Indian stocks: NSE/BSE filings read by AI with price reactions, fundamentals, IPOs and FPI flows.
in.marketping/marketping MCP Server
The in.marketping/marketping Model Context Protocol (MCP) server provides access to Indian stock information derived from NSE/BSE filings. It focuses on AI-readable extraction related to price reactions, fundamentals, IPOs, and FPI flows. The server is identified by the slug in-marketping-marketping.
🛠️ Key Features
Reads NSE/BSE filings for Indian stocks
Extracts or supports analysis of price reactions
Covers fundamentals
Supports IPO-related information
Includes FPI flow data
🚀 Use Cases
Analyze how filings relate to stock price reactions
Search MarketPing's Indian stock market data — companies, corporate announcements, IPO issues, and the text of annual reports, earnings-call transcripts and investor presentations. Returns results with ids to pass to `fetch`. Factual data only — MarketPing publishes no buy/sell recommendations, no price targets and no IPO grey-market premium.
Retrieve the full content of one search result by its id — a company profile with fundamentals and recent announcements, one announcement with its measured price reaction, one page of a filing, or one IPO issue. Factual data only — MarketPing publishes no buy/sell recommendations, no price targets and no IPO grey-market premium.
Parameters1
id
string
required
An id returned by search
Raw schema
{
"type": "object",
"properties": {
"id": {
"type": "string",
"description": "An id returned by search"
}
},
"required": [
"id"
],
"additionalProperties": false
}
resolve_company
Find an Indian listed company by name, ticker or partial match. Returns candidates with their MarketPing slug — call this FIRST unless you already hold a slug, because every other company tool takes one. Factual data only — MarketPing publishes no buy/sell recommendations, no price targets and no IPO grey-market premium.
Parameters1
query
string
required
Company name, NSE/BSE symbol, or part of one
Raw schema
{
"type": "object",
"properties": {
"query": {
"type": "string",
"description": "Company name, NSE/BSE symbol, or part of one"
}
},
"required": [
"query"
],
"additionalProperties": false
}
company_snapshot
Latest fundamentals and valuation for one company: price, market cap, P/E, P/B, TTM revenue and profit, growth, ROCE/ROE and debt ratios. Use for 'how is X doing', 'what does X trade at', or as the numeric backdrop before reading filings. Factual data only — MarketPing publishes no buy/sell recommendations, no price targets and no IPO grey-market premium.
Recent NSE/BSE corporate filings with MarketPing's AI classification — subject, category, document type, importance and sentiment. This is MarketPing's core dataset: use it for 'what has X announced lately', 'any news on X', or (with no company) 'what is happening in the market today'. Factual data only — MarketPing publishes no buy/sell recommendations, no price targets and no IPO grey-market premium.
Parameters2
company
string
optional
Optional — omit for market-wide announcements
days
integer
optional
Look-back window in days (default 30, max 365)
Raw schema
{
"type": "object",
"properties": {
"company": {
"type": "string",
"description": "Optional — omit for market-wide announcements"
},
"days": {
"type": "integer",
"description": "Look-back window in days (default 30, max 365)"
}
},
"required": [],
"additionalProperties": false
}
alert_reaction
How the market actually moved after ONE announcement: percentage returns at 5 minutes, 30 minutes, 1/2/3/5/7/15 days and 1/2/3 months from the announcement price. This is measured data, not a forecast — no other Indian data source publishes it. Get an alert id from recent_alerts first. Factual data only — MarketPing publishes no buy/sell recommendations, no price targets and no IPO grey-market premium.
Full-text search across every page MarketPing holds — annual reports, earnings-call transcripts, investor presentations. Returns {doc_id, page, snippet} hits to follow up with read_pages. SNIPPETS ARE KEYWORD WINDOWS, NOT FACTS: never state a figure from a snippet, open the page and take it from there. Factual data only — MarketPing publishes no buy/sell recommendations, no price targets and no IPO grey-market premium.
