
RPScripts MCP server
Which MCP servers are RPScripts's own, from the official registry and from asking its own domain, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.
read 2026-10-28
- Registry namenet.rpscripts/fivemverified in the MCP registry
The registry name sits under rpscripts.net. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.
- Stateanswerschecked 2026-10-28
- Tools13
- Server calls itselfrpscripts
- Server version2.0.0
- Protocol version2025-06-18
On 2026-10-28 the server answered initialize and tools/list without a sign-in. First answer in 532 ms.
- Whether its tools do the product's job has not been judged yet.
Once connected
- For "Download ready-made FiveM scripts for ESX or QBCore servers", the likely first call is search_products.
- Parameters are untyped or undescribed in 8 of 12 tools: check arguments before calling.
Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.
- INITE MCP score96 of 100answers 100 · definitions 89 · context 97 · connects 100
- Answered100% of days7 of 7 daily checks
- Median first answer563 ms
- Space in an agent's context≈ 3,324 tokensthe definitions of all its tools (12), which an agent carries on every turn
- Tool definitionsB · 89 of 100
- Typed results0 of 12 toolsdeclared outputSchema: results come typed, read once
- Parameters without a description: in 8 of 12
What an agent can do with it
- can do · Download ready-made FiveM scripts for ESX or QBCore servers
- not sure · Generate a custom FiveM script from a written description
- not sure · Install police, hospital or other MLO map interiors
Each of the product's use cases, put to Jev against this server's tool list: can an agent do it with these tools?
Worth a look
None of the five warning signs in these definitions.
A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (25%), doing the product's job (25%), definitions (20%), context (10%), use (10%) and how readily a client connects (10%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →
search_productsSearch the RPScripts catalogue of FiveM scripts, MLOs, server packs, vehicles and assets. Filter by framework, category and USD price; results are ranked by relevance when a query is given, otherwise by popularity. Only published, listed…
get_productDetails of one RPScripts product by slug (from search_products): description, frameworks, version, categories, price, whether it can be bought, and install requirements from RPScripts Lab's static check of the download (dependencies…
list_categoriesAll RPScripts shop categories (scripts by framework and job, MLOs, vehicles, clothing, server packs …) with their paths and URLs.
check_compatibilityChecks whether an RPScripts product (by slug) or your own resource files fit a server: framework (QBCore, Qbox, ESX, vRP, standalone), required resources such as ox_lib, ox_inventory, ox_target or oxmysql, FXServer artifact and game build…
validate_resourceStatically checks a FiveM resource: Lua syntax, fxmanifest.lua directives and referenced files, resource structure, undeclared dependencies, framework API calls against pinned QBCore/Qbox/ESX versions, unknown natives, net-event security…
search_docsSearches RPScripts documentation (installation, downloads, server packs, updates, QBCore/Qbox/ESX guides, compatibility, troubleshooting, AI workflow) and the framework API reference RPScripts reads from pinned QBCore, Qbox, ESX, ox_lib…
validate_server_cfgParses and checks an FXServer server.cfg: syntax, argument counts and values, duplicate or conflicting settings, repeated resource starts, framework and ox resource start order, missing dependencies, OneSync/slot conflicts, secrets…
generate_fxmanifestGenerates a valid fxmanifest.lua (fx_version 'cerulean', game 'gta5') for client/server/shared Lua or JS scripts, NUI pages, maps, vehicle data files and dependencies, then validates it with the RPScripts manifest rules. Lua 5.4 is the…
create_jobGenerates a complete job resource with the RPScripts Jobs Creator for QBCore, Qbox or ESX: job definition and grades with salaries and boss flags, duty, stash, garage, armory, shop, crafting, harvest/process/sell, boss office, wardrobe…
lookup_serverLooks up a public FiveM server by cfx.re join code/link (e.g. cfx.re/join/abc123) or public host:port. Returns what the server or the Cfx server list publishes: hostname, player count, slots, artifact/build, OneSync, tags, public…
list_purchasesLists the RPScripts products the signed-in customer owns (active purchases, including bundle items): product id, name, product page, files with their index for get_download_url, download availability and install requirements. Requires…
get_download_urlCreates a signed download link for one file of a product the signed-in customer owns (from list_purchases). The link is personal, works for 5 minutes and counts toward the limit of 20 downloads per product per day. Requires signing in.
generate_scriptBuilds or changes a FiveM resource with the RPScripts AI generator (QBCore, Qbox, ESX or standalone): the agent writes Lua/NUI files, checks them (syntax, manifest, framework API) and repairs problems. Uses the signed-in customer's AI…
How to connect
Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:
{
"mcpServers": {
"fivem": {
"type": "http",
"url": "https://rpscripts.net/mcp"
}
}
}Add it
Claude Code, in a terminal
claude mcp add --transport http rpscripts https://rpscripts.net/mcpclaude.ai, ChatGPT and other clients: add https://rpscripts.net/mcp as a custom connector in the settings.
Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.
Before we count this visit
Analytics and ad measurement tell us which pages and which of our ads do their job: Google Analytics and Google Ads, the Meta pixel, Yandex Metrica, and one first-party id of our own. Nothing is stored until you answer, and declining changes nothing about the site.