FiveM Enhanced MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| FIVEM_ENHANCED_MCP_CACHE_DIR | No | Local normalized source cache directory. Defaults to platform cache directory. | Platform cache directory |
| FIVEM_ENHANCED_MCP_REQUEST_TIMEOUT_MS | No | Official-source request timeout in milliseconds. Defaults to 15000. | 15000 |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
| resources | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| search_fivem_docsA | Search a focused corpus loaded from official Cfx.re documentation. Use for GTAV Enhanced resource, runtime, NUI, networking, security, and performance questions. |
| get_nativeA | Look up an exact native name or hash in official sources. The caller must provide the execution API set; unknown identifiers return not_found. |
| get_platform_capabilitiesA | Return the verified GTAV Enhanced baseline and the context that must be known before writing code. |
| get_cef_targetA | Read and parse the current CEF/Chromium build pin from the official FiveM repository. Use before choosing an NUI browser target. |
| audit_nui_compatibilityA | Load FiveM's current CEF pin, then statically audit JavaScript, TypeScript, JSX, TSX, or CSS against that verified Chromium milestone. This is a heuristic build-time review, not a runtime browser test. |
| validate_fxmanifestA | Validate supplied fxmanifest.lua text for current Enhanced-only resource rules, compiled script outputs, NUI packaging, and deprecated or experimental fields. |
| review_resource_structureA | Review a supplied resource file list against the documented FiveM requirements and this project's explicit client/server/shared/NUI house standard. |
| review_event_securityA | Perform a static heuristic review of supplied code for untrusted network input, broadcasts, unstable source usage, and event-context mistakes. |
| review_state_bag_usageA | Perform a static heuristic review for nested State Bag serialization, scope-event scaling, and client replication risks. |
| create_performance_test_planA | Create a reproducible measurement plan using profiler, resmon, network, or NUI evidence. It never claims a speedup without measurements. |
| source_healthA | Report freshness, cache state, and errors for official sources checked by this MCP process. |
| refresh_sourcesA | Explicitly refresh the local cache from allowlisted official Cfx.re and citizenfx sources. It does not modify any FiveM project or external service. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| enhanced-scope | Stable project scope and non-goals. |
| source-policy | Allowlisted source hierarchy and trust boundary. |
TDQS
Scored across 12 tools
Most tools have clearly distinct purposes: search, native lookup, platform info, CEF pin retrieval, NUI audit, manifest validation, resource structure review, security review, state bag review, performance planning, and source health. The overlap between audit_nui_compatibility and get_cef_target is minimal since one is informational and the other performs a full audit, and review_resource_structure vs validate_fxmanifest target different artifacts.
The majority of tool names follow a verb_noun pattern (search_fivem_docs, get_native, validate_fxmanifest, review_event_security, refresh_sources), but a few deviate, such as source_health (noun_verb) and audit_nui_compatibility (uses 'audit' instead of 'review'). Overall the pattern is mostly consistent and readable.
12 tools is well within the ideal 3-15 range and each tool serves a specific part of the FiveM development workflow. The count feels appropriately scoped for a specialized MCP server covering documentation, native reference, platform capabilities, code review, security analysis, performance testing, and source cache management.
The tool surface covers the core workflows for a FiveM development assistant: searching docs, looking up natives, checking platform baseline, auditing NUI compatibility, validating manifests, reviewing resource structure/security/state bags, creating performance test plans, and managing source freshness. Minor gaps exist such as no direct code generation or runtime debugging, but these are outside the apparent scope.