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

TheDogs.app

Match dog breeds to your life, compare them, plan a test drive and estimate U.S. vet costs.

Checks passed
13 / 22

1 failed · 8 not measured

Median response
742 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
10

Tool definitions returned by this server

Independent monitoring

Health & checks

Status history

Outdated check

Last connection measurement is over 24 hours old. Current availability is unknown.

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?
312

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 742 ms.

  • Pass
    Valid handshake

    protocolVersion 2025-11-25, serverInfo.name thedogs-app.

  • Pass
    Lists tools

    tools/list returned 10 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 742 ms over 1 samples in 7 days. The bar is 1000 ms. Need at least 5 samples.

  • Not measured
    Consistent (p95)

    95th percentile 742 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

    54 of 54 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.

  • 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 2026-10-12T20:25:01.472626Z, within 180 days.

  • Not measured
    Open-source licence

    No GitHub repository to ask about a licence.

Start using TheDogs.app

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 thedogs-app https://mcp.thedogs.app/mcp

Capabilities

Tools 10

assess_breed_fit

Use this when the user asks whether a specific breed is right for them or what would make it work. It computes a personal fit score and rank for that breed. Reality-checks ONE named breed against the person's lifestyle with the TheDogs.app quiz scoring: overall fit %, its rank among 121 breeds for the same answers, a per-area breakdown (home, activity, experience, kids, shedding, barking, time alone, vet budget, strangers, trainability), the biggest mismatch, and which single change in the person's situation would raise the fit most. Use when someone asks 'is a <breed> right for me?', 'should I get a <breed>?' or 'what would make a <breed> work?'. The five key answers (home, activity, experience, kids, time alone) must come from the user: if any is unknown, ask for it first and never guess or assume a value. The rest default to neutral. Use match_dog_breeds instead when no breed is named. In apps that display widgets, a visual card with these results is shown to the user; there, keep your text reply short and do not repeat every number or list from the card. Do not use for symptoms, emergencies or treatment questions (refer the user to a veterinarian) or for training and behavior how-tos. If several of the five key answers are missing, ask for all of them in one short message, and reuse any answers the user already gave earlier in the conversation.

Discovered
compare_dog_breeds

Use this when the user compares two or three breeds or asks 'X or Y'. Compares 2–3 dog breeds on size, energy, shedding, barking, trainability, kid-friendliness and life expectancy, plus estimated vet costs (expected lifetime cost and modeled monthly insurance premium (benchmark, not a quote) at age 1, U.S. average prices). Use for 'X vs Y' questions. Estimates are statistical, not quotes or recommendations of a policy. In apps that display widgets, a visual card with these results is shown to the user; there, keep your text reply short and do not repeat every number or list from the card. Do not use for symptoms, emergencies or treatment questions (refer the user to a veterinarian) or for training and behavior how-tos. Do not use for cost questions outside the U.S.

Discovered
create_test_drive_plan

Use this when the user is unsure whether they are ready for a specific breed or wants to try life with it before adopting. Builds a short, practical try-before-you-adopt plan (3, 7 or 14 days) for ONE named breed, matched to the person's lifestyle: 3–8 concrete trials (daily exercise at the breed's level, workday/alone-time plan, coat care, noise, floor space, kids supervision, training commitment, and a dog-account budget using TheDogs.app vet-cost estimates), each with daily time ranges and a pass criterion. The trial that tests the person's biggest mismatch is marked decisive and comes first. Use when someone asks how to know if they're ready for a breed, wants to 'try before buying', or is unsure about a specific breed. The five key answers (home, activity, experience, kids, time alone) must come from the user: ask for any that are missing, never guess. Returns a plan_id: nothing is stored, so tell the user to save the summary. In apps that display widgets, a visual card with these results is shown to the user; there, keep your text reply short and do not repeat every number or list from the card. Do not use for symptoms, emergencies or treatment questions (refer the user to a veterinarian) or for training and behavior how-tos. If several of the five key answers are missing, ask for all of them in one short message, and reuse any answers the user already gave earlier in the conversation.

Discovered
estimate_dog_insurance_cost

Use this when the user asks what a specific dog breed will cost at the vet, whether pet insurance is worth it for their dog, or how deductible or reimbursement choices change their risk. It runs TheDogs.app's cost simulation for that breed, age and ZIP code. Simulates thousands of possible lifetimes for a U.S. dog of the given breed and age (breed health-registry data + U.S. vet cost ranges adjusted to ZIP code) and returns expected vet costs, the chance of a year with bills above the owner's emergency savings, the plan structure that keeps that risk under 5%, and a modeled monthly premium (benchmark, not a quote). Use when a user asks whether pet insurance is worth it for their dog, how much vet care or insurance costs for a breed, or how deductible and reimbursement levels change their risk. Present results as a statistical estimate, not as advice: do not tell the user to buy insurance or that 'the model suggests/recommends' a policy; say what the numbers show and leave the decision to the user. Always give the user the reportUrl link (full report with price-by-age chart and all 27 plan structures) and mention that it is an estimate, not a quote. In apps that display widgets, a visual card with these results is shown to the user; there, keep your text reply short and do not repeat every number or list from the card. Do not use for symptoms, emergencies or treatment questions (refer the user to a veterinarian) or for training and behavior how-tos. Do not use for cost questions outside the U.S.

