Skip to main content
Glama

mtgmon Mortgage Analytics

by io.github.lorenzopi
OverviewDiscussionsAdmin

Agency servicer analytics

get_servicer_analytics
Read-onlyIdempotent

Agency (Fannie Mae / Freddie Mac) servicer analytics in one of three modes.

  • mode='scorecard': largest servicers ranked by disclosed origination UPB for the current and previous year with average FICO and LTV. Returns data.servicers (top_n rows of {rank, name, volume, previous_volume, avg_fico, avg_ltv}), data.current_year, data.previous_year.

  • mode='performance': monthly CPR and 90+ day delinquency per top servicer for one origination vintage against the whole-book benchmark. Returns data.servicers {name: {cpr: [{date, value}], dq90: [...]}} downsampled to max_points, data.book {cpr, dq90}, data.vintage, data.latest_date.

  • mode='transfers': where one originator's Fannie Mae loans are serviced today and how servicing moved from the seller. Requires lender (canonical key from search_lenders). Returns data.seller_name, data.summary {loan_count, origination_upb, loans_with_transfer, pct_loans_with_transfer, total_transfer_events, ...}, data.latest_active_servicers {servicer, loans, upb, upb_share_pct}, data.top_routes and data.top_named_routes {from_servicer, to_servicer, events, event_share_pct}, data.first_to_latest {first_servicer, latest_servicer, loans, original_upb} (top_n rows each).

Use for: "largest servicers", "which servicer prepays fastest or has the worst DQ for the 2021 vintage", "who services Rocket's loans now". Do not use for: HMDA origination volume (get_lender_profile) or book-wide delinquency (get_loan_performance topic='delinquency').

Coverage is disclosed agency loans matched by seller/servicer name, not any servicer's full portfolio. UPB and volume are USD; CPR and DQ90 are percent.

Behavior: read-only, no auth or API key, no PII, idempotent and safe to retry. The public endpoint https://mtgmon.com/mcp allows about 60 requests/min and 250 tool calls/day per client IP. Result shape is {data, meta}; meta carries available, as_of, source_scope, weighting, units, cache_status, caveats, and truncated. If meta.available is false the data is unavailable or the cache is still warming (retry after a few seconds); never report it as zero.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
gseNo'all' = Fannie Mae + Freddie Mac combined (default), 'fnma' = Fannie Mae only, 'fhlmc' = Freddie Mac only. Used by scorecard and performance; transfers is Fannie Mae only.all
modeYes'scorecard' (servicers ranked by disclosed volume), 'performance' (per-servicer CPR and DQ90 series for one vintage), or 'transfers' (one lender's servicing-transfer routes; requires `lender`).
top_nNoMaximum servicers (scorecard, performance) or rows per route list (transfers), 1-25 (default 10).
lenderNoCanonical HMDA lender key: the exact `name` value from a search_lenders result, e.g. 'Rocket/Quicken' or 'United Wholesale Mortgage'. Legal names such as 'Rocket Mortgage, LLC' do not match and return meta.available=false. Required for mode='transfers'; ignored by other modes.
vintageNoOrigination year for mode='performance' (default 2021). Ignored by other modes.
max_pointsNoMaximum points per CPR/DQ90 series for mode='performance', 1-120 (default 60). Ignored by other modes.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
dataNo
metaYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed6 schema fields changed
    • addedInput schema / properties / gse / description
      Added value: +"'all' = Fannie Mae + Freddie Mac combined (default), 'fnma' = Fannie Mae only, 'fhlmc' = Freddie Mac only. Used by scorecard and performance; transfers is Fannie Mae only."
    • addedInput schema / properties / lender / description
      Added value: +"Canonical HMDA lender key: the exact `name` value from a search_lenders result, e.g. 'Rocket/Quicken' or 'United Wholesale Mortgage'. Legal names such as 'Rocket Mortgage, LLC' do not match and return meta.available=false. Required for mode='transfers'; ignored by other modes."
    • addedInput schema / properties / max_points / description
      Added value: +"Maximum points per CPR/DQ90 series for mode='performance', 1-120 (default 60). Ignored by other modes."
    • addedInput schema / properties / mode / description
      Added value: +"'scorecard' (servicers ranked by disclosed volume), 'performance' (per-servicer CPR and DQ90 series for one vintage), or 'transfers' (one lender's servicing-transfer routes; requires `lender`)."
    • addedInput schema / properties / top_n / description
      Added value: +"Maximum servicers (scorecard, performance) or rows per route list (transfers), 1-25 (default 10)."
    • addedInput schema / properties / vintage / description
      Added value: +"Origination year for mode='performance' (default 2021). Ignored by other modes."
  2. First observed

TDQS

A4.9/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false; the description adds substantial context beyond them: read-only, no auth/API key, no PII, idempotent and safe to retry, rate limits (60 req/min, 250 calls/day per IP), the {data, meta} response shape, and the critical meta.available=false cache-warming caveat with the instruction to never report it as zero. No contradiction with annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is long, but every sentence earns its place — modes, output shapes, use cases, exclusions, coverage limits, rate limits, response shape. It is front-loaded with the purpose and mode overview before behavioral details. Slightly verbose, but nothing is filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a three-mode, six-parameter tool with an output schema present, the description is exceptionally complete: per-mode return structures are spelled out, edge cases (cache warming, canonical key mismatch, coverage scope) are covered, and error interpretation (meta.available=false) is explained. An agent has everything needed to call it correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3, but the description adds real meaning beyond the schema: it explains that `lender` must be a canonical key from search_lenders and that legal names fail with meta.available=false, and it clarifies cross-parameter interactions (lender required only for transfers, vintage/max_points only for performance, gse ignored by transfers). This materially improves call correctness.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb+resource ('Agency (Fannie Mae / Freddie Mac) servicer analytics') and immediately enumerates three concrete modes with distinct output shapes (scorecard/performance/transfers). It names sibling alternatives (get_lender_profile, get_loan_performance) it is not, so an agent can disambiguate without opening schemas.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides explicit 'Use for:' examples ('largest servicers', 'which servicer prepays fastest...', 'who services Rocket's loans now') and explicit 'Do not use for:' exclusions naming the correct alternatives for each case. Nothing is left to inference.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All mtgmon Mortgage Analytics toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources