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 · Data access / search

com.dropwatchhq/parcel-edge

Cook County IL commercial property-tax appeal leads: assessed value above recent arm's-length sale.

Checks passed
9 / 22

5 failed · 8 not measured

Median response
43 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
7

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?
410
Reliability & speedDoes it respond consistently and quickly?
004
Access & authenticationWhat is required to use this server?
102
Tool qualityAre the tool definitions usable by an agent?
220
Publisher identityCan the publisher be traced to its source?
222

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 43 ms.

  • Pass
    Valid handshake

    protocolVersion 2024-11-05, serverInfo.name parcel-edge.

  • Pass
    Lists tools

    tools/list returned 7 tools.

  • Fail
    Current protocol

    Negotiated 2024-11-05. The bar is 2025-06-18 or newer.

  • Pass
    HTTPS

    The endpoint URL is https.

Performance

  • Not measured
    Fast (p50)

    Median latency 43 ms over 1 samples in 7 days. The bar is 1000 ms. Need at least 5 samples.

  • Not measured
    Consistent (p95)

    95th percentile 43 ms over 1 samples in 7 days. The bar is 3000 ms. Need at least 20 samples.

  • Not measured
    Reliable (uptime)

    1 of 1 attempts returned a tool list in 30 days (100%). The bar is 99%. Need at least 30 samples.

  • Not measured
    Stable tool list

    Fewer than two successful probes in 30 days, so tool-list stability is not measured.

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.

  • Fail
    Parameters documented

    9 of 15 parameters have a description (60%). The bar is 80%.

  • Fail
    Safety hints

    7 tools set neither readOnlyHint nor destructiveHint.

Publisher

  • Pass
    Verified namespace

    Listed in the Official MCP Registry.

  • Fail
    Website matches publisher

    The website host does not match the reverse-domain namespace.

  • Fail
    Source repo linked

    No 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 2026-06-22T23:32:59.241545Z, within 180 days.

  • Not measured
    Open-source licence

    No GitHub repository to ask about a licence.

Start using com.dropwatchhq/parcel-edge

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 com-dropwatchhq-parcel-edge https://parceledge.dropwatchhq.com/mcp

Capabilities

Tools 7

construction_window_leads

Fresh ASSESSABLE construction permits (funded builds) entering the permit→financing window — prospects for hard-money / construction lenders racing the permit-to-loan gap. HONEST: loan-absence is UNVERIFIED (no current free per-parcel mortgage feed); this is a time-boxed absence-window WATCHLIST, re-checked as financing appears. Cook County. Permit amount, age, window status, applicant, work description.

Discovered
county_coverage

Covered counties, streams, buyers, data sources, methodology, and honest signal-density notes per stream. Free.

Discovered
exemption_flags

Non-conclusory exemption-contradiction FLAGS: parcels where a residential/homestead exemption coexists with a NON-OWNER-OCCUPANT owner of record (Allegheny: HOMESTEADFLAG=HOM + corporate owner; Cook: residential parcel deeded to an LLC/corp/trust grantee; Philadelphia: single-family homestead exclusion + entity owner; Travis TX: active 10% homestead appraisal cap on a homesite parcel + LLC owner; Fulton GA: homestead ExCode + entity owner; Harris TX: LLC/corporate owner on a residential parcel — owner-type watchlist, HCAD publishes no homestead boolean to confirm). Candidate improper exemptions for exemption-audit / recovery contractors (~30% contingency of recovered liens). Full owner/exemption EVIDENCE CHAIN. NEVER a fraud verdict — the contractor confirms occupancy. Counties: cook-il, allegheny-pa, philadelphia-pa, travis-tx, harris-tx, fulton-ga.

Discovered
lien_bundle_report

INVESTOR DESK (paid, $0.50 USDC/call; free preview): per-parcel tax-deed title-research report for a single Allegheny County PA PIN. Returns every UNSATISFIED County/School/Municipal tax lien on the parcel bundled into one surviving-lien stack with a per-taxing-body split + total, the tax-year span (a long tail signals a likely JUDICIAL 'free & clear' sale; a short one an UPSET sale where the buyer takes SUBJECT to surviving liens), and the PA statutory redemption posture (72 P.S. §5860 — PA has no general post-sale redemption; the risk is surviving liens). The cross-join a tax-deed investor pays $150–500/parcel for. CANDIDATE title input, NOT a title opinion — confirm sale type + named lienholders with the county/counsel before bidding.

Discovered
overassessment_leads

Scored, dated, deadline-stamped COMMERCIAL property-tax over-assessment leads. Each lead is a parcel whose assessor implied-market value EXCEEDS its most recent CLEAN arm's-length sale price — a candidate over-payment a contingency tax-appeal firm pursues. Counties that publish a public sale price: cook-il, allegheny-pa, philadelphia-pa, king-wa, maricopa-az. (Texas/Georgia counties are non-disclosure — over-assessment is an honest null there; use exemption_flags instead.) Candidates from PUBLIC data; the firm confirms valuation. Not legal/valuation advice.

Discovered
parcel_overassessment

Check a SINGLE Cook County PIN (14-digit) for over-assessment: latest certified AV + most recent clean sale, implied-market conversion, over-assessment ratio + appeal-window status. Free.

Discovered
stalled_surety

STALLED-PROJECT candidates for SURETY / DRAW-CONTROL firms + the exposed construction lender. Each is a large ASSESSABLE building permit (real funded build) whose status is still NOT CLOSED well PAST its size-appropriate build window — an issued-but-never-finaled permit (no certificate-of-occupancy proxy reached). Built off the SAME nightly Cook Assessor Permits pull; the permit carries its own status field. Permit amount, age, expected build window, overdue days/%, current status. HONEST: 'stalled' is a STATUS+RECENCY inference, NOT a verified work-stoppage (paperwork lag / phased builds / slow finaling can also leave a permit OPEN) — the surety/draw-control firm confirms on the ground. Counties that do NOT expose permit status return an honest null for this stream; Cook does, so it ships here. Cook County.

Discovered

Recent measurements

Probe history

View status
Latest stored probes. Raw probe rows are kept for 14 days.
CheckedResultResponseTools
Connected43 ms7