Parameters2
query
string
required
What to look for, in plain words
company
string
optional
Optional — restrict the search to one company
Raw schema
{
"type": "object",
"properties": {
"query": {
"type": "string",
"description": "What to look for, in plain words"
},
"company": {
"type": "string",
"description": "Optional — restrict the search to one company"
}
},
"required": [
"query"
],
"additionalProperties": false
}
list_documents
The documents MarketPing holds for a company — annual reports, earnings-call transcripts, investor presentations, results — newest first, each with a doc_id. A capped list is marked as truncated: never read one as the whole holding. Factual data only — MarketPing publishes no buy/sell recommendations, no price targets and no IPO grey-market premium.
A document's table of contents: section titles, one-line summaries and page ranges. Read this BEFORE read_pages so you open the right four pages instead of guessing — annual reports run to 300+ pages. Factual data only — MarketPing publishes no buy/sell recommendations, no price targets and no IPO grey-market premium.
Parameters1
doc_id
string
required
Document id from list_documents or search_filings
Raw schema
{
"type": "object",
"properties": {
"doc_id": {
"type": "string",
"description": "Document id from list_documents or search_filings"
}
},
"required": [
"doc_id"
],
"additionalProperties": false
}
read_pages
The actual text of a page range (max 12 pages). This is the ONLY source you may quote a document from — cite as {doc_id, page, verbatim quote}, and the quote must really appear on that page. Factual data only — MarketPing publishes no buy/sell recommendations, no price targets and no IPO grey-market premium.
Auditor opinions, key audit matters, CARO exceptions and auditor changes per fiscal year, extracted page-cited from annual reports. Use for governance and red-flag questions. A missing year means not yet read — never read it as 'clean'. Factual data only — MarketPing publishes no buy/sell recommendations, no price targets and no IPO grey-market premium.
The metrics you can filter and sort on in run_screener, with labels, units and groups. Call this before building a screen if you are unsure of a field name. Factual data only — MarketPing publishes no buy/sell recommendations, no price targets and no IPO grey-market premium.
Parameters2
group
string
optional
Optional group filter, e.g. Valuation, Profitability
featured_only
boolean
optional
Default true — the commonly used subset
Raw schema
{
"type": "object",
"properties": {
"group": {
"type": "string",
"description": "Optional group filter, e.g. Valuation, Profitability"
},
"featured_only": {
"type": "boolean",
"description": "Default true — the commonly used subset"
}
},
"required": [],
"additionalProperties": false
}
run_screener
Filter MarketPing's universe of 5,400+ NSE/BSE companies on fundamentals — 108 metrics covering valuation, growth, profitability, leverage and ownership. Use for 'find companies where…' questions. Field names come from screener_fields. Factual data only — MarketPing publishes no buy/sell recommendations, no price targets and no IPO grey-market premium.
Parameters6
filters
array
required
Conditions to apply, e.g. [{"field":"roce","op":"gt","value":20}]
Indian IPOs — open now, upcoming, closed or already listed — with price band, issue size, lot size, dates, subscription figures and post-listing performance. Covers mainboard and SME. MarketPing deliberately publishes no grey-market premium and no apply/avoid verdict; if you need those, this is not the source. Factual data only — MarketPing publishes no buy/sell recommendations, no price targets and no IPO grey-market premium.
Foreign portfolio investor (FPI/FII) flows into Indian markets as NSDL publishes them — daily net equity and debt flows, by investment route, with month-to-date totals. Use for 'are foreign investors buying' questions. Factual data only — MarketPing publishes no buy/sell recommendations, no price targets and no IPO grey-market premium.
Which Indian companies report quarterly results on which dates, as the exchanges have published them. Default window is the next 60 days. Factual data only — MarketPing publishes no buy/sell recommendations, no price targets and no IPO grey-market premium.
MarketPing's briefing for the latest NSE trading day: market score, index and sector moves, FII/DII and FPI flows, breadth, movers, and the day's most important announcements. Use for 'how did the Indian market do today'. Factual data only — MarketPing publishes no buy/sell recommendations, no price targets and no IPO grey-market premium.
