Skip to main content
Glama
README.md
# @pipeworx/rbi-in

Reserve Bank of India rates: the current policy repo rate and the rest of the corridor (standing deposit facility, marginal standing facility, bank rate, reverse repo), CRR and SLR, lending and deposit benchmarks, and the bank's reference exchange rates against the rupee, current or by date range.

Part of [Pipeworx](https://pipeworx.io) — an MCP gateway connecting AI agents to 2016+ live data sources. This is an independent, unofficial integration — not affiliated with, endorsed by, or published by the upstream provider.

## Tools

- `rbi_in_series_list()` — what the pack serves, currency list with quote units, and limits. No upstream call.
- `rbi_in_policy_rates()` — current policy repo, standing deposit facility, marginal standing facility, bank and fixed reverse repo rates (percent), CRR and SLR, base rate and overnight MCLR ranges, savings deposit rate, and the current reference rates with their as-at time. **Current values only** (see below).
- `rbi_in_reference_rates({ currency?, date? | start_date?, end_date? })` — INR per USD, GBP, EUR, AED, RUB, per 100 JPY, per 10,000 IDR; latest by default, with history by date range (max 366 days). Weekends and holidays return `count: 0` with `empty_reason: no_publication_on_date`.

## Auth

Keyless.

## Data sources

- Reserve Bank of India, current rates — policy rates, reserve ratios and lending/deposit benchmarks as the bank shows them today.
- Reserve Bank of India, reference rates (FBIL benchmark) — the reference exchange rates the bank publishes each business day. Each call reads live from the bank; nothing is stored.

Things worth knowing:

- The bank's published current-rates block carries no decision date and no history, so this pack cannot say when the repo rate last changed or list past decisions. That is a real gap against a policy-rate history, not an omission to fill by guessing.
- Reference-rate history comes from a form on the bank's site that carries session state; the pack reads the form's state, submits the date range and reads the table that comes back. If the bank changes the form the tool errors with a named message rather than returning an empty list.
- JPY is quoted per 100 yen and IDR per 10,000 rupiah; `quote` says which.

## Quick Start

Add to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):

```json
{
  "mcpServers": {
    "rbi-in": {
      "url": "https://gateway.pipeworx.io/rbi-in/mcp"
    }
  }
}
```

### What this endpoint actually serves

`tools/list` at `https://gateway.pipeworx.io/rbi-in/mcp` returns the tools in the table
above **plus the shared Pipeworx meta-tools** — `ask_pipeworx`,
`discover_tools`, `search_within`, `remember`/`recall` and the rest of the
gateway-wide set. So the tool count you see is larger than this table: a
single-pack endpoint currently lists roughly 30 shared tools alongside the
pack's own. The connection's `initialize` response states its exact scope, and
is the authoritative answer for a given day.

This is deliberate, not multiplexing by accident. The meta-tools are what let a
scoped connection answer a question this pack does not cover — via
`ask_pipeworx`, which routes across the whole catalog — without you adding a
second MCP server. There is currently no way to mount a pack endpoint without
them; if the extra schemas cost you more context than the routing is worth,
connect to the full gateway once rather than to several pack endpoints.

Or connect to the full Pipeworx gateway to get every pack's tools listed
directly, instead of just this one's:

```json
{
  "mcpServers": {
    "pipeworx": {
      "url": "https://gateway.pipeworx.io/mcp"
    }
  }
}
```

Both URLs reach the same gateway and the same 2016+ data sources. The
only difference is which pack's tools are listed **directly**; `ask_pipeworx`
reaches all of them from either one.

## No MCP client? Call it over HTTP

```bash
curl -X POST https://gateway.pipeworx.io/v1/tools/rbi_in_series_list \
  -H 'Content-Type: application/json' \
  -d '{}'
```

No account needed for the first calls. Inspect any tool: `GET https://gateway.pipeworx.io/v1/tools/rbi_in_series_list`. Find one: `POST https://gateway.pipeworx.io/v1/tools/search_packs` with `{"query":"..."}`.

## Run it from npm

`@pipeworx/mcp-rbi-in` is a local stdio bridge to the Pipeworx gateway: your MCP client
starts it with `npx`, and it forwards every call to the same
`https://gateway.pipeworx.io/rbi-in/mcp` endpoint shown above. It needs network access;
there is no offline mode.

```json
{
  "mcpServers": {
    "rbi-in": {
      "command": "npx",
      "args": ["-y", "@pipeworx/mcp-rbi-in"]
    }
  }
}
```

Without a key it calls anonymously, capped at 50 calls a day. A free account
raises that to 200 a day: get a key at https://pipeworx.io/signup and add
`"env": { "PIPEWORX_API_KEY": "<your key>" }` to the server entry.
The key is sent as a Bearer token, the same way a hosted connection sends it,
so calls are metered and billed exactly as they are there.

It lists **only** this pack's tools by default. Set `PIPEWORX_META_TOOLS=1` to
also list `ask_pipeworx` and the other gateway-wide tools.

Behind an HTTPS proxy: Node's built-in `fetch` does not read `HTTPS_PROXY` by
default. Newer Node releases honour it when `NODE_USE_ENV_PROXY=1` is set; check
your Node version's documentation.

## Using with ask_pipeworx

Instead of calling tools directly, you can ask questions in plain English —
this works on the pack endpoint above as well as on the full gateway:

```
ask_pipeworx({ question: "your question about Rbi In data" })
```

The gateway picks the right tool and fills the arguments automatically.

## More

- [Docs and guides](https://pipeworx.io/docs)
- [pipeworx.io](https://pipeworx.io)

## License

MIT