Skip to main content
Glama
dmang-dev

mcp-retroarch

retroarch_load_state_current

Restore the emulator to its previously saved state by loading from the currently selected save slot. Undo changes and revert to a known baseline.

Instructions

PURPOSE: Restore the emulator from RetroArch's currently-selected save slot (one of slots 0-9). USAGE: Counterpart to retroarch_save_state_current. Use to undo a sequence of writes/inputs (the snapshot/experiment/restore workflow) or to start each tool-call sequence from a known baseline. Loads from whichever slot is currently selected (the same slot save_state_current would target). To load from a specific slot WITHOUT changing the current-slot pointer, use retroarch_load_state_slot instead — that's important if you're alternating between bookmarks. To start fresh from boot, use retroarch_reset. BEHAVIOR: DESTRUCTIVE TO LIVE STATE: replaces ALL current emulator state (RAM, registers, mapper, audio, framecount) with the slot file's contents. Anything not previously snapshotted is lost. The state file MUST come from the same ROM and same core version that produced it — loading mismatched files typically fails or destabilizes the core. FIRE-AND-FORGET: the NCI does NOT acknowledge this command — the call returns as soon as the UDP datagram is sent, with no confirmation that RetroArch received or applied it. To verify the effect, follow up with an observable tool (retroarch_get_status for run state, retroarch_read_memory / retroarch_read_ram for memory mutations, retroarch_screenshot for visual state). UDP packets to a not-listening RetroArch are silently dropped. If the currently-selected slot has no saved state, RetroArch silently ignores the command — no error is raised. To verify the load happened, follow up with a memory-read or screenshot. Transport: RetroArch's Network Control Interface (NCI) over UDP (default 127.0.0.1:55355, requires network_cmd_enable = true in retroarch.cfg). RETURNS: Single line 'Loaded from current slot' (UDP-send confirmation only — does NOT verify the slot existed or the load succeeded).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Fully details destructive behavior (replaces all state), fire-and-forget nature, silent failures, and transport requirements. No annotations provided, so description carries full burden and excels.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Well-structured with headings, front-loaded purpose, and every sentence adds value. Length is justified given complexity.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Covers all aspects: purpose, usage, behavior, verification, transport. No output schema, but description compensates fully.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

No parameters exist, but description clearly communicates that behavior relies on the currently-selected slot. Schema has 100% coverage, and description adds necessary context.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool restores emulator state from the currently-selected save slot. It uses specific verbs and resources, and distinguishes from siblings like 'retroarch_load_state_slot' and 'retroarch_reset'.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly provides when to use (undo sequence, start from baseline) and when not to use (specific slot without pointer change), along with alternative tools and verification methods.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Latest Blog Posts

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/dmang-dev/mcp-retroarch'

If you have feedback or need assistance with the MCP directory API, please join our Discord server