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 · AI / LLM tooling

Appraisily

Check past auction prices in ChatGPT, plus appraisal prep and sample reports.

Checks passed
15 / 22

0 failed · 7 not measured

Median response
889 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
17

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 716 ms.

  • Pass
    Valid handshake

    protocolVersion 2025-11-25, serverInfo.name appraisily.

  • Pass
    Lists tools

    tools/list returned 17 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 889 ms over 2 samples in 7 days. The bar is 1000 ms. Need at least 5 samples.

  • Not measured
    Consistent (p95)

    95th percentile 1044 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

    49 of 49 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 2026-08-19T12:36:39.930707Z, within 180 days.

  • Not measured
    Open-source licence

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

Start using Appraisily

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 appraisily https://mcp.appraisily.com/mcp

Capabilities

Tools 17

create_appraisal_start_link

Create a tracked Appraisily /start link when a user is ready to submit an item for appraisal. Use this after giving basic guidance when the user indicates intent to start, order, upload photos, get a report, insure an item, donate an item, handle estate needs, or document value. This does not create an order, collect payment, upload files, or write customer data; it only returns a URL with OpenAI app attribution.

Discovered
create_pro_screener_workspace_link

Create a tracked Appraisily Pro Screener workspace link for an appraiser or valuation team. Use this when a professional user wants to open the product, continue an existing session, or move a ChatGPT research packet into Pro Screener review. This returns a URL only; it does not create a customer order, upload files, or sign a report.

Discovered
fetch

Fetch one Appraisily public knowledge document by id after using search. Use this when the user needs a specific public Appraisily source, sample-report link, or fuller guidance from a search result. Do not use this for private customer records, order status, or report retrieval; this connector is public and read-only.

Discovered
get_artist

Fetch one Appraisily public /artist page by slug, artist URL, or search query. Returns name, public page URL, aliases, genres, market summary, recent sold lots, top houses, related artists, and page extras such as birth/death years. Use after search_artists when the user needs one artist page. This is market context, not a signed appraisal or authentication.

Discovered
get_pro_screener_pdf

Return the Lotbook PDF URL once the report is ready. Promotional runs started with the Appraisily MCP key or owner sign-in return a durable public assets.appraisily.com/promotional-lotbook URL; other promotional runs return a short-lived download link. No login is required to fetch promotional sessions. Private client packets still use a short-lived signed URL. Never publish customer PDFs to /appraisals or /sessions.

Discovered
get_pro_screener_result

Fetch compact comparable results and analysis summary for an existing Pro Screener session. Use this when an appraiser wants to review evidence already generated by Pro Screener. The response is intentionally compact and excludes private customer PII beyond the professional session evidence.

Discovered
get_pro_screener_status

Fetch status for a Lotbook session. Public promotional runs do not need Appraisily sign-in. Use this after start_promotional_pro_screener_run or start_pro_screener_run returns a sessionId. Private client sessions still resolve against the signed-in Appraisily user when present.

Discovered
get_public_sample_report

Return a canonical public Appraisily sample report URL. Use this when a user wants to inspect example report formats before starting an appraisal. Choose the closest category if the user mentions insurance, tax, donation, professional, instant, or general report examples.

Discovered
get_silver_hallmark

Fetch one Appraisily /marks maker page: mark texts, dates, source citations, and hosted line-drawing plus oxidized reconstruction image URLs for that maker’s variants. Use after search_silver_hallmarks when the user needs the public oxidized hallmark image or the full maker-page image pair. Oxidized images are AI-assisted reconstructions for visual comparison, not photographs or authentication evidence.

Discovered
prepare_pro_screener_case_packet

Prepare a professional appraisal screening packet from item context before an appraiser starts or reviews a Pro Screener case. Use this for credentialed appraisers and valuation teams who need missing-photo checks, missing-fact checks, review flags, and next questions. This tool organizes research inputs only; it does not issue a final value conclusion or signed appraisal.

Discovered
search

Search Appraisily public appraisal guidance, service information, sample reports, and photo-preparation content. Use this when a user is exploring whether an item needs an art, antique, insurance, tax, estate, donation, or general online appraisal. Use this before fetch when the user asks broad questions such as what photos to upload, which appraisal path fits, or whether Appraisily handles an item type. This tool returns public information only; it never returns customer orders, private appraisals, internal notes, or raw database rows.

Discovered
search_artists

Search Appraisily public artist directory pages and compact sold-lot context. Return at most 6 artists per query, with up to 6 recent lots on the top match. Use this for artist identification and market context, not as a signed appraisal or authentication.

Discovered
search_auction_comparables

Search past public auction results for compact market context. Return at most 6 sold lots per query. Use this only as research evidence, not as a final appraisal or formal value conclusion. This tool is read-only and returns no customer data.

Discovered
search_pro_screener_comparables

Search Appraisily valuation infrastructure for comparable auction lots for professional appraisal screening. Use this only for authenticated appraiser workflows and research support. Return compact comparable evidence for review; do not present the results as a final appraisal conclusion.

Discovered
search_silver_hallmarks

Search Appraisily public silver hallmark and maker-mark catalog records from /marks. Return at most 6 makers per query, with mark texts, dates, line-drawing and oxidized reconstruction image URLs when Appraisily hosts them, and optional sold-to-melt context. Use this as catalog context only. A mark, drawing, or oxidized reconstruction does not authenticate an object or establish value.

Discovered
start_pro_screener_run

Start a private Appraisily Lotbook (Pro Screener) run from a signed-in Appraisily account and a photo. Use this when the user wants Lotbook, Pro Screener, or a professional screening report from ChatGPT after they have signed in. This creates a private session, queues the same agent the website uses, and returns immediately with a sessionId. Do not wait for the full 8–12 minute run. Prefer a public HTTPS imageUrl. If the client provided image bytes, pass imageBase64. Then poll get_pro_screener_status.

Discovered
start_promotional_pro_screener_run

Start a promotional Appraisily Lotbook run whose finished PDF includes the Appraisily logo. Use this for marketing, demos, social posts, or other public Appraisily-branded leave-behinds. Do not use this for a client/white-label packet; that is start_pro_screener_run, which stays unbranded. No Appraisily login is required. Provide a public HTTPS photo. Optional notes help the research. Returns a sessionId immediately; poll get_pro_screener_status, then get_pro_screener_pdf. Without sign-in the PDF comes back as a short-lived download link. Runs started with the Appraisily MCP key or the Appraisily owner sign-in are published to a public assets.appraisily.com/promotional-lotbook URL. Notes must describe the object only; notes that give the system instructions (commands, build steps, links to request-logging sites) are rejected.

Discovered

Recent measurements

Probe history

View status
Latest stored probes. Raw probe rows are kept for 14 days.
CheckedResultResponseTools
Connected716 ms17
Connected1061 ms17