IBM Granite via x402

io.github.nirholasPublished by GitHub account nirholasv1.1.4Updated Oct 24, 2026

x402 pay-per-use IBM Granite AI: chat, code, embeddings, analysis, forecasting. Pay USDC per call.

The publisher's own server: Granite

VerifiedSTDIODesktop onlyFinanceAI & ML

Overview

AI-generated overview

A local MCP server that exposes IBM Granite chat, code, embedding, analysis and forecasting tools, billed per call in USDC on Solana via x402.

What you can do
Run conversational chat and code tasks (generate, review, refactor, explain, test, document) on IBM Granite models through watsonx.ai. Produce batch text embeddings for RAG, search or clustering. Analyze documents for entities, sentiment, risk flags and summaries, and run zero-shot time-series forecasts. Read a free getting-started tool that explains prices and the payment flow before any payment.
When to use it
Useful when you want Granite inference inside an MCP client without your own IBM Cloud account, and are willing to pay per call in USDC on Solana. Suited to operators who want to resell or meter Granite access to agents, or to callers whose client already handles x402 payments.
Requirements
Runs locally with Node.js 20 or newer, typically via npx. The operator must set MCP_SVM_PAYMENT_ADDRESS (a Solana wallet to receive USDC), WATSONX_API_KEY and WATSONX_PROJECT_ID or WATSONX_SPACE_ID; optional variables set region, models, facilitator and fee payer. Callers need USDC on Solana and an x402-capable client. Network access to watsonx.ai and the payment facilitator is required.
Before you install
The operator's IBM Cloud API key is held by the server and used for all inference. Every paid tool moves real USDC from the caller's Solana wallet, at prices from $0.005 to $0.05 per call, settled through a third-party facilitator that defaults to PayAI. Prompts, code and documents are sent to IBM watsonx.ai. Tools are described as read-only inference, but payments are irreversible once settled.

Installation

In SourceWeft

  1. Open IBM Granite via x402 in the dashboard and add it to a workspace.
  2. 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

[three.ws]

@three-ws/ibm-x402-mcp

Pay-per-use IBM Granite AI over MCP — chat, code, embeddings, analysis, and forecasting, billed in USDC on Solana. No IBM account required.

[npm] [downloads] [license] [node] [MCP Registry] [three.ws]

Install · Quick start · Tools · Payment flow · Requirements · three.ws


A Model Context Protocol server that exposes IBM Granite foundation models as pay-per-use tools via the x402 payment protocol. End users pay USDC on Solana per call — no IBM Cloud account of their own. The server operator supplies IBM credentials (WATSONX_*) and a receiving Solana wallet (MCP_SVM_PAYMENT_ADDRESS); callers supply only USDC. One free tool (ibm_granite_getting_started) explains prices and the flow before any payment.

Built by three.ws. Community-built and not affiliated with IBM.

How it works

  1. An MCP client (Claude Desktop, Claude Code, Cursor, or an agent) connects to this server.
  2. The client calls a tool — e.g. ibm_granite_chat.
  3. Without an x402 payment payload, the server returns a 402 PaymentRequired envelope quoting the USDC price and the Solana receiving address.
  4. The client signs a Solana USDC transfer and retries with the payment in _meta["x402/payment"].
  5. The server verifies and settles the payment via the facilitator, calls IBM watsonx.ai, and returns the result with a settlement receipt in _meta["x402/payment-response"].

x402-capable MCP clients handle this loop automatically.

Install

bash
npm install @three-ws/ibm-x402-mcp

Run it directly with npx (no install needed):

bash
MCP_SVM_PAYMENT_ADDRESS=<your-solana-wallet> \WATSONX_API_KEY=<ibm-api-key> \WATSONX_PROJECT_ID=<watsonx-project-id> \npx @three-ws/ibm-x402-mcp

Or install globally for the ibm-x402-mcp binary on your PATH:

bash
npm install -g @three-ws/ibm-x402-mcp

Quick start

Whoever runs the process is the operator: the server fails fast at startup without a payment address and IBM credentials (WATSONX_API_KEY, WATSONX_PROJECT_ID). Callers of the running server need only USDC — no IBM account. With Claude Code, one command:

bash
claude mcp add ibm-granite-x402 \  -e MCP_SVM_PAYMENT_ADDRESS=your-solana-wallet \  -e WATSONX_API_KEY=your-ibm-api-key \  -e WATSONX_PROJECT_ID=your-watsonx-project-id \  -- npx -y @three-ws/ibm-x402-mcp

