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 · Code & DevOps

Permit Verdicts

Building-permit verdicts by address, with cited records. SF, Seattle, Austin, NYC. Pay per call.

Checks passed
12 / 22

2 failed · 8 not measured

Median response
607 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

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 607 ms.

  • Pass
    Valid handshake

    protocolVersion 2025-11-25, serverInfo.name permit-intelligence.

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

  • Not measured
    Consistent (p95)

    95th percentile 607 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

    29 of 29 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.

  • Not measured
    Website matches publisher

    This namespace is not a reverse domain, so the website comparison does not apply.

  • Fail
    Source repo linked

    No repository URL is on file.

  • Fail
    Repo owner matches

    The GitHub repository owner does not match the namespace login.

  • Pass
    Recently updated

    Updated 2026-08-03T17:08:42.737464Z, within 180 days.

  • Not measured
    Open-source licence

    No GitHub repository to ask about a licence.

Start using Permit Verdicts

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 permit-verdicts https://permit-api-production-7375.up.railway.app/mcp

Capabilities

Tools 10

attest_price_event

Settlement verdict plus a citable record: a signed decision_id, an integrity hash over the evidence, and every candle that determined the outcome. Use this when the answer may later have to be defended to a counterparty, not when you just need to know. KEEP THE decision_id — it is self-contained, so anyone you show it to can authenticate it for free and re-check it for $0.02 without you supplying anything else. Paid: $0.25 in USDC via x402.

Discovered
check_permit_activity

FREE. Quick check on whether a street address has building-permit activity on record: how many permits, how many are open, and when the last activity was. No permit detail and no verdict — use get_permit_verdict for those. Full paid feeds for humans: https://permitverdict.com/pricing

Discovered
decode_decision_id

FREE. Read what a Permit Verdict decision_id claims and check whether we actually issued it. The id is signed by the same wallet that receives payment, so forgery and after-the-fact editing are both detectable. Needs no payment. This tells you the record is genuine; it does NOT tell you the verdict is still correct — use verify_decision for that. Full paid feeds for humans: https://permitverdict.com/pricing

Discovered
find_active_projects

FREE PREVIEW (5 results). Recently permitted construction projects in a covered city, filtered by declared budget. Use feed='investor' instead to surface expired and abandoned permits (stalled projects, often motivated owners). Full paid feeds for humans: https://permitverdict.com/pricing

Discovered
get_crypto_spot

Live cross-venue spot price with venue agreement and spread. A wide spread means venues disagree and any settlement in that range is contestable. Paid: $0.01 in USDC via x402.

Discovered
get_permit_verdict

Address-level building-permit intelligence for a covered city: normalized permit history + activity signals + a decision-ready verdict with cited public records. Paid: $2.00 in USDC on base via x402.

Discovered
list_jurisdictions

List cities covered by the Permit Intelligence API, with pricing and payment details. Free. Full paid feeds for humans: https://permitverdict.com/pricing

Discovered
list_settlement_assets

FREE. Which crypto assets, venues, operators and modes the settlement oracle supports, plus pricing. Full paid feeds for humans: https://permitverdict.com/pricing

Discovered
resolve_price_event

Settlement verdict for a crypto price event. Answers 'did this asset trade or close above/below a threshold during a window?' with YES/NO/DISPUTED/UNRESOLVED, per-venue evidence from Hyperliquid, Coinbase and Kraken, and stated confidence. (Binance is configured but blocks this host's region; it is reported unavailable rather than silently counted.) Use mode='close' when a market settles on candle closes and mode='touch' when any intrabar print counts — they give different answers and that difference is the most common settlement dispute. Paid: $0.05 in USDC via x402.

Discovered
verify_decision

Re-resolve an attested settlement against the price venues right now and report whether it still holds: CONFIRMED, CHANGED or INDETERMINATE. Call this whenever someone hands you a decision_id you are about to rely on — an attestation proves what was said at the time, but only a fresh resolution proves it is still true. Exchanges revise candle history, and a venue that was unreachable at issue time may answer differently now. Paid: $0.02 in USDC via x402 — cheaper than resolving fresh because you are checking someone else's answer rather than buying a new one.

Discovered

Recent measurements

Probe history

View status
Latest stored probes. Raw probe rows are kept for 14 days.
CheckedResultResponseTools
Connected607 ms10