MarketPing's curated stacks: public lists of Indian companies rebuilt every day from layers (quality/value/growth screens, an index, a Discover catalyst page) with one rule — how many layers a company must clear today. Returns each stack's slug, rule, member count and what entered or left today. With a linked MarketPing account, also the caller's own stacks. Use for 'which companies clear several quality screens right now'. Factual data only — MarketPing publishes no buy/sell recommendations, no price targets and no IPO grey-market premium.
The companies in one stack as of today's snapshot, with how many layers each clears, which ones, how many consecutive days it has been in the stack, market cap and P/E. Takes a slug from list_stacks. Membership is a fact about screens cleared today — never a rating. Factual data only — MarketPing publishes no buy/sell recommendations, no price targets and no IPO grey-market premium.
What entered, left, cleared more or fewer layers in a stack since a date (default: the previous daily snapshot). Use for 'what is new in this list today / this week'. Factual data only — MarketPing publishes no buy/sell recommendations, no price targets and no IPO grey-market premium.
Parameters2
stack
string
required
Stack slug from list_stacks
since
string
optional
YYYY-MM-DD; compares today's snapshot with the newest one on or before this date
Raw schema
{
"type": "object",
"properties": {
"stack": {
"type": "string",
"description": "Stack slug from list_stacks"
},
"since": {
"type": "string",
"description": "YYYY-MM-DD; compares today's snapshot with the newest one on or before this date"
}
},
"required": [
"stack"
],
"additionalProperties": false
}
list_models
The valuation models saved to this MarketPing account (Models: DCF, excess return, sum of parts), with the company and a link. Needs a linked account. Optional `company` narrows to one company (slug). Factual data only — MarketPing publishes no buy/sell recommendations, no price targets and no IPO grey-market premium.
Recompute one of the account holder's saved models (DCF, excess return or sum of parts) with MarketPing's engine and return the value per share, the bridge and the projected years (3, 5 or 10, as the model sets). The figure is the holder's own arithmetic over their inputs — report it as THEIR model, never as MarketPing's view or a target. Needs a linked account; nothing is changed. Factual data only — MarketPing publishes no buy/sell recommendations, no price targets and no IPO grey-market premium.
The companies this MarketPing account follows, with their alert status. Needs a linked MarketPing account — the assistant will offer to connect one. Factual data only — MarketPing publishes no buy/sell recommendations, no price targets and no IPO grey-market premium.
Add a company to this MarketPing account's watchlist, so its filings start arriving as alerts. Needs a linked MarketPing account. Subject to the plan's company limit. Factual data only — MarketPing publishes no buy/sell recommendations, no price targets and no IPO grey-market premium.
Indian stock-market research for AI assistants: NSE/BSE corporate filings read by AI with the
measured price reaction after each one, fundamentals for 5,000+ companies, page-cited reads of
annual reports and earnings calls, a 108-metric screener, the IPO pipeline, FPI flows, the results
calendar and the daily market briefing.
Auth: none for 20 of the 24 tools. No API key, no sign-up. Four account tools use OAuth 2.1.
Writes: exactly one tool (watchlist_add), annotated readOnlyHint: false. Everything else is read-only.
Advice: none. MarketPing publishes what companies filed and what the stock did next — no buy/sell calls, no price targets, no ratings, no grey-market premium.
This repository is the server's public contract: the exact tool catalogue the server returns from
tools/list (tools.json), a registry manifest (server.json), and a small open-source stdio bridge
for clients that cannot speak Streamable HTTP directly. The server itself runs on MarketPing's
infrastructure; its handlers are thin read-only wrappers over the same code paths that serve
marketping.in.
Connect
Claude (claude.ai / Claude Desktop) — Settings › Connectors › Add custom connector
That runs the published mcp-remote bridge against the endpoint above and nothing else. It stores
no credentials of its own; mcp-remote keeps OAuth tokens in its standard location (~/.mcp-auth)
only if you link an account.
bin/marketping-mcp.js in this repo does the same thing as a named wrapper. It is not published
to npm, so npx -y @marketping/mcp will not resolve — run it from a clone, or just use the
mcp-remote form above.
