treasury-fiscaldata-mcp-server

<div align="center"> <h1>@cyanheads/treasury-fiscaldata-mcp-server</h1> <p><b>Query US Treasury national debt, interest rates, exchange rates, and fiscal datasets via MCP.</b> <div>8 Tools · dataframe drop is opt-in</div> </p> </div> <div align="center">

</div> <div align="center">

</div> <div align="center">

Public Hosted Server: https://treasury-fiscaldata.caseyjhand.com/mcp

</div>

---

Overview

US Treasury Fiscal Data: the national debt, interest rates, exchange rates, and other federal fiscal datasets. Pull the headline numbers in one call, query any Fiscal Data endpoint directly, and run SQL over large pulls.

Tools

| Tool | Description | |:-----|:------------| | treasury_list_datasets | Browse the curated catalog of 17 Treasury Fiscal Data endpoints with field names, descriptions, and update cadence | | treasury_query_dataset | Query any Treasury Fiscal Data endpoint by path, field list, filters, sort, and page — with optional DataCanvas spill | | treasury_get_debt | Fetch national debt (Debt to the Penny) — latest record, specific date, or date-range series with optional DataCanvas spill | | treasury_get_interest_rates | Average interest rates Treasury pays on outstanding securities by type — marketable issues, non-marketable series, and aggregate totals | | treasury_get_exchange_rates | Official Treasury statutory exchange rates for ~165 countries, published quarterly | | treasury_dataframe_describe | List DataCanvas dataframes materialized by the treasury_* tools with schema, row count, and TTL | | treasury_dataframe_query | Run a single-statement SELECT against DataCanvas dataframes using standard DuckDB SQL | | treasury_dataframe_drop | Delete a staged dataframe and its provenance (disabled unless TREASURY_DATAFRAME_DROP_ENABLED=true) |

Capability reference

treasury_list_datasets _tool

• Filter by category (debt, interest_rates, exchange_rates, revenue_spending, savings_bonds, securities, other) or keyword search.
• Returns endpoint paths, fields, types, and update cadence from a bundled catalog, with no network call.

---

treasury_query_dataset _tool

• Query an endpoint with { field, operator, value } filters (eq, gt, gte, lt, lte, in), sort, and pagination: page_size 1–10000 (default 100), page_number starts at 1.
• Returns rows, field labels, total_count, and total_pages; error reasons are invalid_endpoint, invalid_field, invalid_filter, and page_out_of_range.
• Pass canvas_id to stage the page for SQL analysis; the returned canvas_id is the assigned table name.

---

treasury_get_debt _tool

• mode=latest returns the newest business-day record; mode=date accepts a YYYY-MM-DD date; mode=series accepts a date range. Coverage begins 1993-04-01.
• Returns debt totals and a 20-row series preview; compare retrieved_records with total_records. A missing date returns no_data_for_date.
• Series staging starts above 500 rows or on request via canvas_id; paging stops at 50,000 rows.

---

treasury_get_interest_rates _tool

• mode=latest returns the newest month's rates, optionally filtered by security_type; mode=series accepts a date range.
• Rates are percentages, with available security types disclosed when a filter matches nothing; the series preview holds at most 20 rows.
• Series staging starts above 200 rows or on request via canvas_id.

---

treasury_get_exchange_rates _tool

• Quarterly official reporting rates in foreign currency units per 1 USD. Filter countries by exact name; mode=latest returns one current row per currency and mode=series accepts a date range.
• Each row carries record_date and effective_date; mixed_record_dates flags a result spanning quarters. Series previews hold 20 rows; retrieved_records discloses progress against total_records.
• Series staging starts above 500 rows or on request via canvas_id; paging stops at 50,000 rows.
• country_not_found error when a requested country has no records

---

treasury_dataframe_describe _tool

• Omit name to list the tenant's active dataframes, or supply one exact table name.
• Returns provenance, created/expiry timestamps, row count, and column schema; truncated / max_rows disclose a capped source pull.
• Table expiry defaults to 24h after staging, configurable with CANVAS_TTL_MS.

---

treasury_dataframe_query _tool

• Accepts one read-only SELECT; row_limit defaults to 1000 (max 10000) and preview may not exceed it. System catalogs, external-file functions, and SQL mutations are denied.
• Returns rows and row_count_capped; errors distinguish canvas_unavailable, system_catalog_access, invalid_sql, missing_table, and invalid_query_bounds.
• register_as materializes the full result as a new dataframe with a fresh TTL.

