Finance Trading AI AgentsSAFE
A comprehensive, free MCP server designed specifically for financial analysis and quantitative trading. This specialized platform offers one-click local deployment with a sophisticated department-based architecture that mirrors real financial company operations.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
[](https://badge.fury.io/py/finance-trading-ai-agents-mcp) [](https://pypi.org/project/finance-trading-ai-agents-mcp/) [](https://opensource.org/licenses/MIT)
A free, professional, open-source financial analysis and quantitative trading MCP server. It lets you deploy a local financial MCP service with one command, using a departmental architecture that simulates a real financial firm's operations. It supports traditional indicators, price action analysis, economic calendar, fundamentals, and news integration—providing seamless interaction with LLMs and algorithmic trading.
💬 Community & Support
[](https://docs.aitrados.com/wechat_group.png) [](https://discord.gg/aNjVgzZQqe)
Join our community for discussions, support, and updates!
✨ Features
- 🚀 One-click deployment: Quickly spin up a local financial MCP service
- 🏢 Departmental architecture: Simulates real-world financial company departments
- 📊 Comprehensive analysis: Traditional technical indicators + price action analysis
- 📅 Real-time data: Economic calendar, fundamentals,broker/securities information ,and news integration
- 🤖 AI integration: Interfaces optimized for LLMs
- ⚡ High performance: Real-time streaming OHLC data processing
- 🔧 Extensible: Support for custom MCP services
- MCP can call the broker to query account information, place orders, and cancel orders.
- 🪩 Support local RPC/PubSub service.you can cross process/software/code languages communication.
Fastest experience
- [MCP FOR AI (langchain-trad
42882fa92b5dOBSERVED · 2026-10-07Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add finance-trading-ai-agents-mcp --env AITRADOS_SECRET_KEY=${AITRADOS_SECRET_KEY} -- uvx finance-trading-ai-agents-mcp{
"mcpServers": {
"finance-trading-ai-agents-mcp": {
"command": "uvx",
"args": [
"finance-trading-ai-agents-mcp"
],
"env": {
"AITRADOS_SECRET_KEY": "${AITRADOS_SECRET_KEY}"
}
}
}
}Exposed tools (3)
3 read · 0 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
get_custom_abc | read | return f |
get_economic_calendar_event_codes | read | |
get_latest_news_list | read |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | WARN |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- none-observed
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (8)
aitrados_mt5.zip
After starting the service, visit: `http://127.0.0.1:11999/`
## http://127.0.0.1:11999/mcp_servers.json and see the custom_mcp_server1 server
After it starts, open your browser at: http://127.0.0.1:11999/
mcp_config=get_client_mcp_config(departments,mcp_base_url="http://127.0.0.1:11999")
mcp_config=get_client_mcp_config(departments,mcp_base_url="http://127.0.0.1:11999")
aitrados-api, fastapi, fastmcp, aitrados-broker
Gates applied: no_behavioural_pass, no_license.
42882fa92b5dfull audit observations/trust-audit/mcp-server/aitrados__finance-trading-ai-agents.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-07 | 42882fa92b5d | SAFE | B | 89 | first audit |
Questions
What is the Finance Trading AI Agents MCP server?
A comprehensive, free MCP server designed specifically for financial analysis and quantitative trading. This specialized platform offers one-click local deployment with a sophisticated department-based architecture that mirrors real financial company operations.
What tools does Finance Trading AI Agents expose?
3 in total: 3 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is Finance Trading AI Agents safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.
What credentials does Finance Trading AI Agents need?
It reads AITRADOS_SECRET_KEY from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does Finance Trading AI Agents run?
It speaks streamable-http, so it runs as a service you connect to over the network. It is published on PyPI as finance-trading-ai-agents-mcp.
How current is this page?
The grade is for one exact copy of the source (42882fa92b5d), read on 2026-10-07. The repository is watched and re-audited when it changes.