- Home
- Skills
- Trading & Investing
- Indexa Capital Assistant
Works with the AI Agents you already use
Indexa Capital Assistant
Ask your AI agent about your Indexa Capital portfolio, returns, fees and taxes. Read-only, runs locally
Free
Indexa Capital Assistant
Example session with this skill installed
How has my portfolio performed compared to the benchmark this year, and what were the fees?
- Read your context and instructions
- Compiled the indexa capital assistant
I have retrieved the performance data and fee breakdown for your Indexa Capital investment account (12345-IS) for the period of 2024-01-01 to 2024-05-22.
Performance and Fees Summary
| Metric | Value |
|---|---|
| Cumulative Return | +5.42% |
| Benchmark Return | +4.10% |
| Alpha (vs Benchmark) | +1.32% |
| Annualized Volatility | 8.1% |
| Total Fees Paid | 42.15 EUR |
| Account Value | 24,560.00 EUR |
The portfolio is currently outperforming the benchmark by 1.32% year-to-date. The fees paid represent approximately 0.17% of the current portfolio value for this period. All figures are in EUR.
Next steps
- Review the specific instrument transactions to see which funds drove the outperformance.
- Check for any pending orders if you recently added funds to maintain this allocation.
- Run a fiscal result query if you are planning to rebalance for tax optimization.
Connects securely to your tools. The creator never sees your data.
About this skill
Ask your AI agent about your Indexa Capital investments in plain language and get answers from your real data.
This skill teaches your agent when and how to use the open-source indexa-mcp server, a local, read-only connection to your Indexa Capital accounts. It picks the right tool for each question, uses date filters and pagination correctly, and presents results clearly.
What you can ask
“How much do I have in Indexa and how is it split?” “What’s my annualized return, and how am I doing against the benchmark?” “List my contributions in 2025.” “How much have I paid in fees?” “Do I have any pending orders?” “What gains and losses did I realize this year?” (useful when preparing your tax return)
Guided setup If the MCP server isn’t installed yet, the skill walks you through it. It never asks you to paste your API token in the chat: you keep the token in an environment variable or your Keychain, and the agent only runs the install command that references it.
Safe by design
Read-only: it cannot move money, place orders or change your portfolio. Runs on your machine; the server opens no network port. Never returns personal data such as ID, address or contract details.
Requirements
An Indexa Capital account and your own API token (Indexa private area → User settings → Applications). The indexa-mcp server (Python 3.11+ and uv).
Unofficial project, not affiliated with Indexa Capital. Data you query is sent to the AI client you use; the Indexa token itself is not read-only, so keep it private and revoke it in Indexa if it ever leaks.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Trading & Investing.
Read-only access only. Requires pre-configured INDEXA_API_TOKEN environment variable. Does not support executing trades or account modifications. Personal identity data is not returned.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before buying a skill.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Free to use
No account required to browse
Trust & safety
Security scan
Security scan passed 9 days ago
- Free with an Agensi account
- Software
- Indexa MCP
Git
uv (Python tool runner)