consensa-mcp
An MCP server that records consented, attributed, paid-for receipts for open-source dependencies, settling per-call USDC payments on Algorand with on-chain attribution.
README
consensa-mcp
An MCP server that lets an AI agent record a consented, attributed, paid-for receipt for the open-source dependencies it consumes — settled per call in USDC on Algorand via Consensa. Each call splits payment on-chain: provider 80%, upstream maintainers' escrow 11% (per-dependency attribution), commons 7%, protocol 2%.
Tools
consensa_attribution_preview(manifest)— free. Which upstream deps would be attributed on-chain, plus the split and price. No payment.consensa_clearance(manifest)— paid. Pays USDC from the configured wallet and returns the on-chain receipt (paymentTxId,settleTxId, split, upstream).consensa_receipt(paymentTxId)— free. Look up a prior receipt.
Bring-your-own-wallet
You run this server with your own funded Algorand spend wallet
(CONSENSA_MCP_PAYER_MNEMONIC). Consensa never holds or spends your funds. Use a
dedicated, low-balance wallet, and start on Testnet.
Configure
Copy .env.example and fill it in — see that file for every variable. The payer
mnemonic must come from your environment; never commit it.
Spend guards (defaults): MAX_SPEND_USDC_PER_RUN=5.00, MAX_PER_CALL_USDC=0.02,
MAX_CALLS_PER_MIN=10, plus idempotency (identical manifest within the TTL is not
charged twice). Optionally pin CONSENSA_EXPECTED_PAYTO so the server refuses to
pay any other address.
Run (from the cloned repo)
npm install
# env below is only needed for the PAID tool; preview/receipt need no wallet.
$env:CONSENSA_NETWORK="testnet"; $env:CONSENSA_MCP_PAYER_MNEMONIC="<25 words>"
npm run dev # tsx src/index.ts (or: npm run build && npm start)
The server speaks MCP over stdio.
Use from an MCP client (e.g. Claude Desktop)
{
"mcpServers": {
"consensa": {
"command": "npx",
"args": ["tsx", "src/index.ts"],
"cwd": "/absolute/path/to/consensa-mcp",
"env": {
"CONSENSA_NETWORK": "testnet",
"CONSENSA_ENDPOINT": "https://consensa-endpoint-production.up.railway.app",
"CONSENSA_MCP_PAYER_MNEMONIC": "<your 25-word mnemonic>",
"MAX_SPEND_USDC_PER_RUN": "5.00"
}
}
}
}
Status
v0.1 MVP, validated end-to-end on Algorand MainNet (a real per-call clearance settles on-chain, with the payment split verified to the microUSDC). Bring-your-own-wallet; start on Testnet.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.