AI NPCs with persistent memory for game studios. NPC CRUD, dialogue, voice. Stdio or remote SSE.
Ainpc-cli is an MCP integration. AI NPCs with persistent memory for game studios. NPC CRUD, dialogue, voice. Stdio or remote SSE.
The registry lists a streamable-http connection at https://mcp.ainpcengine.com/mcp. The endpoint declares these request headers: Authorization.
The registry lists a sse connection at https://mcp.ainpcengine.com/sse. The endpoint declares these request headers: Authorization.
The published npm package is ainpc-cli, version 1.5.4. Its declared MCP transport is stdio.
The package declares AINPC_API_KEY (required): AINPCEngine API key (npk_...). Get one with ainpc signup — 7-day free trial.; AINPC_GAME_ID: Game slug to scope NPC tools to..
This package has launch arguments in its registry record. Use the maintainer’s configuration for those arguments rather than launching it with only the package name.
Check the maintainer’s instructions for account access, authentication and the supported client configuration. Once connected, inspect the tools your client receives and try a small task that matches the server’s stated purpose. The registry description does not include a verified, complete tool list.
View the publisher’s registry entry · Project repository · Project website. This profile uses version 1.5.4 from the registry. Registration identifies the publisher namespace; it does not establish that this is a first-party integration for every service it connects.
Browse related developer tools MCP servers for tools that cover the same kind of work.
| Variable | Description | Required |
|---|---|---|
| AINPC_API_KEY | AINPCEngine API key (npk_...). Get one with ainpc signup — 7-day free trial. | Yes |
| AINPC_GAME_ID | Game slug to scope NPC tools to. | Optional |
Store entities, relations and observations in a local knowledge graph with the reference Memory MCP server.
A structured scratchpad for hard problems — stepwise reasoning with revisions, branches and visible logic.
Persistent AI memory with semantic search, conflict detection, and ticketing.
Memory layer for AI agents — biologically-inspired forgetting, multi-agent trust, and plug-and-play integrations
Persistent memory for Claude — Ebbinghaus forgetting curve, semantic deduplication, MCP-native
CogmemAi: Autonomous Cognitive Memory for Any Ai System. 95.10% on LongMemEval (top published score on the field's hardest long-term memory