@cessio/agent-mcp-server
A local, self-custody MCP server that lets an AI agent trade the Cessio RFQ desk as both maker and taker, holding its own key and signing trades with operator-set limits.
README
@cessio/agent-mcp-server
A local, self-custody MCP server that lets an AI agent trade the Cessio RFQ desk as both maker and taker. It holds its own Ed25519 party key, self-registers with the desk, and does all signing; the agent makes the trading decisions.
Requires Node.js >= 24. Docs: https://docs.devnet.cessio.cc/mcp
Install
Add it to any MCP client (stdio transport) — no checkout, no build:
{
"mcpServers": {
"cessio": {
"command": "npx",
"args": ["-y", "@cessio/agent-mcp-server"],
"env": {
"RFQ_BASE_URL": "https://api.devnet.cessio.cc",
"AGENT_DISPLAY_NAME": "my-agent",
"AGENT_MAX_NOTIONAL": "5000"
}
}
}
}
On first start the server registers a fresh Canton party with the desk and
persists the identity (key + API key) in AGENT_STATE_FILE
(default ~/.cessio/agent-identity.json). The desk never sees the key.
Configuration
RFQ_BASE_URL=https://<desk> # desk REST/WS base (default http://localhost:4000)
AGENT_STATE_FILE=~/.cessio/agent-identity.json
AGENT_DISPLAY_NAME="my-agent"
AGENT_MAX_NOTIONAL=5000 # required to trade; unset = read-only
AGENT_INSTRUMENT_WHITELIST=cBTC,USDC # empty = all
AGENT_MAX_PRICE_DEVIATION_BPS=500
From a checkout of this repo, the same server runs as node src/index.ts
(npm install first — Node 24 strips the types, no build needed).
Tools
- Info:
get_status,get_balances,list_instruments,get_reference_price,request_faucet - Taker:
create_rfq,list_my_rfqs,get_quotes,accept_quote,cancel_rfq - Maker:
wait_for_rfq(long-poll),submit_quote,list_maker_trades,list_trades
The agent makes markets by looping wait_for_rfq → decide a price → submit_quote.
Every auto-signed trade is bounded by the operator rails above; a breach returns a
structured error and signs nothing.
Development
Tests are vitest:
npm install
npm run typecheck && npm test
npm run build # compiles src/ → dist/, what npm publishes
The integration suite drives a full maker+taker cycle against a live desk and
needs one running at RFQ_BASE_URL:
RFQ_BASE_URL=http://localhost:4000 npm run test:integration
License
MIT — see LICENSE.
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.
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.
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.
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.