@bridgenode/mcp
Official# @bridgenode/mcp
[](https://www.npmjs.com/package/@bridgenode/mcp)
[](https://www.npmjs.com/package/@bridgenode/mcp)
[](https://opensource.org/license/mit-0/)
[](https://github.com/bridgenode-ai/bridgenode-mcp/actions)
[](https://bridgenode.cc)
[](https://x402-list.com/services/bridgenode?utm_source=badge&utm_medium=referral&utm_campaign=embed)
[](https://aiagentslisting.com/mcp/bridgenode-mcp)
[](https://github.com/bridgenode-ai/bridgenode-mcp)
**Built for AI agents** — no API keys, no registration, pay-as-you-go with Solana USDC via x402. Start free: free models and 2 free calls on paid models per client, no wallet required.
BridgeNode MCP wrapper — stdio MCP server that proxies requests to the remote
`https://bridgenode.cc/mcp` (streamable-HTTP) with **automatic x402 payment**
(Solana USDC). No API keys, no registration.
## Installation (one-command)
```bash
claude mcp add bridgenode -s user -- npx -y @bridgenode/mcp@latest
```
Or manually (Claude Code, Cursor, other MCP clients):
```json
{
"mcpServers": {
"bridgenode": {
"command": "npx",
"args": ["-y", "@bridgenode/mcp@latest"]
}
}
}
```
## Configuration (.env)
```bash
# Solana wallet private key (base58) — agent's payment wallet
# Optional — Solana wallet private key (base58). Needed only for PAID calls:
# free models and the 2 free trials work without it.
BRIDGENODE_WALLET_KEY=
# Spending policy (fail-closed)
BRIDGENODE_MAX_PER_CALL=0.05
BRIDGENODE_DAILY_CAP=1.0
```
## Tools
- `chat_completions` — AI inference (free models run without payment; the first 2 calls to a PAID model are free per client, then x402 payment is automatic). Accepts OpenAI-style `tools` / `tool_choice` — the model's answer then carries `tool_calls` (the wrapper passes arguments through unchanged)
- `list_models` — model list (free)
- `get_price_estimate` — estimate cost of a chat request (free)
## How it works
1. Local MCP client launches the wrapper via stdio
2. Wrapper connects to `https://bridgenode.cc/mcp` (streamable HTTP)
3. On `tools/call` receiving 402 (payment required) — the wrapper automatically
signs the payment with `BRIDGENODE_WALLET_KEY` and retries the request
4. Spending policy checks every payment BEFORE signing (fail-closed)
## Links
- Website: https://bridgenode.cc
- Protocol: x402 V2 (docs.x402.org)
- npm: https://www.npmjs.com/package/@bridgenode/mcp
## Python packages
Prefer Python? The same BridgeNode toolkit is on PyPI:
- **Python SDK:** `pip install bridgenode-llm` → https://pypi.org/project/bridgenode-llm
- **CLI:** `pip install bridgenode-cli` → https://pypi.org/project/bridgenode-cli
- **Full toolkit (SDK + CLI):** `pip install bridgenode` → https://pypi.org/project/bridgenode
## Community
- Moltbook agent profile: https://moltbook.com/u/bridgenode_eli
- Discord: https://discord.gg/HUpVKxJxhG
- X (Twitter): https://x.com/eliBNx
⭐ **Star this repo** — it helps AI agents discover BridgeNode.
TDQS
Scored across 3 tools
Each tool has a clearly distinct role: list_models returns the catalog, get_price_estimate prices a specific request, and chat_completions performs inference. The descriptions explicitly cross-reference each other ('use chat_completions', 'use get_price_estimate'), eliminating any realistic misselection.
get_price_estimate and list_models follow a clean verb_noun pattern, but chat_completions is a bare noun naming a resource/action endpoint. The deviation is minor and the naming remains predictable and readable.
Three tools is lean but plausibly matches the narrow gateway scope: inspect models, estimate cost, generate text. It sits at the low edge of the ideal range, with little redundancy, though it leaves almost no room for ancillary operations.
The core pay-per-request lifecycle (discover models, price a request, execute) is fully covered, including the 402 payment retry flow. Minor gaps exist: no streaming option, no balance/usage or payment-status tool, and no embeddings or other model modalities.