get_calendar_summary
Summarize new-issue municipal bond calendar by grouping dimension. Returns count and total par per group sorted by par descending for quick top-level analysis.
Instructions
Aggregate the new-issue calendar by a grouping dimension. Returns count and total par per group, sorted by par descending. Perfect for slides: 'NY leads this week at $1.2B across 8 deals; hospitals and schools dominate the sector mix.'
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| group_by | No | state | |
| top_n | No |
Implementation Reference
- server.py:422-441 (schema)Tool registration and schema for get_calendar_summary as part of list_tools(). Defines input properties: group_by (enum of state/sector/tax_status/bank_qualified/sale_method, defaults to state) and top_n (integer, defaults to 10).
Tool( name="get_calendar_summary", description=( "Aggregate the new-issue calendar by a grouping dimension. Returns " "count and total par per group, sorted by par descending. Perfect " "for slides: 'NY leads this week at $1.2B across 8 deals; hospitals " "and schools dominate the sector mix.'" ), inputSchema={ "type": "object", "properties": { "group_by": { "type": "string", "enum": ["state", "sector", "tax_status", "bank_qualified", "sale_method"], "default": "state", }, "top_n": {"type": "integer", "default": 10}, }, }, ), - server.py:924-951 (handler)Handler implementation inside _dispatch(): fetches the full calendar via fetch_calendar(), groups rows by the specified dimension (state/sector/tax_status/bank_qualified/sale_method), aggregates count and total_par per group, sorts by par descending, and returns top_n groups.
if name == "get_calendar_summary": cal = await fetch_calendar() rows = cal["all"] group_by = args.get("group_by", "state") key_map = { "state": lambda r: r.get("State", "?"), "sector": lambda r: r.get("_sector", "?"), "tax_status": lambda r: r.get("Tax Status", "?"), "bank_qualified": lambda r: r.get("Bank Qualified", "?"), "sale_method": lambda r: "—see sale_method split in pulse—", } keyer = key_map.get(group_by, key_map["state"]) agg: dict[str, dict[str, Any]] = {} for r in rows: k = keyer(r) slot = agg.setdefault(k, {"count": 0, "total_par": 0.0}) slot["count"] += 1 slot["total_par"] += float(r.get("_principal_num", "0") or 0) out = sorted( [ {"group": k, "count": v["count"], "total_par_usd": v["total_par"], "total_par_formatted": _fmt_amount(v["total_par"])} for k, v in agg.items() ], key=lambda x: x["total_par_usd"], reverse=True, )[: int(args.get("top_n", 10))] return {"group_by": group_by, "groups": out, "total_deals": len(rows)} - server.py:422-755 (registration)Tool is registered inside the list_tools() handler of the MCP server. Returned as part of the Tool list from @server.list_tools().
Tool( name="get_calendar_summary", description=( "Aggregate the new-issue calendar by a grouping dimension. Returns " "count and total par per group, sorted by par descending. Perfect " "for slides: 'NY leads this week at $1.2B across 8 deals; hospitals " "and schools dominate the sector mix.'" ), inputSchema={ "type": "object", "properties": { "group_by": { "type": "string", "enum": ["state", "sector", "tax_status", "bank_qualified", "sale_method"], "default": "state", }, "top_n": {"type": "integer", "default": 10}, }, }, ), Tool( name="classify_sector", description=( "Classify a muni bond issue description into a sector using the same " "keyword rules the calendar tool uses. Useful to show Marciano the " "classifier is deterministic, not a black box." ), inputSchema={ "type": "object", "properties": { "description": {"type": "string"}, }, "required": ["description"], }, ), Tool( name="get_recent_sales", description=( "Most actively traded muni CUSIPs right now from EMMA's " "/TradeData grid — description, coupon, maturity, high/low " "price & yield, trade count, total trade amount, and a link " "to each security's EMMA detail page. Use this to gauge " "live-market color for comparable deals." ), inputSchema={ "type": "object", "properties": {"limit": {"type": "integer", "default": 25}}, }, ), Tool( name="get_recent_preliminary_statements", description=( "Recent Preliminary Official Statements (POS) — pre-pricing " "documents filed right before a deal comes to market. This " "is the leading edge of the new-issue pipeline. Each row " "links to the filing PDF and the issuer page." ), inputSchema={ "type": "object", "properties": { "limit": {"type": "integer", "default": 25}, "issuer_contains": { "type": "string", "description": "Filter issuer (auto-expanded