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

Hum Internet Availability

Check internet providers, plans, speeds, and known pricing at a specific U.S. street address.

Checks passed
12 / 22

2 failed · 8 not measured

Median response
576 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?
310
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 576 ms.

  • Pass
    Valid handshake

    protocolVersion 2025-11-25, serverInfo.name com.letshum/broadband.

  • 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 576 ms over 1 samples in 7 days. The bar is 1000 ms. Need at least 5 samples.

  • Not measured
    Consistent (p95)

    95th percentile 576 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

    0 of 16 parameters have a description (0%). 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 2026-08-27T21:48:21.418012Z, within 180 days.

  • Not measured
    Open-source licence

    No GitHub repository to ask about a licence.

Start using Hum Internet Availability

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 hum-internet-availability https://mcp.letshum.com/mcp

Capabilities

Tools 4

check_availability

Use this when someone asks what internet service or plans are available at a U.S. street address: providers, speeds and prices. U.S. addresses only; not for outages, speed tests or router troubleshooting. Start with {address}: the full street address, and include the apartment or unit in the address. Continue only with returned IDs: {candidate_id} (plus unit if asked) to pick an address, {lookup_id} to keep checking, or {lookup_id, question_set_id, answers}. Each call waits for live results; while status is checking, call again with lookup_id. Providers reported only in FCC area data were not checked at the address. Select only returned offer_id values.

Discovered
create_order

Only after presenting the current review and obtaining authorization for its terms_hash, commit with its validation_token and one stable idempotency_key. After a lost or uncertain response, call get_order first; do not blindly resubmit.

Discovered
get_order

Retrieve recorded fulfillment evidence with checkout_id, especially after a lost or uncertain create_order response. Public statuses do not prove ISP acceptance or installation confirmation.

Discovered
validate_order

Start: {"lookup_id":"<returned lookup_id>","offer_id":"<returned offer_id>"}. Poll: {"checkout_id":"<returned checkout_id>"}. Edit: {"checkout_id":"<returned checkout_id>","expected_revision":<current revision>,"details":{<changed fields>}}. Use exactly one shape. Customer, installation, consents and internet_addons belong inside details, never at the root. Start a checkout only when the customer asks to order. Each call waits for progress; while checking, poll with checkout_id only. Edits restart validation. On stale expected_revision, retrieve with checkout_id only before editing at the current revision. required_fields defines the contract; field_errors identifies actual missing/invalid fields relative to details. Refreshes the offer and returns an exact review without submitting an order. When preferred installation dates are required, provide both first and second choices using a time_window value allowed by the input schema. Installation type must be self or professional. Record the customer's explicit true or false choices for auto-pay and paperless billing; never enable them silently. Match the customer's equipment preference using returned equipment_options and catalog facts. Customer-owned equipment, included provider equipment and optional paid equipment are different choices. A free provider gateway does not satisfy an own-equipment request. Price or included status alone does not establish ownership. If an offer lacks the requested option, inspect another qualified offer or explain the limitation and ask the customer to choose; never fabricate an option. Send the complete selection in details.internet_addons using returned option_id and quantity values. Omit it to preserve current/default selections; [] declines optional items. Select at most one radio option and retain dependent parents. Ready means technically valid, not necessarily correct for the customer. Compare the entire review with the customer's budget, speed, equipment, billing and installation choices. Resolve mismatches before requesting authorization. Present every returned charge, discount, condition and unknown; do not invent a price adjustment for declined auto-pay or paperless billing. Never repeat the service PIN or full date of birth, even if supplied earlier. Keep capability IDs, terms_hash and validation_token out of customer-facing prose. Obtain explicit authorization for this exact current review before create_order; shopping intent or validation alone is not authorization.

Discovered

Recent measurements

Probe history

View status
Latest stored probes. Raw probe rows are kept for 14 days.
CheckedResultResponseTools
Connected576 ms4