Discovered
find_similar_breeds

Use this when the user loves a breed that may not fit them, or asks for a similar but easier breed. Finds breeds that share the look and personality of a breed the user is drawn to (e.g. 'I love Huskies but…', 'something like a German Shepherd but smaller/easier', 'dogs similar to a Golden'). Uses TheDogs.app look & personality tags plus AKC group. If the five key lifestyle answers are given, it only returns easier-to-find breeds that fit the user at least 10 points better than the loved breed, with their fit %; without answers it returns the closest look-and-vibe twins. Use match_dog_breeds when no breed is named, assess_breed_fit to check one breed. In apps that display widgets, a visual card with these results is shown to the user; there, keep your text reply short and do not repeat every number or list from the card. Do not use for symptoms, emergencies or treatment questions (refer the user to a veterinarian) or for training and behavior how-tos.

Discovered
get_arrival_checklist

Use this when the user is getting a dog soon and asks what to buy or prepare. Builds TheDogs.app's arrival checklist for a breed: what to have before the dog comes home, on day one and in the first week, sized for the breed (crate, harness), with breed-specific items (e.g. ramp for back-problem breeds, cooling mat for flat-faced breeds) and a 'don't buy yet' list. Optional lifestyle answers personalize it (apartment, alone all day, first dog). Use when the user is getting a dog soon, passed a test drive, or asks what to buy/prepare. The list is editorial, not sponsored; it contains no prices or shopping links. In apps that display widgets, a visual card is shown to the user; there, keep your text reply short and do not repeat every item from the card. Do not use for symptoms, emergencies or treatment questions (refer the user to a veterinarian) or for training and behavior how-tos.

Discovered
get_breed_profile

Use this when the user asks for a general overview of ONE named breed (what it's like, pros and cons, health watch). For a personal fit check use assess_breed_fit; to weigh 2–3 breeds use compare_dog_breeds; for vet costs use estimate_dog_insurance_cost. Returns TheDogs.app's (sarcastic but factual) profile of a dog breed: tagline, short description, strengths, Dr. Waggs' reality check, health watch list, key stats and breed-specific gear picks (product types chosen for the breed's health risks), with links to the full breed page and its vet-cost estimate. Health items are general breed tendencies, not a diagnosis. In apps that display widgets, a visual card with these results is shown to the user; there, keep your text reply short and do not repeat every number or list from the card.

Discovered
list_breeds

Use this when the user asks which breeds TheDogs.app covers or a breed name can't be matched. Lists dog breeds supported by the TheDogs.app pet insurance cost estimator, optionally filtered by a search term.

Discovered
match_dog_breeds

Use this when the user wants a personal recommendation of which dog breed suits their home, schedule, activity level, experience or family. It scores all 121 breeds with TheDogs.app's matching engine. Runs the TheDogs.app breed-matching quiz on 121 breeds and returns the top 3 matches as cards with a sarcastic tagline, why the breed works, Dr. Waggs' reality check and a link to the breed page. Use when someone asks which dog breed suits them. The five key answers (living situation, activity, experience, kids, time alone) must come from the user: if any is unknown, ask for it first and never guess or assume a value. The rest default to neutral. Always share the links. In apps that display widgets, a visual card with these results is shown to the user; there, keep your text reply short and do not repeat every number or list from the card. Do not use for symptoms, emergencies or treatment questions (refer the user to a veterinarian) or for training and behavior how-tos. If several of the five key answers are missing, ask for all of them in one short message, and reuse any answers the user already gave earlier in the conversation.

Discovered
review_test_drive

Use this when the user reports back on a TheDogs.app test drive plan (by plan ID or by describing how the trials went). Reviews a finished TheDogs.app test drive: takes the plan_id and, for each trial, whether it worked, was a struggle, or was skipped. Returns three blocks (Worked / Needs a solution / Not yet known), a fix for each struggle, an overall readout that weighs the decisive trial most, and better-matching, easier-to-find breeds when it didn't go well. Use when the user reports back on a test drive. Trial keys come from the plan (exercise, alone, coat, noise, space, kids, training, budget); map the user's words to them and leave out trials they didn't mention. Nothing is stored. In apps that display widgets, a visual card with these results is shown to the user; there, keep your text reply short and do not repeat every number or list from the card.

Discovered

Recent measurements

Probe history

View status
Latest stored probes. Raw probe rows are kept for 14 days.
CheckedResultResponseTools
Connected742 ms10