Foundrynet Inference

io.github.FoundryNetPublished by GitHub account FoundryNetv1.0.1Updated Oct 24, 2026

x402 LLM proxy + data-enriched analysis (17 sources) + TimesFM predictive IoT intelligence.

VerifiedStreamable HTTPWeb executableFinanceData & AnalyticsAI & ML

Overview

AI-generated overview

A remote x402-paid inference endpoint offering an LLM proxy, data-enriched analysis, and TimesFM forecasting for IoT telemetry, billed per request in USDC.

What you can do
Send chat requests through a Claude LLM proxy endpoint, billed per call.Run data-enriched analysis where the service plans a query, consults FoundryNet servers and synthesizes an answer.Produce TimesFM breach forecasts from historical series with a threshold, plus a natural-language recommendation and attestation.Normalize IoT telemetry and return forecasts and anomaly detection.Discover routes and pricing through the x402 discovery endpoints.
When to use it
Useful when you want an assistant to call a hosted inference service for chat, enriched analysis or IoT time-series forecasting without running models yourself, and you are willing to pay per request in USDC over x402.
Requirements
Remote streamable HTTP endpoint; no local runtime or declared authentication. Requests are paid per call via x402 v2 on Solana mainnet USDC; an fnet_ Forge key can bypass payment. Forecast routes need at least 16 historical data points.
Before you install
Each call costs money: $0.02 for chat, $0.10 for predict or infer, $0.25 for analyze, settled in USDC on Solana mainnet. Queries and telemetry are sent to a third-party service. The README lists server-side secrets such as ANTHROPIC_API_KEY, HELIUS_API_KEY and PAYMENT_RECIPIENT, which are operator configuration, not client credentials.

Installation

In SourceWeft

  1. Open Foundrynet Inference in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/io.github.FoundryNet%2Ffoundrynet-inference/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "foundrynet-inference": {
      "type": "http",
      "url": "https://foundrynet-inference-production.up.railway.app/mcp"
    }
  }
}

README

FoundryNet 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.

RoutePriceWhat
POST /v1/chat$0.02Claude LLM proxy {model, messages}
POST /v1/analyze$0.25Data-enriched analysis {query} — Claude plans → queries FoundryNet servers → synthesizes
POST /v1/predict$0.10TimesFM breach forecast {canonical_field, values, threshold, oem?} + NL rec + MINT attest
POST /v1/infer$0.10IoT 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.

Source: README.md at commit 69f3a69

Tools

0
SourceWeft has not read this server's tools yet.

Version history

1
  1. v1.0.1LatestSep 16, 2026

Score

75% 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 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listedRequired15 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.