mcpField
N
Ny Authority Debt

Ny Authority Debt

Remote
pipeworx.ioFinance0Updated 1d ago

About Ny Authority Debt

Ny Authority Debt provides researchers and public finance analysts with New York public authority debt issuance data from four state datasets. It supports searches, issuer profiles, borrowing totals, and explicit coverage information.

Key features

  1. 01Search issuance by authority, project, size, date, or tax status
  2. 02View an authority's issuance history and annual totals
  3. 03Aggregate borrowing by year and authority class
  4. 04Check dataset coverage and limitations

Use cases

  1. 01Research bonds issued for a public project
  2. 02Compare annual borrowing across authority classes
  3. 03Review an authority's new-money and refunding issuance

MCP support

Exposes search, profile, totals, and coverage tools to MCP clients through Pipeworx or a standalone stdio MCP server. The gateway endpoint also provides shared Pipeworx meta-tools.

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://gateway.pipeworx.io/ny-authority-debt/mcp
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.

Tools

Details

From the project README

ny-authority-debt

New York public authority debt issuance — which authority borrowed, for what project, on what terms, and when. Sourced from the four Authorities Budget Office datasets New York publishes on data.ny.gov. Keyless.

Part of Pipeworx — an MCP gateway connecting AI agents to 1683+ live data sources.

Tools

ToolAnswers
ny_authority_debt_searchWhich New York bonds were issued — by authority, project, size, date or tax status?
ny_authority_debt_profileEverything one authority has issued, with totals by year and new-money vs refunding.
ny_authority_debt_totalsAggregate borrowing by year and authority class; the largest issuers.
ny_authority_debt_coverageWhat is covered, how far back, and explicitly what is not here.

Coverage

Four authority classes, ~4,470 reported rows:

ClassDatasetRows
State Authority83xh-6x8i1,617
Local Authorityqbd7-9grw814
Industrial Development Agencycci8-aavx632
Local Development Corporationsh2f-cc7d1,410

Each row is one authority's report for one fiscal year. Rows where issued_debt_obligations is N mean this authority issued nothing that year — the tools filter to Y so an authority's quiet year never looks like an issue with blank fields.

What this is not

  • No secondary-market trade prices. This is primary issuance: what was sold and on what terms. Beyond that, most municipal bonds trade infrequently enough to have no current market price at all — what vendors sell as a muni "price" is usually an evaluated price, an estimate rather than a trade. A caller who assumes otherwise will read absence as "no trades happened".
  • No CUSIPs. See below.
  • New York only. California is covered by ca-debtwatch. For identifying one individual bond anywhere, use openfigi_search with marketSecDes: "Muni".

Two constraints that shaped the code

CUSIP is dropped deliberately. The State Authorities dataset carries a cusip_number column, populated on 1,295 rows with real 9-character CUSIPs. CUSIP identifiers are licensed by CUSIP Global Services, and that licence — not copyright in the underlying facts — is the binding constraint. The column is stripped before anything is returned, there is no CUSIP filter, and nothing is stored. Key on the issuer name here, and on FIGI via openfigi for an individual bond. Do not add it back.

EMMA is linked, never fetched. MSRB's terms are a contract accepted by using EMMA and they forbid building a database from their content. The official_statement_url this pack returns is a link New York itself published — often to a PDF hosted on emma.msrb.org, sometimes to the authority's own site — and it is passed straight through without being requested or parsed. emma_search_url is a composed search link, named for what it honestly is: the path returns 200, but the page is script-driven and we deliberately do not parse it, so it may not pre-fill the search.

Data sources

  • New York State Open Data — https://data.ny.gov (Authorities Budget Office debt-issuance reporting)
Gotcha: Socrata catalog search federates across states

Querying another state's Socrata catalog (e.g. data.texas.gov) returns these same dataset ids, because the catalog API federates. Texas does not publish them. Always check metadata.domain on a catalog hit before attributing a dataset to a state — verified 2026-09-01 that all four report domain: data.ny.gov.

Quick Start

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

{
  "mcpServers": {
    "ny-authority-debt": {
      "url": "https://gateway.pipeworx.io/ny-authority-debt/mcp"
    }
  }
}
What this endpoint actually serves

tools/list at https://gateway.pipeworx.io/ny-authority-debt/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:

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

Both URLs reach the same gateway and the same 1683+ 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

curl -X POST https://gateway.pipeworx.io/v1/tools/ny_authority_debt_search \
  -H 'Content-Type: application/json' \
  -d '{"authority":"Dormitory","min_amount":100000000,"limit":3}'

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

Standalone (no gateway account)

This package also runs as a local stdio MCP server — no Pipeworx account, no gateway round-trip:

{
  "mcpServers": {
    "ny-authority-debt": {
      "command": "npx",
      "args": ["-y", "@pipeworx/mcp-ny-authority-debt"]
    }
  }
}

Or run it directly to confirm it starts:

npx -y @pipeworx/mcp-ny-authority-debt

It speaks MCP over stdin/stdout and answers initialize/tools/list/tools/call for only this pack's tools — none of the shared meta-tools the gateway connection above adds. Same source, same tools, no ask_pipeworx routing.

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 Ny Authority Debt data" })

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

More

License

MIT

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.