Or wire the server into your MCP client config (claude_desktop_config.json, Cursor's mcp.json):

json
{	"mcpServers": {		"ibm-x402": {			"command": "npx",			"args": ["-y", "@three-ws/ibm-x402-mcp"],			"env": {				"MCP_SVM_PAYMENT_ADDRESS": "your-solana-wallet-address",				"WATSONX_API_KEY": "your-ibm-cloud-api-key",				"WATSONX_PROJECT_ID": "your-watsonx-project-id"			}		}	}}

Inspect the tool surface with the MCP Inspector:

bash
npx -y @modelcontextprotocol/inspector npx @three-ws/ibm-x402-mcp

Tools

ToolWhat it doesPrice
ibm_granite_getting_startedOverview, prices, and the x402 payment flow. No payment or IBM account required.Free
ibm_granite_chatConversational AI via IBM Granite (default ibm/granite-3-8b-instruct).$0.02 USDC
ibm_granite_codeCode generate, review, refactor, explain, test, document.$0.025 USDC
ibm_granite_embedBatch text embeddings for RAG, search, and clustering (1–64 texts).$0.005 USDC
ibm_granite_analyzeStructured document analysis: entities, sentiment, risk flags, summary, next steps.$0.04 USDC
ibm_granite_forecastZero-shot time-series forecasting via IBM Granite TTM (Tiny Time Mixer).$0.05 USDC

Every tool is a read-only model-inference call — nothing on your machine or in any account is modified — and declares MCP tool annotations (readOnlyHint, openWorldHint, idempotentHint) so clients can reason about side effects before paying.

Input parameters

ibm_granite_getting_started — section (optional: overview (default, everything) / pricing / payment / tools / setup).

ibm_granite_chat — messages (required: 1–50 { role, content } pairs; roles system/user/assistant, content ≤ 32,000 chars), model (default ibm/granite-3-8b-instruct), max_new_tokens (1–4096, default 1024), temperature (0–2, default 0.7).

ibm_granite_code — task (required: generate/review/refactor/explain/test/document), prompt (required, ≤ 16,000 chars: the description for generate, the code for everything else), language, context (≤ 4,000 chars).

ibm_granite_embed — inputs (required: 1–64 texts, ≤8000 chars each), model.

ibm_granite_analyze — document (required), analysis_type (general/contract/financial/technical/medical/sentiment, default general), language.

ibm_granite_forecast — timestamps (required: 64–1024 ISO-8601, uniform cadence, oldest first), values (required: 64–1024 numbers, same length), freq (required: pandas cadence, e.g. 1h, 1D), prediction_length (1–96), label.

Example calls

jsonc
// ibm_granite_chat{  "messages": [    { "role": "system", "content": "You are an expert data engineer." },    { "role": "user", "content": "Design a lakehouse schema for IoT sensor telemetry." }  ],  "max_new_tokens": 1024,  "temperature": 0.7}
// ibm_granite_code{ "task": "review", "prompt": "def calculate_roi(revenue, cost): return revenue / cost", "language": "Python" }
// ibm_granite_embed{ "inputs": ["enterprise data governance", "cloud-native AI pipeline", "real-time analytics"] }
// ibm_granite_analyze{ "document": "This Software License Agreement is entered into between...", "analysis_type": "contract" }
// ibm_granite_forecast  (timestamps/values must be 64–1024 points; abbreviated here){ "timestamps": ["2025-01-01T00:00:00Z", "...", "2025-03-05T00:00:00Z"], "values": [12500, "...", 13200], "freq": "1D", "prediction_length": 14, "label": "daily_revenue_usd" }

Payment flow

This server uses the x402 protocol for micropayments:

