Conduit loan sizer on 2026 CMBS underwriting MCP server

Which MCP servers are Conduit loan sizer on 2026 CMBS underwriting's own, from the official registry and from asking its own domain, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.

read 2026-11-01

← Back to Conduit loan sizer on 2026 CMBS underwriting

Whose server it is

Registry nameloans.conduit/conduit-loansverified in the MCP registry

The registry name sits under conduit.loans. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.

When we asked itchecked 2026-11-01

Stateanswerschecked 2026-11-01
Tools2
Server calls itselfconduit-loans
Server version1.0.0
Protocol version2025-06-18

On 2026-11-01 the server answered initialize and tools/list without a sign-in. First answer in 114 ms.

Should an agent connect itNot proven either way yet

Its tools do estimate the largest conduit loan a property can carry; see which lender test limits the loan size, but not estimate prepayment cost on a conduit loan.
Checked on 2 of the 7 days it takes to judge reliability.

Once connected

For "estimate the largest conduit loan a property can carry", the likely first call is size_conduit_loan.
For "see which lender test limits the loan size", the likely first call is size_conduit_loan.

Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.

Measured dailydaily checks: 2, the first on 2026-11-01

INITE MCP scoreafter a weeka score needs 7 daily checks: 2 so far
What an agent can do with it2 of 3 use cases
Answeredmeasuring2 of the 7 daily checks it takes to print a share
Median first answer366 ms
Space in an agent's context≈ 791 tokensthe definitions of all its tools (2), which an agent carries on every turn
Tool definitionsA · 100 of 100
Typed results0 of 2 toolsdeclared outputSchema: results come typed, read once

Every tool passes all six checks.

What an agent can do with it

can do · estimate the largest conduit loan a property can carry
can do · see which lender test limits the loan size
cannot · estimate prepayment cost on a conduit loan

Each of the product's use cases, put to Jev against this server's tool list: can an agent do it with these tools?

Worth a look

None of the five warning signs in these definitions.

A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (25%), doing the product's job (25%), definitions (20%), context (10%), use (10%) and how readily a client connects (10%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →

Tools it offers2 tools · read 2026-11-01

current_underwriting
Debt service coverage (DSCR), loan-to-value, debt yield and coupon percentiles (10th to 90th) plus the share of full-term interest-only loans for CMBS conduit loans originated in the last 12 months, read from the trusts' own SEC ABS-EE…
size_conduit_loan
Maximum CMBS conduit loan for a property from its NOI and value: runs the coverage (DSCR), loan-to-value and debt yield tests and says which one binds, with debt service and the resulting ratios. Defaults are the edge of what last year's…

How to connect

Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:

{
  "mcpServers": {
    "conduit-loans": {
      "type": "http",
      "url": "https://conduit.loans/mcp"
    }
  }
}

Add it

Claude Code, in a terminal

claude mcp add --transport http conduit https://conduit.loans/mcp

Add to Cursor Add to VS Code

claude.ai, ChatGPT and other clients: add https://conduit.loans/mcp as a custom connector in the settings.

Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.