MCP HeartbeatTHE MCP OBSERVATORY
Public workspace

Explore

Evidence for your next connection.

Independent measurements of remote MCP servers. Every observation has a timestamp.

Read-only probes

MCP server · Knowledge & memory

CMD+RVL Receipts

Check claims against current public CMBS filings and NPORT-P coupons, with citations.

Checks passed
15 / 22

0 failed · 7 not measured

Median response
1056 ms

Median of successful probes over 7 days

30-day uptime
Not measured

Share of countable probes over 30 days, including daily rollups. Auth challenges are excluded.

Discovered tools
12

Tool definitions returned by this server

Independent monitoring

Health & checks

Status history

Responded

The server completed its last measured handshake. This is an observation, not a guarantee.

Last checked
Check summary by test group
Test areaPassedFailedUnmeasured
ConnectionCan a client connect and discover tools?
500
Reliability & speedDoes it respond consistently and quickly?
103
Access & authenticationWhat is required to use this server?
102
Tool qualityAre the tool definitions usable by an agent?
400
Publisher identityCan the publisher be traced to its source?
402

Unmeasured means there is not enough evidence to decide. How these checks work

Inspect individual checks 22 recorded

Core

  • Pass
    Reachable

    Latest probe returned HTTP 200 in 1187 ms.

  • Pass
    Valid handshake

    protocolVersion 2025-11-25, serverInfo.name cmdrvl-receipts.

  • Pass
    Lists tools

    tools/list returned 12 tools.

  • Pass
    Current protocol

    Negotiated 2025-11-25. The bar is 2025-06-18 or newer.

  • Pass
    HTTPS

    The endpoint URL is https.

Performance

  • Not measured
    Fast (p50)

    Median latency 1056 ms over 2 samples in 7 days. The bar is 1000 ms. Need at least 5 samples.

  • Not measured
    Consistent (p95)

    95th percentile 1174 ms over 2 samples in 7 days. The bar is 3000 ms. Need at least 20 samples.

  • Not measured
    Reliable (uptime)

    2 of 2 attempts returned a tool list in 30 days (100%). The bar is 99%. Need at least 30 samples.

  • Pass
    Stable tool list

    No tool was removed and no required parameter was added in the last 30 days.

Access

  • Pass
    Open access

    tools/list succeeded with no credential, and the record declares none.

  • Not measured
    Standard auth

    Auth is not required, so the OAuth metadata check does not apply.

  • Not measured
    Free tier cited

    No publisher quote has been checked.

Tools

  • Pass
    Tools described

    Every tool description is at least 20 characters.

  • Pass
    Valid input schemas

    Every inputSchema is a JSON Schema object.

  • Pass
    Parameters documented

    35 of 35 parameters have a description (100%). The bar is 80%.

  • Pass
    Safety hints

    Every tool sets readOnlyHint or destructiveHint.

Publisher

  • Pass
    Verified namespace

    Listed in the Official MCP Registry.

  • Pass
    Website matches publisher

    The website host matches the reverse-domain namespace.

  • Pass
    Source repo linked

    A repository URL is on file.

  • Not measured
    Repo owner matches

    This namespace is not an io.github login, so the owner comparison does not apply.

  • Pass
    Recently updated

    Updated 2026-11-02T18:28:06.284563Z, within 180 days.

  • Not measured
    Open-source licence

    The GitHub licence lookup has not returned an OSI result yet.

Start using CMD+RVL Receipts

Connect to this server

Choose your client, copy the configuration, then enable the server in your client’s MCP settings.

Run this command in your terminal, then restart Claude Code.

Claude Code

claude mcp add --transport http cmd-rvl-receipts https://receipts.cmdrvl.com/mcp

Capabilities

Tools 12

coverage

What this server covers: deals and loans against the universe, the field inventory with full bound definitions, counterparty roles, current-only scope, and dual-sourced agreement stats (single-source reported separately). An OUT_OF_COVERAGE answer means the deal or field is outside this coverage; UNVERIFIED means it is covered but could not be confirmed. Contact cairn@cmdrvl.com for deeper coverage, history, bonds, entitlements.

