About foundrynet-inference
foundrynet-inference is an x402-gated service for Claude proxying, data-enriched analysis, and predictive IoT telemetry. It offers chat, analysis, forecasting, and inference routes, with forecasts requiring at least 16 historical points.
Key features
- 01Claude chat proxy
- 02Analysis across FoundryNet servers
- 03TimesFM threshold forecasts
- 04IoT telemetry normalization
- 05Anomaly detection and MINT attestation
Use cases
- 01Proxying chat requests to Claude
- 02Synthesizing analysis from FoundryNet data
- 03Forecasting IoT threshold breaches
- 04Normalizing telemetry and identifying anomalies
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://foundrynet-inference-production.up.railway.app/mcpclaude mcp add --transport http foundrynet-foundrynet-inference https://foundrynet-inference-production.up.railway.app/mcp{"mcpServers":{"foundrynet-foundrynet-inference":{"type":"http","url":"https://foundrynet-inference-production.up.railway.app/mcp"}}}Open in Cursor{"servers":{"foundrynet-foundrynet-inference":{"type":"http","url":"https://foundrynet-inference-production.up.railway.app/mcp"}}}Open in VS Code{"mcpServers":{"foundrynet-foundrynet-inference":{"type":"http","url":"https://foundrynet-inference-production.up.railway.app/mcp"}}}{"mcpServers":{"foundrynet-foundrynet-inference":{"serverUrl":"https://foundrynet-inference-production.up.railway.app/mcp"}}}Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.
Tools
Details
From the project READMEFoundryNet Inference
x402-gated revenue engine: LLM proxy + data-enriched analysis + predictive (IoT) intelligence.
Standard x402 v2 on Solana mainnet USDC (self-settled, Base-ready). An fnet_ Forge key bypasses.
| Route | Price | What |
|---|---|---|
POST /v1/chat | $0.02 | Claude LLM proxy {model, messages} |
POST /v1/analyze | $0.25 | Data-enriched analysis {query} — Claude plans → queries FoundryNet servers → synthesizes |
POST /v1/predict | $0.10 | TimesFM breach forecast {canonical_field, values, threshold, oem?} + NL rec + MINT attest |
POST /v1/infer | $0.10 | IoT telemetry `{telemetry:{field:value |
Discovery: GET /x402, GET /x402/:route (402 + PAYMENT-REQUIRED header), GET /.well-known/x402.
Note: /v1/predict and /v1/infer forecasts require ≥16 historical points (TimesFM constraint).
Env: ANTHROPIC_API_KEY, FORGE_API_KEY (fnet_), FORGE_BASE_URL, HELIUS_API_KEY,
PAYMENT_RECIPIENT, PAYMENT_USDC_MINT, PUBLIC_URL. Base-ready: set X402_NETWORK +
swap the facilitator in lib/x402.js for CDP/Base.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.