✨ **AiCore** is a comprehensive framework for integrating various language models and embedding providers with a unified interface. It supports both
AiCore MCP server exists for a simple reason — assistants are far more useful when they can act on AiCore directly instead of describing what you should do. ✨ AiCore is a comprehensive framework for integrating various language models and embedding providers with a unified interface. It supports both synchronous and.
The server ships on npm as @anthropic-ai/claude-code, so your MCP client can launch it on demand — there is no separate build step. Add the server block to your client's configuration, restart it, and the tools register themselves.
Once AiCore is connected, these are the calls the assistant has available:
Method — PathGET — /healthPOST — /queryDELETE — /query/{session_id}Sync — llm_config = LlmConfig( provider="openai", model="gpt-4o", api_key="super_secret_openai_key" )Async — async def main(): llm_config = LlmConfig( provider="openai", model="gpt-4o", api_key="super_secret_openai_key" )Prerequisites — The Prerequisites tool exposed by this serverQuickstart — config = LlmConfig( provider="claude_code", model="claude-sonnet-4-5-20250929", # No api_key needed — auth is handled by the CLI )Reasoner4All — The Reasoner4All tool exposed by this serverYou will need 5 environment variables: BRAVE_API_KEY, CONFIG_PATH, CLAUDE_PROXY_TOKEN, TOOL_CALL_START_TOKEN, TOOL_CALL_END_TOKEN. The server will not start without them, which is usually why the tools fail to appear on a first run. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.
## Before you rely on it
- It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
- With 9 tools registered it takes up a noticeable share of the context window; turn it off in projects that never touch AiCore.
- Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
- MCP clients confirm each tool call by default. Leave that on until you have watched what the aicore mcp server does with a few real requests.
## Choosing this one
This sits in the AI and media services group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. AiCore's toolset — `Method`, `GET`, `POST` and 6 more — is a fair guide to whether it matches your workflow. It is maintained by BrunoV21; worth a glance at recent repository activity before you build anything load-bearing on it.
This entry was verified against AiCore's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.
| Tool | What it does |
|---|---|
| Method | Path |
| GET | /health |
| POST | /query |
| DELETE | /query/{session_id} |
| Sync | llm_config = LlmConfig( provider="openai", model="gpt-4o", api_key="super_secret_openai_key" ) |
| Async | async def main(): llm_config = LlmConfig( provider="openai", model="gpt-4o", api_key="super_secret_openai_key" ) |
| Prerequisites | The Prerequisites tool exposed by this server. |
| Quickstart | config = LlmConfig( provider="claude_code", model="claude-sonnet-4-5-20250929", # No api_key needed — auth is handled by the CLI ) |
| Reasoner4All | The Reasoner4All tool exposed by this server. |
{
"mcpServers": {
"aicore": {
"command": "npx",
"args": ["-y", "@anthropic-ai/claude-code"],
"env": {
"BRAVE_API_KEY": "your-value",
"CONFIG_PATH": "your-value",
"CLAUDE_PROXY_TOKEN": "your-value",
"TOOL_CALL_START_TOKEN": "your-value",
"TOOL_CALL_END_TOKEN": "your-value"
}
}
}
}Add to claude_desktop_config.json, then restart Claude Desktop.
| Variable | Description | Required |
|---|---|---|
| BRAVE_API_KEY | Credential the server authenticates with. | Yes |
| CONFIG_PATH | Filesystem location the server is allowed to use. | Optional |
| CLAUDE_PROXY_TOKEN | Credential the server authenticates with. | Yes |
| TOOL_CALL_START_TOKEN | Credential the server authenticates with. | Yes |
| TOOL_CALL_END_TOKEN | Credential the server authenticates with. | Yes |
Search built for AI, not humans — semantic web search that returns model-ready content, plus code context.
Answers, not links — delegate questions to Perplexity's search-grounded models and get cited responses back.
Give your assistant a voice — text-to-speech, voice cloning and audio tools from the ElevenLabs API.
Give your assistant a real code sandbox — isolated cloud VMs for actually running the code it writes.
The ML hub in your context window — search models, datasets, papers and run Spaces from the official server.
Thousands of open models on tap — run image, video and audio generation through Replicate's hosted API.