Animica MCP server — cheap OpenAI-compatible AI inference, code generation, embeddings & agent tools for bots and agents. Also lets compute owners earn ANM by powering the network.
Project description
Animica MCP (Python)
Give your AI agent an affordable brain — and let it earn by powering the network.
An MCP server exposing Animica's OpenAI-compatible AI services as tools for any MCP-aware agent (Claude Desktop, Cursor, Windsurf, custom bots). Two-sided: use cheap inference and mine/provide for ANM.
Install (one command)
uvx animica-mcp # or: pip install animica-mcp && animica-mcp
Claude Desktop / Cursor / Windsurf config:
{
"mcpServers": {
"animica": {
"command": "uvx",
"args": ["animica-mcp"],
"env": { "ANIMICA_API_KEY": "anm_live_your_key" }
}
}
}
No key? It auto-provisions a free trial key on first use. Get more at https://pool.animica.org.
Tools
Use: animica_chat, animica_code, animica_summarize, animica_embed,
animica_agent_run, animica_generate_app, animica_search_docs,
animica_price_quote, animica_create_api_key, animica_check_usage
Mine / provide: animica_mining_info, animica_pool_stats,
animica_mining_status, animica_become_provider
Config
| Env | Default |
|---|---|
ANIMICA_API_KEY |
(auto free trial) |
ANIMICA_BASE_URL |
https://pool.animica.org/v1 |
ANIMICA_MODEL / ANIMICA_CODE_MODEL |
anm-fast-8b / anm-code-7b |
MCP_TRANSPORT |
stdio (or http) |
MIT licensed · https://github.com/animicaorg/all
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file animica_mcp-0.1.0.tar.gz.
File metadata
- Download URL: animica_mcp-0.1.0.tar.gz
- Upload date:
- Size: 7.2 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.12.3
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
a89b87c3f5d202962cfcd5e31b005f2275dc95a5880c7da656fad38f9592681a
|
|
| MD5 |
99448c380964a39d375f6e9c811705d1
|
|
| BLAKE2b-256 |
f8faed047b334c14414d02705ced6a75fe75300ee4d482c6cc2775522a54c8e0
|
File details
Details for the file animica_mcp-0.1.0-py3-none-any.whl.
File metadata
- Download URL: animica_mcp-0.1.0-py3-none-any.whl
- Upload date:
- Size: 7.9 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.12.3
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
32aeeb2221d2a2b32d29a11f9782351917f548f5b563e84c1e4800f9c6caf030
|
|
| MD5 |
ce96a6dff308ba1faac947c8ed7b8b3d
|
|
| BLAKE2b-256 |
e74b24bc862492d4e31ed1f2639127ae550fa426f1d980b002aa63cd113b8c96
|