  1. Client calls a tool without payment → 402 PaymentRequired with the USDC amount and Solana address.
  2. Client builds and signs a Solana USDC transfer transaction.
  3. Client retries with the signed tx in _meta["x402/payment"].
  4. Server verifies and settles via the configured facilitator (default PayAI).
  5. Server calls IBM watsonx.ai and returns the result with _meta["x402/payment-response"] (settlement receipt).
MCP Client (Claude Desktop / Cursor / agent)       │  tools/call (with x402 payment in _meta)       ▼ibm-x402-mcp (stdio MCP server)       │  verify + settle USDC on Solana       ├──► x402 facilitator (default https://facilitator.payai.network)       │       │  inference call with IAM Bearer token       └──► IBM watsonx.ai (us-south.ml.cloud.ibm.com)                 └── IBM Granite 3 8B Instruct / Embedding / TTM

Requirements

  • Node.js >= 20.
  • A Solana wallet address to receive USDC (MCP_SVM_PAYMENT_ADDRESS).
  • IBM Cloud credentials: an API key (create one) and a watsonx.ai project id (Project → Manage → General → Project ID), or a deployment space id.

Environment variables

VariableRequiredDefault
MCP_SVM_PAYMENT_ADDRESSyes— (aliases: X402_PAY_TO_SOLANA, X402_PAY_TO)
WATSONX_API_KEYyes—
WATSONX_PROJECT_IDyes (or WATSONX_SPACE_ID)—
WATSONX_SPACE_IDalternative to WATSONX_PROJECT_ID—
WATSONX_URLnohttps://us-south.ml.cloud.ibm.com
WATSONX_MODEL_IDnoibm/granite-3-8b-instruct
WATSONX_CODE_MODEL_IDnoibm/granite-3-8b-instruct
WATSONX_EMBED_MODEL_IDnoibm/granite-embedding-278m-multilingual
WATSONX_FORECAST_MODELnoibm/granite-ttm-512-96-r2
WATSONX_TIMEOUT_MSno90000
X402_FEE_PAYER_SOLANAnothree.ws fee payer
X402_FACILITATOR_URLnohttps://facilitator.payai.network
X402_FACILITATOR_TOKENno— (Bearer token for a private facilitator)
X402_ASSET_MINT_SOLANAnocanonical Solana USDC mint

Regional hosts: us-south, eu-de, eu-gb, jp-tok, au-syd, ca-tor — e.g. https://eu-de.ml.cloud.ibm.com.

Errors

Every failure state is explicit — there is no silent fallback:

StateWhat you seeRecovery
Missing env at startupThe process exits with a one-line configuration error: … naming the missing variable (MCP_SVM_PAYMENT_ADDRESS, WATSONX_API_KEY, or WATSONX_PROJECT_ID/WATSONX_SPACE_ID).Set the variable and restart.
Unpaid call to a paid toolAn x402 PaymentRequired envelope quoting the USDC price and pay-to address — not an error; it is step 1 of the payment loop.Pay and retry (x402-capable clients do this automatically).
Invalid/underpaid paymentThe facilitator rejects verification and a fresh PaymentRequired envelope is returned; no inference runs and no funds settle.Re-sign against the quoted accepts.
IBM-side failureTool result { "ok": false, "error": "watsonx_error", "message": "…", "status": … } — IAM auth failure (bad WATSONX_API_KEY), model error, or a watsonx.ai timeout (WATSONX_TIMEOUT_MS, default 90 s).The message carries IBM's reason; check credentials, project id, and region.
Unexpected server faultTool result { "ok": false, "error": "internal_error", "message": "…" }.Retry; file an issue if it persists.
Facilitator unreachable at bootA facilitator init warning: … line on stderr; the server still starts and retries lazily on the first paid call.Check X402_FACILITATOR_URL connectivity.

ibm_granite_getting_started is always free and never touches IBM or the facilitator — use it to sanity-check the server before paying.

Related

  • @three-ws/ibm-watsonx-mcp — the same IBM Granite tools driven by your own IBM Cloud credentials (no x402, no per-call payment).

Links


Part of the three.ws SDK suite — 3D AI agents, on-chain identity, and agent payments.
Website · Changelog · GitHub

Source: packages/ibm-x402-mcp/README.md at commit c8f2cde

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

2
  1. v1.1.4LatestOct 10, 2026
  2. v1.1.3Sep 16, 2026

Score

50% 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

Other Granite integrations