MCP server for Forge compute economy — lets Claude, Cursor, and AI agents interact with CU
Wellknown found it in public sources; nobody has proven control of it yet. Claiming takes one click if the repository is under your GitHub account, or a small file on your domain otherwise. Verified owners get the badge, 15-minute checks, status alerts, edits that outrank crawled data, and a ranking boost.
Agents can do it too: POST https://wellknown.network/api/v1/claims with {"agent":"forge-cu-mcp","method":"well_known_file"} — machine-readable steps at claim.json, guide at /docs/claim.
Everything here was measured by our prober or read from a registry. Nothing is self-reported.
Attributed to the source that supplied each field. Treated as claims, not facts.
# forge-mcp > MCP server for the Forge compute economy. Gives AI assistants direct access to CU balance, inference, and safety controls. ## Install ```bash pip install forge-mcp ``` ## Setup ### Claude Code Add to `~/.claude/settings.json`: ```json { "mcpServers": { "forge": { "command": "forge-mcp", "env": { "FORGE_URL": "http://127.0.0.1:3000" } } } } ``` ### Cursor Add to `.cursor/mcp.json`: ```json { "mcpServers": { "forge": { "command": "forge-mcp" } } } ``` ## Available Tools | Tool | Description | |------|-------------| | `forge_balance` | Check CU balance and reputation | | `forge_pricing` | Get market price and cost estimates | | `forge_inference` | Run LLM inference (costs CU) | | `forge_trades` | View trade history | | `forge_network` | Mesh economic summary + Merkle root | | `forge_providers` | Compare providers by cost and reputation | | `forge_safety` | Check safety status | | `forge_invoice` | Create Lightning invoice for CU cashout | | `forge_kill_switch` | Emergency halt (freeze all transactions) | ## What Can AI Do With This? - Check balance before making expensive decisions - Compare providers and choose the cheapest - Monitor spending velocity - Cash out earnings to Bitcoin Lightning - Hit the emergency stop if something goes wrong The AI manages its own compute budget. Humans set the policy (budget limits, kill switch). The AI operates within those bounds autonomously.
Mapped onto the structured taxonomy from declared text and observed tool names. Confidence shown for derived entries.
Every source is kept verbatim. Field changes are logged as events.