.
- Credits: consumed by
tests.start_one(an actual run), not by any create/patch/delete/read call. Those only touch definitions or return data.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 66 lines · 64 tokens per session scan A c6f83e8bcf74
gatling-mcp is a skill published in the GitHub repository gatling/gatling-ai-extensions (5 stars, last pushed 2d ago), licensed Apache-2.0. It adds 64 tokens to every session and 1,727 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
review-prs
Review a GitHub pull request in the googleapis/mcp-toolbox repo against the team's reviewer checklist: PR title/description conventions, linked issue, logic errors and unhandled edge cases, breaking changes, test coverage, docs updates, security (input handling), and new dependencies. Use whenever a maintainer asks…
reproduce-bug
Reproduce a reported bug in googleapis/mcp-toolbox and decide whether it is real, delivering an evidence-backed verdict: confirmed, already fixed, misconfiguration, client-side, works as intended, not reproducible, or blocked. Use whenever a maintainer asks you to reproduce, verify, confirm, or investigate a bug…
fix-failing-tests
Diagnose a failing test in the googleapis/mcp-toolbox repo and land a fix by reasoning from the actual error: read the failure, reproduce it, shrink it until the cause is forced into the open, then fix the cause. Use this whenever a test or CI job is red, a build breaks after a change, many packages fail at once, or a…
tool-abuse-detection
Detect tool misuse and unexpected code execution via dialogue testing. Use when the agent exposes file, code-execution, or network tools.
dev-browser
Browser automation with persistent page state. Use when users ask to navigate websites, fill forms, take screenshots, extract web data, test web apps, or automate browser workflows. Trigger phrases include "go to [url]", "click on", "fill out the form", "take a screenshot", "scrape", "automate", "test the website"…
langbot-testing
Test LangBot WebUI and core product flows with an automated browser and backend logs. Use when validating the configured LangBot frontend, pipeline Debug Chat, model provider setup and test buttons, bot and knowledge-base UI flows, or troubleshooting failed LangBot end-to-end tests.