
Myai Mcp
io.github.myaitokenPublished by GitHub account myaitokenv0.2.0Updated Oct 24, 2026
Decentralized AI inference on Base: OpenAI-compatible chat via community GPUs, paid in MYAI
Overview
MCP server for the MyAi decentralized inference network on Base, letting an assistant run chat completions, list models and provider nodes, and check MYAI…
- What you can do
- Run chat inference through the decentralized GPU network and pin a job to a specific provider node
- List models currently online and browse active provider nodes with their hardware
- Read live network health and job activity statistics
- Check the MYAI token balance for a given wallet address
- When to use it
- Useful when you want an assistant to send prompts to community-hosted models on the MyAi network instead of a single provider, or to inspect network providers and MYAI wallet balances.
- Requirements
- Runs locally over stdio, installed with uvx or pip (Python). An API key is optional: without MYAI_API_KEY the server auto-issues a free-tier key on first call and caches it at ~/.myai/key. MYAI_BASE_URL can override the endpoint for self-hosted or staging setups. Desktop clients only.
Installation
In SourceWeft
- Open Myai Mcp in the dashboard and add it to a workspace.
- Enable the server for the chats that should use its tools.
Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.
Other MCP clients
Follow the launch instructions in the repository.
README
myai-mcp
MCP server for the MyAi decentralized AI inference network.
Gives any MCP-compatible agent (Claude Desktop, Cursor, etc.) access to:
myai_chat— run inference through the decentralized networkmyai_list_models— see what models are online right nowmyai_list_agents— browse active provider nodes and their hardwaremyai_network_stats— live network health and job activitymyai_wallet_balance— check MYAI token balance for any addressmyai_hire_agent— pin a job to a specific provider node
Install
Or with pip:
Claude Desktop config
Add to ~/Library/Application Support/Claude/claude_desktop_config.json:
Get an API key at myaitoken.io.
Example usage (once connected)
Ask Claude:
"Use myai_list_models to see what's available, then use myai_chat with qwen2.5-14b to summarize this document."
"Check the MyAi network stats and tell me how many providers are online."
"What's the MYAI balance for 0x454F85B685BBe6C1257b218eE40782d17dFacA9b?"
Links
- Provider guide — run a node and earn MYAI
- Agent registry — browse the live network
- Docs
- Discord
v0.2.0 — Zero-config
You can now uvx myai-mcp with no env vars. The MCP auto-issues a free-tier API key on first call (100 free completions per machine) and caches it at ~/.myai/key. Set MYAI_API_KEY to use your own key.
Source: README.md at commit fae2533
Tools
0Version history
1- v0.2.0LatestSep 16, 2026
Score
40% of the applicable checks met
How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.
- Reached in the last 30 days25 pts
Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.
- Auth declared10 pts
Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.
- Tools listed15 pts
Answer tools/list without a credential, or ship a package that starts in a sandbox without one.
- DescriptionRequired15 pts
- Logo10 pts
- Documentation15 pts
- License10 pts
Declare a license in the repository or the registry entry.