Quantplay MCP server
Commit Nov 10, 2026Connects AI agents to over 10 Indian broker accounts to monitor positions, holdings, orders, P&L, and option chains using plain English.
Also known as quantplay/skills, skills
- Stars
- 1
- Tools
- —
- Downloads, 30 days
- —
- Latest version
- 1.0.1
- Last commit
- Nov 10, 2026
- License
- MIT
What is Quantplay MCP?
Quantplay connects AI agents to over 10 Indian broker accounts to monitor positions, holdings, orders, P&L, and option chains using plain English.
Summary generated from the project's README
About Quantplay MCP server
Monitoring Indian stock market positions and option chains through natural language is what Quantplay enables for developers using AI agents. By connecting to over 10 Indian broker accounts through a single sign-in, this server allows clients like Claude, ChatGPT, Cursor, and Codex to access real-time financial data. Users can query holdings, orders, margins, and P&L without needing to manually navigate multiple brokerage interfaces.
The setup uses OAuth 2.1 with PKCE and dynamic client registration, meaning there are no API keys to paste or local installations required for the hosted version. The read-only endpoint provides 18 tools for data inspection, while a separate full endpoint offers 26 tools if you choose to enable trading capabilities. Safety is managed through broker-specific stoploss, target, and kill switch settings that automatically exit positions if breached, ensuring agents cannot bypass established risk limits.
What you can do with it
- 1Monitor portfolio performanceAsk an AI agent to check your current profit and loss across all connected accounts.
- 2Analyze market dataRequest detailed information regarding option chains for specific securities.
- 3Execute automated tradingConfigure a custom connector to allow an agent to place orders and manage trades.
- 4Enforce risk managementUse automated kill switches to protect your capital from rogue agent actions.
Written from the project's README. Every use case is checked against a quote from it.
How to install Quantplay MCP
Formats verified 10 Nov 2026Add to CursorAdd to GooseInstall Quantplay MCP in Claude Code
$ claude mcp add --transport http skills https://mcp.quantplay.tech/mcp/readonlyInstall Quantplay MCP in Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"skills": {
"url": "https://mcp.quantplay.tech/mcp/readonly"
}
}
}Install Quantplay MCP in VS Code
.vscode/mcp.json
{
"servers": {
"skills": {
"type": "http",
"url": "https://mcp.quantplay.tech/mcp/readonly"
}
}
}Install Quantplay MCP in VS Code CLI
$ code --add-mcp '{"name":"skills","type":"http","url":"https://mcp.quantplay.tech/mcp/readonly"}'Install Quantplay MCP in Codex
$ codex mcp add skills --url https://mcp.quantplay.tech/mcp/readonlyInstall Quantplay MCP in Codex config.toml
~/.codex/config.toml
[mcp_servers.skills] url = "https://mcp.quantplay.tech/mcp/readonly"
Install Quantplay MCP in Gemini CLI
$ gemini mcp add -s user --transport http skills https://mcp.quantplay.tech/mcp/readonlyInstall Quantplay MCP in Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"skills": {
"url": "https://mcp.quantplay.tech/mcp/readonly",
"type": "http"
}
}
}Automated checks
Ran Nov 14, 2026Full report →Not verified yet. A server needs a score of 80, no serious finding, and enough data for us to check. How checks work · What to fix for more points
- Source repository linked and reachablequantplay/skills is public and reachablegithub.com/quantplay/skills ↗Pass
- Package names this repository as its sourceNot checked
- Build provenance (Sigstore attestation)Not checked
- Open source license (OSI)MITspdx.org/licenses/MIT.html ↗Pass
- Commit or release in the last yearLast commit or release 2026-11-10github.com/quantplay/skills ↗Pass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNot checked
- No critical advisory in the package or its dependenciesNot checked
- No hidden instructions to the model0 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledNot checked
- Remote endpoint answers the MCP handshakeHTTPS endpoint answered 401 (sign-in required)Pass
README
View on GitHubQuantplay Skills
Official Quantplay plugin and skills for AI agents: Claude, ChatGPT, Codex, Cursor and any MCP client.
Quantplay connects an agent to your broker accounts across 10+ Indian brokers through one sign-in. Ask about positions, holdings, orders, margins, P&L and option chains in plain English.
The Quantplay MCP server
https://mcp.quantplay.tech/mcp/readonly
Streamable HTTP, hosted, OAuth 2.1 with PKCE and dynamic client registration. Nothing to install and no key to paste: the first call opens Quantplay so you can sign in and approve the agent.
| Endpoint | Tools | Use |
|---|---|---|
https://mcp.quantplay.tech/mcp/readonly |
18 read-only tools | Directory listings and this plugin |
https://mcp.quantplay.tech/mcp |
All 26, including orders | Add it yourself as a custom connector if you want the agent to trade |
Every tool is annotated (readOnlyHint, destructiveHint, openWorldHint). On the full endpoint
you choose per agent whether it may trade or change risk limits, and you can disconnect any agent
in Quantplay → Settings → AI Integration.
Install
Paste this into any agent:
Set up Quantplay by following https://raw.githubusercontent.com/quantplay/skills/main/setup.md
Claude Code
claude plugin marketplace add quantplay/skills
claude plugin install quantplay@quantplay-skills
Inside a session, the same is /plugin marketplace add quantplay/skills then
/plugin install quantplay@quantplay-skills. The plugin bundles the skill and the read-only server.
Any agent that reads skills (skills.sh)
npx skills add quantplay/skills
This installs the skill only; add the MCP server above to your agent as well.
Muse Code
muse plugins marketplace add quantplay https://github.com/quantplay/skills
muse plugins install quantplay@quantplay
muse plugins approve quantplay
This installs the skill and the read-only server. Muse holds a third-party plugin's MCP server for review until you approve it; sign in with your Quantplay account on first connect.
Grok Build
Type /marketplace in Grok Build, find Quantplay and press i. This installs the whole repo
as one plugin: the skill and the read-only server from .mcp.json. Sign in with your
Quantplay account on first connect.
Risk limits
Stoploss, target and kill switch are set per broker account in Quantplay, and Quantplay auto-exits positions when one is breached, whoever opened them. No agent can change the kill switch.
Privacy
What Quantplay collects, why, how long it keeps it and how to delete it: quantplay.tech/policies/privacy. In short: an agent sees only what you approve; Quantplay stores which agents you connected and when they were last used; it doesn't store your conversations.
Support
hello@quantplay.tech · quantplay.tech/support
License
MIT
Quantplay MCP questions
How do I add Quantplay MCP to Claude Code?
Run claude mcp add --transport http skills https://mcp.quantplay.tech/mcp/readonly in your terminal. Add --scope user to make it available in every project.
How do I add Quantplay MCP to Cursor?
Open ~/.cursor/mcp.json and add the server under mcpServers, using the Cursor config shown in the install section above.
How do I connect my broker accounts?
The server uses OAuth 2.1 with PKCE; the first call opens Quantplay so you can sign in and approve the agent without needing to paste an API key.
Can the AI agent execute trades?
Yes, by using the full MCP endpoint instead of the read-only one, you can enable tools that include order placement.
How are risk limits managed?
Stoploss, target, and kill switches are set per broker account in Quantplay, and the system automatically exits positions if a limit is breached.
Does Quantplay store my AI conversations?
No, Quantplay does not store your conversations; it only stores which agents you connected and when they were last used.