MCP Quickstart
Connect AletaIndex to any MCP-compatible AI agent in under 2 minutes.
Compatible with: Claude Code, Cursor, Windsurf, and any MCP-supporting tool.
Step 1 — Get an API Key
Sign up at aletaindex-narrative.com
Free trial: 10 tickers, 90 days history, 500 credits.
Prerequisites — Install uv
The MCP server runs via uvx, which is part of uv — a fast Python package manager. If you don't have it yet:
curl -LsSf https://astral.sh/uv/install.sh | sh
Then restart your terminal. uvx will be available automatically. No other setup needed.
Step 2 — Add to Your Agent Config
Claude Code
Add to ~/.claude/settings.json:
{
"mcpServers": {
"aletaindex": {
"command": "uvx",
"args": ["narrative-intelligence-mcp"],
"env": {
"NARRATIVE_API_KEY": "nk_your_key_here"
}
}
}
}
Restart Claude Code. Done.
Claude Desktop
Open Claude Desktop → Claude menu → Settings → Developer → Edit Config.
Add to claude_desktop_config.json:
{
"preferences": { "...existing preferences..." },
"mcpServers": {
"aletaindex": {
"command": "uvx",
"args": ["narrative-intelligence-mcp"],
"env": {
"NARRATIVE_API_KEY": "nk_your_key_here"
}
}
}
}
Save and relaunch Claude Desktop.
Cursor / Windsurf
Add to your MCP config file:
{
"mcpServers": {
"aletaindex": {
"command": "uvx",
"args": ["narrative-intelligence-mcp"],
"env": {
"NARRATIVE_API_KEY": "nk_your_key_here"
}
}
}
}
Step 3 — Start Asking
💡 For best results, paste this at the start of your conversation:
You have access to the Aleta Index MCP, which provides narrative intelligence
derived from institutional news sources.
When analyzing stocks, prioritize the narrative layer: global narratives,
daily topics, sentiment scores, mention counts, sentiment trends, and
behavioral patterns. The narrative layer aggregates signal across hundreds
of sources and contains sufficient information for analysis — avoid reading
individual article bodies unless specifically necessary.
No setup prompts needed. Just ask naturally:
What narratives are driving NVDA this week?
Has TSLA sentiment shifted in the last 3 days?
Analyze narrative risk across my portfolio: NVDA 30%, AAPL 25%, TSLA 20%, MSFT 25%
The agent automatically calls the right tools and formats the response.
Available Tools
| Tool | Description |
|---|---|
get_narratives |
Full narrative hierarchy for one or more tickers: global narratives, daily topic clusters, articles, and sentiment scores |
get_portfolio_risk |
Macro risk theme analysis across a portfolio — identifies which narratives create concentrated exposure across multiple holdings |
Example Agent Session
You: What's the narrative situation for NVDA right now?
Agent: [calls get_narratives(tickers="NVDA", from_date="2026-05-03", to_date="2026-05-10")]
NVDA — Last 7 Days
Active Narratives (5):
1. AI Infrastructure Supercycle — +0.68 sentiment, 47 articles, ESCALATING
2. Export Control Headwinds — -0.41 sentiment, 23 articles, stable
3. Data Center Capex Cycle — +0.55 sentiment, 18 articles, new spike May 7
4. Blackwell GPU Supply Chain — +0.31 sentiment, 12 articles, stable
5. China Market Access — -0.22 sentiment, 8 articles, declining
Sentiment on "Export Control Headwinds" improved +0.12 over the week,
suggesting the market is discounting near-term regulatory risk.
Manual Installation (alternative to uvx)
pip install narrative-intelligence-mcp
Then use narrative-intelligence-mcp as the command instead of uvx narrative-intelligence-mcp.
Troubleshooting
"NARRATIVE_API_KEY is not set" — Add your API key to the env section of your MCP config.
"Rate limit exceeded" — You've used all your credits. Upgrade at aletaindex-narrative.com/subscription.
"Access denied: Ticker X requires Plus tier" — This ticker is not included in the free tier. Upgrade at aletaindex-narrative.com/subscription. Free tickers: TSLA, NVDA, AAPL, MSFT, AMZN, GOOGL, META, AMD, NFLX, JPM.
Prefer REST API?
Metadata
Release files for narrative-intelligence-mcp 0.1.4
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| narrative_intelligence_mcp-0.1.4.tar.gz | 8.3 kB | With provenance | Details for narrative_intelligence_mcp-0.1.4.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| narrative_intelligence_mcp-0.1.4-py3-none-any.whl | Python 3 | none | any | Details for narrative_intelligence_mcp-0.1.4-py3-none-any.whl |
Total release size: 15.5 kB
Release files / narrative_intelligence_mcp-0.1.4.tar.gz
| Download URL | narrative_intelligence_mcp-0.1.4.tar.gz |
|---|---|
| Size | 8.3 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
9574ae706659fd682bff0eeee5afefe789069fa405988a60de10c00b680e5bb3
|
|
BLAKE2b-256 checksum How to use checksums |
e99b273d4cb21a410bbb707cd642271234a76e4aa9b214b8634250f34816b6cb
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Sep 6, 2026.
Transparency logRelease files / narrative_intelligence_mcp-0.1.4-py3-none-any.whl
| Download URL | narrative_intelligence_mcp-0.1.4-py3-none-any.whl |
|---|---|
| Size | 7.2 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
67ccc866c7fa0eb5b01ebc46c3bae7028584de7c274f5d7fe00629da5e791703
|
|
BLAKE2b-256 checksum How to use checksums |
4d30cd473dcd36049458f90ba5bf64766f659ac7c9c5915d250ab167b434dee8
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Sep 6, 2026.
Transparency logSecurity for narrative-intelligence-mcp 0.1.4
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
Full provenance
All 2 files in this release have been uploaded with provenance metadata.
Attestation for narrative_intelligence_mcp-0.1.4.tar.gz
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Sep 6, 2026.
Transparency logA note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.