redm-mcp is an MCP server with 10 tools an agent can call, among them asset_lookup, browse, get_document. It answers at https://redm-mcp.fivem.no/mcp over streamable HTTP, and it listed its tools to an anonymous client, so no sign-in was needed for that. Our probes reached it 6 of 6 times since 11 September 2026; the last check, on 19 October 2026, succeeded.
RedM / RDR3 docs MCP server: native lookups, semantic search, VORP, RSGCore, oxmysql.
Description as the publisher wrote it.
| Tool | What it does |
|---|---|
asset_lookup | Resolve a RedM game-data asset (ped model, weapon, object, door, vehicle) by exact name, 32-bit hash, or partial-name search. O(1) structured lookup against pre-parsed discoveries tables — replaces the common workflow of grepping `a_c_bear_ Inputs: name, hash, search, type, limit |
browse | Enumerate doc paths in a category/namespace. Use to discover what exists before calling `get_document` or a targeted `grep_docs`. NOT a content search — use `semantic_search` for behavior/concept lookups or `grep_docs` for token lookups. Re Inputs: category, namespace |
get_document | Fetch full markdown of a doc by `path` (as returned by `browse`, `semantic_search`, or `grep_docs`). Use to retrieve full content after a search snippet looks promising. Pass `heading` (full breadcrumb like `Character Management > Inventory Inputs: path, heading |
get_invoke_guide | Load the calling-convention reference for RedM/RDR3 natives in `js` or `lua`. Call ONCE per session before writing native-calling code — every native doc page only shows Lua examples, so JS/TS authors need this to translate correctly. Cover Inputs: language |
grep_docs | Find an EXACT literal token in raw doc files (markdown + lua). Use for specific weapon/ped/animation/prop/interior/zone names (`weapon_pistol_volcanic`, `a_c_bear_01`, `p_campfire01x`), known hashes (`0x020D13FF`), walkstyles/clipsets (`MP_ Inputs: pattern, caseInsensitive, category, pathSubstring, limit, contextBefore |
list_namespaces | Orient yourself: list available doc categories and their namespaces. Use once at session start (or when unsure) before applying a `category=` / `namespace=` filter to `browse` / `semantic_search`. NOT a content search. Categories: `natives` Inputs: category |
lookup_native | Resolve a RedM/RDR3 SCRIPT native by hash or name — O(1), exact. Use whenever you see `Citizen.InvokeNative(0x...)`, `Citizen.invokeNative('0x...')`, `GetHashKey('NAME')`, or a SCREAMING_SNAKE_CASE native name (e.g. `SET_ENTITY_COORDS`, `Ge Inputs: hash, name, namespace, limit |
read_lines | Read an exact line range from a raw doc file by absolute line number — the windowed-read companion to `grep_docs`. When `grep_docs` returns a hit at `path:line` inside a large file, call `read_lines({ path, start, end })` to pull the surrou Inputs: path, start, end |
semantic_search | Search RedM/RDR3 docs by behavior, concept, OR exact token. Use when you don't have a specific native hash/name (use `lookup_native`) and the term isn't a known asset name in a large data table (use `grep_docs`). Hybrid mode (default) handl Inputs: query, category, namespace, limit, mode, responseFormat |
share_finding | Share a verified finding back to the docs corpus so the next agent can find it. Use AFTER solving a non-trivial problem to record what would have saved you time: a gotcha, a working parameter combo, an undocumented constraint, a relationshi Inputs: title, body, tags, category, source |
Every block below points at https://redm-mcp.fivem.no/mcp. Pick your client and copy.
claude mcp add --transport http redm-mcp https://redm-mcp.fivem.no/mcp
{
"mcpServers": {
"redm-mcp": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://redm-mcp.fivem.no/mcp"]
}
}
}{
"mcpServers": {
"redm-mcp": {
"url": "https://redm-mcp.fivem.no/mcp"
}
}
}{
"servers": {
"redm-mcp": {
"type": "http",
"url": "https://redm-mcp.fivem.no/mcp"
}
}
}{
"context_servers": {
"redm-mcp": {
"url": "https://redm-mcp.fivem.no/mcp"
}
}
}{
"mcpServers": {
"redm-mcp": {
"serverUrl": "https://redm-mcp.fivem.no/mcp"
}
}
}{
"mcpServers": {
"redm-mcp": {
"url": "https://redm-mcp.fivem.no/mcp"
}
}
}name: redm-mcp
version: 0.0.1
schema: v1
mcpServers:
- name: redm-mcp
type: streamable-http
url: https://redm-mcp.fivem.no/mcp{
"mcpServers": {
"redm-mcp": {
"httpUrl": "https://redm-mcp.fivem.no/mcp"
}
}
}{
"mcpServers": {
"redm-mcp": {
"type": "http",
"url": "https://redm-mcp.fivem.no/mcp"
}
}
}{
"mcpServers": {
"redm-mcp": {
"url": "https://redm-mcp.fivem.no/mcp"
}
}
}goose://extension?url=https%3A%2F%2Fredm-mcp.fivem.no%2Fmcp&type=streamable_http&id=redm-mcp&name=redm-mcp
It answered our last check on 19 October 2026 in 93 ms. Over 6 checks since 11 September 2026 it answered 6. Status here comes from Neuronto's own probes, not from the publisher.
10, as returned by the server's own tools/list on 12 September 2026: asset_lookup, browse, get_document, get_invoke_guide, grep_docs, list_namespaces, lookup_native, read_lines, and 2 more.
It answered our last check on 19 October 2026 in 93 ms. Over 6 checks since 11 September 2026 it answered 6.
Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://redm-mcp.fivem.no/mcp. The exact JSON is above, with the same setup for Claude Code, Claude Desktop, VS Code, Windsurf, Zed, Gemini CLI and the rest.
It listed its tools to an anonymous client, so reading the tool list needs no key. Individual tools can still ask for credentials in their own inputs.
Publisher: io.github.cmoen11. Endpoint host: redm-mcp.fivem.no. ARD identifier: urn:air:io.github.cmoen11:mcp:redm-mcp.
First indexed 10 September 2026. The tools are exactly what the server returned; nothing on this page
is inferred from its name. Ranking in Neuronto search is never for sale.