for abbreviations)", }, }, }, ), Tool( name="get_recent_annual_reports", description=( "Recent issuer annual financial reports filed as continuing " "disclosures — the source for post-issuance updated obligor " "financials (revenue, operating income, debt-service coverage)." ), inputSchema={ "type": "object", "properties": { "limit": {"type": "integer", "default": 25}, "issuer_contains": {"type": "string"}, }, }, ), Tool( name="search_issuers_by_state", description=( "List municipal issuers for a state (all 9k+ rows, not just " "page 1) and filter by name. Feed the issuer_id into " "get_issuer_outstanding_bonds or get_issuer_profile to drill " "down. IMPORTANT: the `contains` filter auto-expands your " "query into every EMMA abbreviation variant (hospital→HOSP, " "authority→AUTH, children→CHLDN, senior→SR, community→CMNTY, " "etc.) — always search in natural English, never in the " "telegraphic form. For hospital/senior-living/charter-school " "obligors, search the CONDUIT, not the obligor: e.g. CHLA " "bonds are filed under CALIFORNIA PUB FIN AUTH HEALTH CARE " "FACS REV — found by searching `contains=\"health care " "facilities\"`. See the emma://rules/EMMA_ABBREVIATIONS.md " "resource for the full variant map and conduit cheat sheet." ), inputSchema={ "type": "object", "properties": { "state": {"type": "string", "description": "2-letter state code"}, "contains": { "type": "string", "description": "Case-insensitive name filter", }, "limit": {"type": "integer", "default": 50}, }, "required": ["state"], }, ), Tool( name="get_issuer_outstanding_bonds", description=( "List an issuer's outstanding bond issues from their EMMA profile — " "issue description, dated date, maturity range. The most reliable " "drill-down on any issuer." ), inputSchema={ "type": "object", "properties": { "issuer_id": { "type": "string", "description": "EMMA issuer GUID (from search_issuers_by_state)", }, "issuer_url": { "type": "string", "description": "Any EMMA issuer URL (from emma_quick_search; can be a QuickSearch/Navigate redirect)", }, "limit": {"type": "integer", "default": 25}, }, }, ), Tool( name="get_issuer_profile", description=( "Full issuer profile: name, outstanding issues, attempted fetch of " "Official Statements, Pre-Sale docs, Continuing Disclosures, and " "Recent Trades. EMMA loads the latter via tab interaction; empty " "sections are reported honestly rather than guessed at." ), inputSchema={ "type": "object", "properties": { "issuer_id": {"type": "string", "description": "EMMA issuer GUID"}, "issuer_url": { "type": "string", "description": "Any EMMA issuer URL (from emma_quick_search)", }, }, }, ), Tool( name="get_security_details", description=( "Pull security-level fields for a 9-digit CUSIP: issuer, coupon, " "maturity, dated date, par. CUSIPs that are redeemed / matured / " "pre-refunded return a clear 'no records' response — try a " "currently-outstanding CUSIP from get_issuer_outstanding_bonds." ), inputSchema={ "type": "object", "properties": {"cusip": {"type": "string"}}, "required": ["cusip"], }, ), Tool( name="emma_quick_search", description=( "**START HERE** when the user names a specific obligor, issuer, " "or keyword. Uses EMMA's global quick search (the same box in " "EMMA's header) which indexes BOTH long-form and obligor-in-" "parens names — so 'Childrens Hospital' finds " "'CALIFORNIA HEALTH FACILITIES FINANCING AUTHORITY (LUCILE " "SALTER PACKARD CHILDRENS HOSPITAL AT STANFORD)' without " "needing the conduit-issuer chase. Returns matching issuers " "(across all states) and matching specific issues. Each " "issuer row has a URL you can feed into " "get_issuer_outstanding_bonds." ), inputSchema={ "type": "object", "properties": { "query": { "type": "string", "description": "Natural-language search: obligor name, issuer name, CUSIP, state, or keyword", }, "limit": {"type": "integer", "default": 25}, }, "required": ["query"], }, ), Tool( name="get_issue_details", description=( "Full IssueView page for a given IssueView URL — per-CUSIP " "detail (par at issuance, coupon, maturity, initial offering " "price, current LT rating, price, yield, and ratings from " "Fitch, KBRA, Moody's, S&P), the Official Statement PDF link, " "and recent trade activity. This is the single most " "information-dense page on EMMA for modeling a specific deal." ), inputSchema={ "type": "object", "properties": { "issue_url": { "type": "string", "description": "EMMA IssueView URL (https://emma.msrb.org/IssueView/Details/P#####)", } }, "required": ["issue_url"], }, ), Tool( name="get_recent_continuing_disclosures", description=( "Recent