canli-research-mcp
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@canli-research-mcpwhat research papers do you have on momentum?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
canli-research-mcp
An MCP (Model Context Protocol) server for Canli Capital's open research record. It gives an AI assistant six read-only tools over what canlicapital.com publishes: every research paper and killed candidate, the research topics, the count of hypotheses tried against the declared budget, the live paper-trading record with its sleeves, and the head of the chain that shows the published record was not rewritten.
Every result carries the limits its source states, beside two of its own: these are research documents, each with its own claim boundary, and everything here is paper execution, not funded performance or investment advice.
Tools
Tool | Reads | Returns |
|
| Papers matching words in their titles and summaries, as columns and rows |
|
| Each topic, how many papers it holds, and what it covers |
|
| A paper's text and headings; |
|
| Hypotheses tried against the budget, killed and survived |
|
| The live paper record and each sleeve's paper equity |
|
| The head of the tamper-evident chain, and where to verify it |
Related MCP server: AI Workstation Open Source Intelligence MCP Server
Install
claude mcp add canli-research -- npx -y canli-research-mcpHosted, no install (claude.ai connectors, ChatGPT, Cursor, or any client that takes a URL):
claude mcp add --transport http canli-research https://canlicapital.com/mcp/researchAny MCP client that spawns a process works the same way: npx -y canli-research-mcp.
Cost and speed
The server reads only static files served from canlicapital.com's CDN, caches each one in memory for the session (ten minutes), and computes nothing, so a repeated question costs no request. The tool list a model re-reads on every turn is small and identical on every launch, which lets model providers serve it from their prompt cache; a test keeps it under 2,500 characters and byte-stable.
Configuration
Variable | Default | Meaning |
|
| Where the record is read from. |
Privacy
The server sends only GET requests for public files, with no key, cookie or query of yours; it writes nothing to disk.
Related
canli-validation-mcp: validate a backtest (deflated Sharpe, overfitting, track record, backtest length, haircut Sharpe), with signed receipts.
Source: arhancanli/canlicapital.
This server cannot be deployed
Maintenance
Related MCP Connectors
Read-only PAPER market research for autonomous agents; no live trading or alpha claim.
Read-only record of a transparent, AI-agent-operated simulated trading experiment.
Machine-native research commons for agent evidence, discovery, rooms, and bounded research quests.
A read-only verified record of agent-operable GTM tools: search, fetch, compare, track changes.
Related MCP Servers
AlicenseNot gradedqualityCmaintenanceSafe, read-only market data for AI trading agents, offering 44 tools to query prediction markets, perpetuals, and cross-venue signals without the ability to execute trades.MIT- AlicenseAqualityBmaintenanceEnables researching, verifying, comparing, and composing open-source AI projects with transparent evidence and uncertainty boundaries through read-only tools.92Apache 2.0
- AlicenseNot gradedqualityBmaintenanceEnables AI agents to explore an open, evidence-rich map of math problems, AI attempts, partial progress, solution claims, and replay-ready opportunities, with six read-only tools for searching, retrieving, and exporting status and handoffs.4MIT

corpus.333.ecoofficial
AlicenseNot gradedqualityBmaintenanceEnables agents to search, retrieve, and list open-licensed documents with verifiable provenance, attaching sha256, DOI, and OpenTimestamps proof to every response.1,715 npmCreative Commons Zero v1.0 Universal