indian-stock-market-mcpSAFE
MCP-first server for Indian equity research with local CSV/ Parquet data, price history, ticker validation, weekly performance, and Nifty 50 rankings.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
[](https://github.com/ratan-systems/indian-stock-market-mcp/actions/workflows/ci.yml)
A local, MCP-first server for Indian equity research with daily OHLCV data. It works with Codex, Claude Code, Cursor, and other MCP-compatible clients.
The server does not call OpenAI or Anthropic APIs and does not require either provider's API key. Your MCP client supplies the model; this project supplies the market-data tools.
[!WARNING] This is a research and demonstration tool, not investment advice. Verify data quality, corporate-action treatment, and price-adjustment status before using results for investment decisions or production backtests.
Demo
The MCP client discovers the available research tools, returns RELIANCE price history, ranks weekly performers, and handles an unavailable ticker.
What It Does
- Reads a local
.parquetor.csvdaily-equity dataset. - Returns recent price history for one ticker.
- Validates whether a ticker exists in the configured dataset.
- Calculates five-session close-to-close performance for one ticker.
- Ranks weekly performers from the bundled Nifty 50 universe.
- Lists all symbols in the configured dataset or the bundled Nifty 50 list.
- Diagnoses the configured dataset: readability, schema, counts, date range,
data-quality problems, available analyses, and warnings.
The current 0.x scope is deliberately small: local historical data, research-oriented tools, and a quick MCP demo. It does not provide live prices, fundamentals, news, order execution, or portfolio management.
v0.1.1 Scope
v0.1.1 hardens the public foundation rather than adding research features. It tightens dataset validation and error handling, ships the
3c0ca6b4a967OBSERVED · 2026-10-08Connect
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.
claude mcp add indian-stock-market-mcp -- uvx indian-stock-market-mcp
{
"mcpServers": {
"indian-stock-market-mcp": {
"command": "uvx",
"args": [
"indian-stock-market-mcp"
]
}
}
}Exposed tools (7)
7 read · 0 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
get_available_universe | read | List every stock symbol available in the currently configured |
get_data_capabilities | read | Diagnose the configured dataset: whether it is readable, its format, |
get_nifty50_universe | read | List all 50 stock symbols in the Nifty 50 index. |
get_price_history | read | Return recent daily OHLCV data for an Indian equity symbol. |
get_stock_weekly_return | read | Return how much one stock |
rank_weekly_performers | read | Rank Nifty 50 stocks by weekly price change, best to worst. |
validate_ticker | read | Check whether an Indian equity ticker is available. |
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 | PASS |
| L1 | Static analysis of the code | WARN |
| 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
- declared (1 observation(s))
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (2)
module = __import__(PACKAGE)
entry_point = getattr(importlib.import_module(module_name), function_name)
Gates applied: no_behavioural_pass.
3c0ca6b4a967full audit observations/trust-audit/mcp-server/ratan-systems__indian-stock-market-mcp.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 |
|---|---|---|---|---|---|
| 2026-10-08 | 3c0ca6b4a967 | SAFE | B | 89 | first audit |
Questions
What is the indian-stock-market-mcp MCP server?
MCP-first server for Indian equity research with local CSV/ Parquet data, price history, ticker validation, weekly performance, and Nifty 50 rankings.
What tools does indian-stock-market-mcp expose?
7 in total: 7 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is indian-stock-market-mcp 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 indian-stock-market-mcp need?
No credential environment variables were found in its source, so it appears to need none.
How does indian-stock-market-mcp run?
It speaks stdio, so it runs as a local process your client starts. It is published on PyPI as indian-stock-market-mcp.
How current is this page?
The grade is for one exact copy of the source (3c0ca6b4a967), read on 2026-10-08. The repository is watched and re-audited when it changes.