Discovered
covered_deals

List every deal this server can verify, with CIKs, aliases and filing periods. Returns the full covered set, which can be long.

Discovered
find_deals

Search covered deals by id, trust name, CIK, alias, shelf, vintage or deal_ref. An EXACT query returns one dominant result. A fuzzy query returns a small ranked set with match reasons, periods and a suggested next call. Returns at most the requested number of matches.

Discovered
quickstart

Compact capability manifest for clients: purpose, workflow, routing table, examples, vocabulary guard, scope caveats, next actions, and contact. A short, low-token summary of what this server does and what it returns.

Discovered
verify_appraised_value

Verify issuance appraised value (Annex A vs ABS-EE); a date or basis mismatch is DATE_INCOMMENSURATE / BASIS_INCOMMENSURATE, not DENY.

Discovered
verify_building_size

Verify issuance building size (Annex A vs ABS-EE); a unit mismatch is UNITS_INCOMMENSURATE, not DENY.

Discovered
verify_claims

Bulk verifier: paste text, get per-claim statuses. ASSERTIONS ONLY: a QUESTION ('is it $9.4M?') binds nothing and returns total 0; single-value questions are not claims and are not checked here. Deterministic grammar, four families: loan fields, pool fields, servicer identity, loan-status counts. Unparsed text is listed in unchecked_spans, never dropped. EXACT deal references (id, alias, CIK) work best; matching is never fuzzy. Statuses (verified / contradicted / insufficient_evidence / out_of_scope) are answers, not errors. Each claim has a claim_id, citations and a confidence.

Discovered
verify_counterparty

Adjudicate 'who is the <role> on deal X' against the SEC 10-D counterparty roster (today: master and special servicer). A SINGLE-SOURCE roster fact. Master is the roster party, NOT the ABS-EE tape's primary servicer. Pass claimed_name: CONFIRM/DENY under the ledger's name normalization, never fuzzy. Says WHO the party is, not that a loan is in special servicing. Unknown deal or role: OUT_OF_COVERAGE.

Discovered
verify_deal_field

Verify one pool-level field of a deal: the ABS-EE loan-tape rollup against the 10-D trustee's reported fact. These are COLLATERAL (loan-pool) balances and flows, NOT bond or certificate balances, and SCHEDULED and ACTUAL are different fields. No loan_id. Always the CURRENT period. Pass claimed_value; no claim: UNVERIFIED; an unknown deal or field: OUT_OF_COVERAGE.

Discovered
verify_fund_holding_coupon

Verify the NPORT cross-filer annualized coupon rate (annualized_rate) for one security identifier. Security-grain, N-source receipt: citations are peer NPORT-P filings by registrant CIK, dissenters included. CURRENT-ONLY (latest NPORT period exported). Ticker matches are not unique: set require_hard_identifier=true when a claim needs ISIN, CUSIP or other hard identity.

Discovered
verify_loan_field

Verify one loan-grain field of a CMBS loan against the SEC 10-D and ABS-EE filings. Values are TRUST-LEVEL (this trust's piece, not the whole loan). Always the CURRENT period; the receipt stamps its as-of. Pass claimed_value: you get CONFIRM / DENY / CONFLICT / UNVERIFIED plus an sf-receipt. No claim: UNVERIFIED. An unknown deal, loan or field: OUT_OF_COVERAGE.

Discovered
verify_loan_status_counts

Verify count claims over loan status ('N in special servicing / paid off / defeased') for a deal. Counts are DERIVED from the ABS-EE tape, not reported by any filing. Three grains, never mixed: activity (active, resolved_paid_off, defeased); servicing: in_special_servicing = loans CURRENTLY with the special servicer (the count for 'N in special servicing'; it OVERLAPS active, never sum); resolution reason (resolved_via_special_servicing and other payoff reasons) = loans that already LEFT the pool, NOT current counts. Pass `claimed` for exact per-status adjudication. Uncovered deal: UNVERIFIED.

Discovered

Recent measurements

Probe history

View status
Latest stored probes. Raw probe rows are kept for 14 days.
CheckedResultResponseTools
Connected1187 ms12
Connected925 ms12