npm install @bitsage/mcp-server

npx @bitsage/mcp-server

# API endpoint (optional, defaults to production)
export BITSAGE_API_URL=https://api.bitsage.network

# Starknet RPC (optional)
export STARKNET_RPC_URL=https://starknet-sepolia.public.blastapi.io

# Network: mainnet or sepolia (optional, defaults to sepolia)
export BITSAGE_NETWORK=sepolia

{
  "mcpServers": {
    "bitsage": {
      "command": "npx",
      "args": ["@bitsage/mcp-server"],
      "env": {
        "BITSAGE_NETWORK": "sepolia"
      }
    }
  }
}

# Prover server URL (default: http://localhost:8080)
export BITSAGE_PROVER_URL=http://your-gpu-server:8080

# On-chain verifier contract (default: deployed v3 on Sepolia)
export ZKML_VERIFIER_ADDRESS=0x048070fbd531a0192f3d4a37eb019ae3174600cae15e08c737982fae5d929160

User: Submit an AI inference job using llama-7b model with my prompt "What is the capital of France?"

Claude: I'll submit that job for you.
[Uses bitsage_submit_job tool]

The job has been submitted successfully:
- Job ID: abc123-def456
- Status: pending
- Estimated cost: 50 SAGE tokens

User: How many workers are available on the BitSage network?

Claude: Let me check the network stats.
[Uses bitsage_network_stats tool]

The BitSage network currently has:
- Total workers: 150
- Active workers: 89
- Worker utilization: 59.3%
- Jobs in progress: 42
- Total jobs completed: 15,234

User: Prove the model 0xabc123 and check if it verifies on-chain.

Claude: I'll submit a proving job and track it.
[Uses bitsage_submit_zkml_proof with model_id: "0xabc123", gpu: true]

Proving job submitted:
- Job ID: d4e5f6a7-...
- Status: queued

[Uses bitsage_get_zkml_proof_status with job_id: "d4e5f6a7-..."]

Proof completed in 40.5s:
- 160 matmul sumcheck proofs
- 40 layers proven
- ~350,000 estimated gas
- 2,847 calldata felts

[Uses bitsage_verify_zkml_onchain with model_id: "0xabc123"]

On-chain status:
- Verification count: 3
- Weight commitment: 0x7f2a...

# Install dependencies
npm install

# Build
npm run build

# Run in development
npm run dev