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 · Other

McClipFace

McClipFace finds current coupon codes, promo codes, deals and discounts for stores and products.

Checks passed
12 / 22

2 failed · 8 not measured

Median response
1462 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
4

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?
004
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?
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 1462 ms.

  • Pass
    Valid handshake

    protocolVersion 2025-11-25, serverInfo.name clippy-mc-clipface.

  • Pass
    Lists tools

    tools/list returned 4 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 1462 ms over 1 samples in 7 days. The bar is 1000 ms. Need at least 5 samples.

  • Not measured
    Consistent (p95)

    95th percentile 1462 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.

  • Pass
    Parameters documented

    23 of 23 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.

  • 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 2026-10-30T22:20:58.161312Z, within 180 days.

  • Not measured
    Open-source licence

    No GitHub repository to ask about a licence.

Start using McClipFace

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 mcclipface https://mcclipface.com/mcp

Capabilities

Tools 4

discover_deals

Deals and discounts across stores; use it for browsing with no store named. No arguments for general deals, or non-sensitive categories/keywords for the shopper's interests. Present as a short curated edit with each pick's match_reason.

Discovered
find_coupons

Current coupon codes, promo codes, discount codes and deals for one store the shopper names (also when they ask to buy or check out there). Optional target_url/target_urls: a picked product page for a deep link. Results carry the rules that apply to them.

Discovered
find_product_coupons

Coupon codes, promo codes and discount codes for a named product across stores; product codes work only on that item. For a store, use find_coupons.

Discovered
report_coupon_result

Call this the turn the shopper says a code worked or failed. Records whether a coupon code or no-code deal tried at checkout worked (merchant and code for codes, including a code found outside McClipFace, with merchant as the store's domain; offer_id for no-code deals). Not a lookup. Stores no personal or cart data. Optional and off by default (Private mode, which lasts until the shopper changes it). Report only a confirmed result (the shopper says a code worked or was rejected, or a no-code deal did or didn't apply, or you saw it at checkout), never because a code was found, shown or copied. A result you saw counts only if you tried the code with checkout tools the shopper authorized, never an untested or unfinished one. One call per distinct code tested; a success counts even if another code saved more. Consent: report only in Community mode. At the first confirmed success in a conversation, once the purchase is done or declined (never mid-try, mid-purchase, next to the cart offer, or before or instead of a search), ask once: "Success! <code> worked: <saving> off. Want to turn on Community mode so other shoppers get this code too? Only the store, the code and the result are shared, never your cart or anything about you. (Yes / No)" Fill in the real code; leave out ": <saving> off" if the saving isn't known; start with "I tried N codes and" only if you tested them yourself, never for a code the shopper reports. If a try ends with no code working, ask once instead: "None of these worked. Want to turn on Community mode so other shoppers can skip codes that don't work? Only the store, the codes and the results are shared, never your cart or anything about you. (Yes / No)" Yes turns Community mode on for that conversation: report that result and later confirmed results, the shopper's and yours, until the shopper turns it off. No, or no answer, means report nothing and don't ask again in that conversation. It carries to later conversations only if the shopper agreed to remembering it and you noted the version and choice; then ask again only for a newer version. A Community mode yes given to older wording that didn't say the store and code are shared doesn't count: stay in Private mode until the shopper says yes to the current question. No answer is no consent; never infer it from install, lookups or coupon tests. McClipFace can't verify consent, only your statement of it. Keep shopping either way; follow the host's tool approvals. Report once per offer and outcome; for a no-code deal, pass offer_id with outcome worked, didnt_work or not_found. Send only the store, the code or offer_id, the outcome, and optionally reason; never amounts, cart, totals or user data. Commission disclosure for the links the lookup tools return: Offers with tracked=true use affiliate links: a purchase through one may earn a commission at no extra cost. Say so once per chat, before you first share or open one: "This is an affiliate link and may earn a commission at no extra cost to you." Codes are ranked on the code itself. Results come only from affiliate programs McClipFace has joined, its licensed coupon data partner, stores that share their codes with McClipFace directly and codes shoppers reported working at checkout. Commission never affects which offers are returned or how they are ranked. It never puts a pricier option first.

Discovered

Recent measurements

Probe history

View status
Latest stored probes. Raw probe rows are kept for 14 days.
CheckedResultResponseTools
Connected1462 ms4