The 24 tools
Exact schemas and annotations: tools.json (the live tools/list response, captured
19 Sep 2026). Every description ends with the no-advice line — that is part of the contract the
consuming model reads.
Tool
What it returns
Auth
search
Companies, filings, IPOs and documents matching a query (ChatGPT search contract)
none
fetch
The full content of one search result by id
none
resolve_company
A listed company by name/ticker/partial match, with candidates
none
company_snapshot
Latest fundamentals and valuation for one company
none
recent_alerts
Recent NSE/BSE filings with AI subject, category, importance, sentiment
none
alert_reaction
The measured move after ONE filing: 5 min … 3 months
none
search_filings
Full-text search across every document page MarketPing holds
none
list_documents
The documents held for a company, newest first
none
doc_contents
A document's table of contents with page ranges
none
read_pages
The text of a page range (max 12 pages) — the only quotable source
none
audit_report
Auditor opinions, key audit matters, CARO exceptions per fiscal year
none
screener_fields
The 108 metrics available to run_screener
none
run_screener
Filter the 5,000+ company universe on fundamentals
none
ipo_pipeline
Open / upcoming / closed / listed IPOs with issue data and subscription
none
fpi_flows
FPI/FII flows as NSDL publishes them
none
results_calendar
Who reports results on which dates
none
daily_briefing
The latest trading day's briefing: score, indices, sectors, flows, movers
none
list_stacks
MarketPing's curated stacks (public daily-rebuilt company lists)
none
run_stack
The members of one stack as of today's snapshot
none
stack_changes
What entered/left a stack since a date
none
list_models
The valuation models saved to the linked account
linked account
run_model
Recompute one saved model with overrides
linked account
watchlist_list
The companies the linked account follows
linked account
watchlist_add
Write. Add a company to the linked account's watchlist
linked account
Data handling
A tool call sends only the tool's arguments (a company name, a query, a date range) to
mcp.marketping.in over HTTPS. Nothing else leaves the client; the bridge adds no telemetry.
Anonymous calls are metered by caller class: a direct end-user IP gets its own daily budget
(200 tool calls per IST day, the same as the Free plan); hosted assistants (claude.ai, ChatGPT)
call from vendor egress ranges and share a bounded pool. Quota exhaustion is a normal tool
result with a message, never an auth error.
Linking a MarketPing account (OAuth 2.1; discovery at https://mcp.marketping.in/.well-known/oauth-authorization-server and /.well-known/oauth-protected-resource)
unlocks the four account tools and the account's plan budget (Investor 1,000 / Trader 2,000
calls per day). Tokens are issued by MarketPing's own authorization server and can be revoked
from the account's settings.
Every result carries a marketping.in URL so the assistant can cite the page. Document text
comes only from read_pages, page-anchored, so quotes are checkable.
No tool fetches arbitrary URLs, runs code, or reads anything outside MarketPing's database.
MarketPing is an Indian stock-market research platform built around one
idea: every NSE and BSE corporate filing, read by AI the moment it is published, delivered to
WhatsApp within a minute, and followed by the measured price reaction — what the stock actually
did 5 minutes to 3 months later. 500,000+ filings decoded, 1.9 million reactions measured, 5,000+
companies. It publishes no buy/sell calls, no price targets and no ratings.
What the same data looks like on the site (every MCP result links back to one of these):
Nexa AI — ask anything about a company and get page-cited answers
Features · Pricing — free for 5 companies with
WhatsApp delivery; Investor ₹199/month (30), Trader ₹599/month (100)
llms.txt — the answer blocks MarketPing publishes for AI assistants
License
The bridge and the files in this repository are MIT-licensed (see LICENSE). The MarketPing
service and its data are proprietary; use of the endpoint is subject to https://marketping.in/terms.