continuing-disclosure filings (audited financials, " "material events, rating changes, quarterly operating data). " "Each row has a direct link to the filed PDF. This is where " "post-issuance credit work lives — ratings today, not at " "issuance; updated obligor financials for modeling." ), inputSchema={ "type": "object", "properties": { "limit": {"type": "integer", "default": 50}, "disclosure_contains": { "type": "string", "description": "Filter disclosure description (auto-expanded for EMMA abbreviations)", }, "issuer_contains": { "type": "string", "description": "Filter issuer name (auto-expanded for EMMA abbreviations)", }, }, }, ), Tool( name="extract_pdf_text", description=( "Extract text from a previously-downloaded OS PDF so you can " "pull financials, debt service tables, obligor financials, " "rating language, bond purpose, sources-and-uses, etc. into " "an Excel model. Works best on OS PDFs saved via " "download_official_statement." ), inputSchema={ "type": "object", "properties": { "path": { "type": "string", "description": "Absolute path to the saved PDF", }, "pages": { "type": "string", "description": "Page range like '1-20' or '45,46,47' (optional — default: all)", }, "max_chars": { "type": "integer", "default": 120000, "description": "Cap on returned characters to protect context", }, }, "required": ["path"], }, ), Tool( name="get_recent_official_statements", description=( "List the EMMA Recent Official Statements grid — the 10 most " "recently filed OS documents across the muni market, with issuer, " "series, dated date, and a link back to the issuer. Feed a row's " "issue_url into get_official_statement_pdf to grab the PDF URL." ), inputSchema={ "type": "object", "properties": {"limit": {"type": "integer", "default": 10}}, }, ), Tool( name="get_official_statement_pdf", description=( "Given an EMMA IssueView/Details/P##### URL, return the direct " "Official Statement PDF URL (and issue title). This is the " "canonical primary-source OS — use it before quoting coupons, " "maturities, or call features." ), inputSchema={ "type": "object", "properties": { "issue_url": { "type": "string", "description": "EMMA IssueView URL (https://emma.msrb.org/IssueView/Details/P#####)", } }, "required": ["issue_url"], }, ), Tool( name="download_official_statement", description=( "Download an Official Statement PDF from EMMA to local disk. " "Pass either a direct PDF URL or an IssueView URL (the tool will " "resolve it to the PDF link). Returns file path + size. Use when " "the banker wants the OS to attach to a deck or read offline." ), inputSchema={ "type": "object", "properties": { "url": { "type": "string", "description": "Either a direct .pdf URL or an IssueView/Details/P##### URL", }, "filename": { "type": "string", "description": "Optional filename (without extension)", }, }, "required": ["url"], }, ), Tool( name="get_market_pulse", description=( "Snapshot of this week's muni primary market: total par, deal count, " "top 5 states, top 5 sectors, top 5 lead managers if available, " "competitive-vs-negotiated split. Built entirely from the live " "new-issue calendar — one call, boardroom-ready." ), inputSchema={"type": "object", "properties": {}}, ), ] - server.py:762-788 (helper)Helper function fetch_calendar() that loads the new-issue calendar from EMMA via headless browser, enriches rows with sector classification and parsed principal amount (_principal_num), and caches the result. It is called by get_calendar_summary to get the rows to aggregate.
async def fetch_calendar() -> dict[str, list[dict[str, str]]]: """Fetch the full new-issue calendar and return structured rows from each subtable (all / competitive / negotiated / recent sales). Enriches every row with inferred sector.""" cache_key = "_calendar" if (cached := cache_get(cache_key)) is not None: return cached tables = await load_tables(f"{EMMA_BASE}/ToolsAndResources/NewIssueCalendar") def _pull(table_id: str) -> list[dict[str, str]]: t = tables.get(table_id, {}) rows = structured(t.get("header", []), t.get("rows", [])) for r in rows: desc = r.get("Issuer Name/Issue Description", "") r["_sector"] = classify_sector(desc) r["_principal_num"] = str(_parse_amount(r.get("Principal Amount ($)", ""))) return rows payload = { "all": _pull("tblAllUpcomingIssues"), "competitive": _pull("tblCompetitiveUpcomingIssues"), "negotiated": _pull("tblNegotiatedUpcomingIssues"), "recent_sales": _pull("tblRecentSales"), } cache_put(cache_key, payload) return payload