---

treasury_dataframe_drop _tool

• Accepts the exact name from treasury_dataframe_describe, a data tool's canvas_id, or query's registered_as; deletes that table and its provenance for the tenant.
• Returns name and dropped: true; an absent or expired table returns missing_table with guidance to list active tables.
• Disabled by default. Set TREASURY_DATAFRAME_DROP_ENABLED=true and CANVAS_PROVIDER_TYPE=duckdb to make it callable; the HTTP landing page shows the disabled tool and enable hint otherwise.

Features

Built on @cyanheads/mcp-ts-core: stdio and Streamable HTTP transports, pluggable auth (none / jwt / oauth), swappable storage (in-memory, filesystem, Supabase, Cloudflare KV/R2/D1), structured logging with optional OpenTelemetry tracing.

Fiscal Data-specific:

• All API values are strings; "null" means no value. Treasury dataframe columns are VARCHAR — CAST to DECIMAL or DATE for arithmetic and date comparisons. DataCanvas requires CANVAS_PROVIDER_TYPE=duckdb; configured canvas tools report canvas_unavailable otherwise.
• Curated catalog of 17 endpoints with field metadata — no discovery round-trip required; pass any endpoint path directly to treasury_query_dataset for datasets outside the catalog
• Convenience tools for the three most-queried datasets — national debt, interest rates, exchange rates
• DataCanvas integration: large pulls register as df_<id> dataframes queryable via DuckDB SQL, with automatic staging thresholds per tool
• No API key required — the US Treasury Fiscal Data API is free and public

Agent-friendly output:

• Provenance: filter-expression echo (applied_filters) and field-label maps (field_labels) let agents verify what was sent and read raw field names
• Enrichment notices: empty-result guidance, partial-country mismatches, canvas staging confirmations, and truncated-series warnings all name the next tool call
• Graceful truncation: series and query results carry truncated / retrieved_records / row_count_capped fields instead of silently dropping rows
• Canvas provenance: source tool, original query parameters, row count, and column schema surfaced by treasury_dataframe_describe

Getting started

Connect Claude Code to the public instance:

claude mcp add --transport http treasury-fiscaldata-mcp-server https://treasury-fiscaldata.caseyjhand.com/mcp

Or run it locally:

claude mcp add treasury-fiscaldata-mcp-server -- npx -y @cyanheads/treasury-fiscaldata-mcp-server

For other MCP clients:

{
  "mcpServers": {
    "treasury-fiscaldata-mcp-server": {
      "command": "npx",
      "args": ["-y", "@cyanheads/treasury-fiscaldata-mcp-server"]
    }
  }
}

No API key is required. DataCanvas is enabled by default in npm and Docker installs; CANVAS_PROVIDER_TYPE=none disables it. The portable Claude Desktop .mcpb bundle omits DuckDB native bindings and supports Treasury API queries with DataCanvas disabled. For Docker or a source build, see Running the server.

Configuration

| Variable | Description | Default | |:---------|:------------|:--------| | CANVAS_PROVIDER_TYPE | duckdb backs dataframe describe/query, and drop when enabled. With none, callable canvas tools return canvas_unavailable; drop stays off the tool list unless separately enabled. | duckdb (none in the desktop bundle) | | CANVAS_TTL_MS | Per-table TTL for DataCanvas dataframes in milliseconds. | 86400000 (24h) | | TREASURY_DATAFRAME_DROP_ENABLED | Register treasury_dataframe_drop as callable. Also requires CANVAS_PROVIDER_TYPE=duckdb. | false | | MCP_TRANSPORT_TYPE | Transport: stdio or http. | stdio | | MCP_HTTP_PORT | Port for HTTP server. | 3010 | | MCP_SESSION_MODE | HTTP session handling: auto, stateful, or stateless. Setting it overrides the server's own declaration; leaving it unset falls through to that declaration, not to the schema default. | stateless (declared in src/index.ts) | | MCP_AUTH_MODE | Auth mode: none, jwt, or oauth. | none | | MCP_LOG_LEVEL | Log level (debug, info, notice, warning, error). | info | | LOGS_DIR | Directory for log files (Node.js/Bun only). | <project-root>/logs | | LOG_TOOL_FAILURE_PAYLOADS | Log failed-call arguments and results, redacted by key name. Secrets inside free-form values are not redacted. | false | | LOG_TOOL_FAILURE_PAYLOAD_MAX_BYTES | Byte cap for each logged failed-call payload. | 16384 | | OTEL_ENABLED | Enable OpenTelemetry spans and metrics. | false | | OTEL_EXPORTER_OTLP_ENDPOINT | Base OTLP endpoint for traces and metrics. | Unset | | OTEL_EXPORTER_OTLP_LOGS_ENDPOINT | Explicit OTLP log endpoint; the base endpoint does not enable log export. | Unset |

See .env.example for the full lis