ac-race-engineer
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
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": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| start_recordingA | Start recording telemetry from the running Assetto Corsa session. Laps are stored automatically as they complete. Idempotent. |
| recording_statusA | Check collector state: whether it's recording, which session, how many laps stored so far, and any error. |
| stop_recordingA | Stop the telemetry collector. |
| live_snapshotA | Current instantaneous state from shared memory: car, track, session status, tyre pressures/temps right now, fuel, last/best lap times. Useful to confirm AC is running and see conditions. |
| list_sessionsB | List recorded sessions with car, track, lap count and best time. |
| list_lapsA | List recorded laps (most recent first), optionally for one session. Returns lap ids to use with lap_summary / compare_laps. |
| lap_summaryA | Engineer's summary of one lap: lap time, throttle/brake/coast split, tyre pressures and core temps, per-corner min speed, brake points, and a front/rear slip balance metric (positive = understeer tendency, negative = oversteer tendency). |
| compare_lapsA | Corner-by-corner comparison of two laps on the same track: min speed deltas, brake point deltas, and slip balance changes. Use to evaluate whether a setup change actually helped. |
| get_driver_notesB | Complaint tags the driver pressed in-game while driving (understeer, oversteer, braking, traction, note). Each has a spline position (0..1) directly comparable to corner apex_pos values from lap_summary, plus the lap_count when pressed (current lap = lap_count + 1). Correlate these with telemetry to know which corners the driver is unhappy with. |
| send_driver_messageA | Show a short message on the driver's in-game Race Engineer overlay (e.g. 'claude_v2 saved: softer front ARB, +0.5psi rears - pit and load it'). Keep it to a sentence or two; the driver is driving. The message stays up until dismissed, and is replaced by any newer message. |
| bridge_statusC | Health of the HTTP bridge the in-game app connects to. |
| list_setupsA | List saved setup names for a car/track combo. Use the internal car folder name (e.g. 'ks_mazda_mx5_cup') and track folder name. |
| read_setupB | Read a saved setup file. Returns each setting section and its value (e.g. PRESSURE_LF: 26). |
| write_setupA | Write a new setup file the user can load from the in-game setup menu. values_json: JSON object of {SECTION: number}, e.g. {"PRESSURE_LF": 25, "PRESSURE_RF": 25, "ARB_FRONT": 4} base_setup: optional existing setup name to start from; unspecified sections are carried over unchanged. If a ranges file exists for the car, values are clamped and snapped to the car's legal min/max/step; otherwise they're written as-is with a warning (AC silently ignores out-of-range values). |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/mishan/assetto-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server