https://observatory.horizonshield.dev/mcp ↗
Public record of one read only walk over the official MCP registry: who answered, tools, who pays.
MCP Observatory: one read only walk over every https endpoint in the official registry is a remote MCP server published at observatory.horizonshield.dev. It has been probed 9 times since 9/12/2026. It answered in 9 of them (100.0%), a near-uninterrupted record. Median response time is 481 ms, placing it among the faster endpoints. It offers a narrow, focused set of 6 tools. On the protocol side it speaks the 2026-07-28 stateless spec.
Can an LLM agent pick the right tool here — names, descriptions and parameter clarity are assessed.
mcp_observatory_lookup — Parameters 'address' and 'host' lack format examples (e.g., IPv4, domain).mcp_observatory_measure_now — No explicit error handling documentation beyond robots.txt compliance.mcp_observatory_summary — Description could clarify when to use it vs. 'state' for measurement context.Risk: low
tools/list structure, inputSchema validity, and a functional smoke test — the components of the 0-100 score.
Tools the server advertised in the latest measurement — measured, not catalog-claimed.
mcp_observatory_stateWhat was measured, when, over what population, and what the measurement cannot tell you. Read this before quoting any number from this server.
mcp_observatory_summaryThe counts, as published and as corrected. How many addresses answered, how many tools they exposed, how many stated who compensates their operator.
mcp_observatory_lookupWhat happened when we contacted one address, or an aggregate for one host. Returns the record hash and the procedure to recompute it. There is no tool here that lists addresses; you must already hold the one you are asking about.
addressstringhoststringmcp_observatory_disclosure_guideHow the 152 servers that stated who compensates their operator actually did it - the field names observed in the wild, with counts. Not a specification we invented.
mcp_observatory_measure_nowContact one https address now and report what we see: whether it speaks MCP, whether it carries an agent card, and whether that card names who compensates the operator. Read only; no tool is called. robots.txt is read first and honoured. This does NOT change the published record - the next full walk does that. Rate limited, because it contacts somebody else's server on your behalf.
addressstringrequiredmcp_observatory_methodHow the walk was run, what we got wrong and corrected, and the four rules the report holds itself to.
Derived by comparing consecutive probes — changes in era, protocol version, build and reachability.
Add this badge to your README — it updates automatically as measurements change.
[](https://mcpmetrics.io/servers/io-github-ogasurfproject-jpg-hs-mcp-observatory)<a href="https://mcpmetrics.io/servers/io-github-ogasurfproject-jpg-hs-mcp-observatory"><img src="https://mcpmetrics.io/badge/io.github.ogasurfproject-jpg/hs-mcp-observatory/era.svg" alt="mcpmetrics"></a>You are seeing the last 7 days. Sign up for the full history. Which check failed and why is in the dashboard.
Sign up free to seeThe catalog entries whose name and description are closest to this one, found with the same index the search box uses.
Find official Korean public datasets, agency-site menus, disclosure listings, and source URLs.
28 public tools for queues, inboxes, webhooks, approvals and temporary workflows. Two resources.
AI-operated. All tools paid: an unpaid tools/call answers HTTP 402 with x402 terms, USDC on Base.
Public wine registry and guides: search wines, grapes, regions, appellations. No account.
Argentina CUIT/CUIL validation and AFIP fiscal QR generation. Pure, no-auth MCP tools.
Normalized official data with provenance, aggregations, insights, free samples and agent access.
| Run | Era | Modern | ms | Legacy | ms | Versions |
|---|---|---|---|---|---|---|
| 2026-09-13 08:43:04 | Dual-era | 200 | 558 | 200 | 397 | 2025-11-25, 2026-07-28, 2025-06-18 |
| 2026-09-13 06:40:42 | Dual-era | 200 | 543 | 200 | 583 | 2025-11-25, 2026-07-28, 2025-06-18 |
| 2026-09-13 04:35:29 | Dual-era | 200 | 339 | 200 | 347 | 2025-11-25, 2026-07-28, 2025-06-18 |
| 2026-09-13 01:33:33 | Dual-era | 200 | 481 | 200 | 463 | 2025-11-25, 2026-07-28, 2025-06-18 |
| 2026-09-12 23:31:36 | Dual-era | 200 | 485 | 200 | 518 | 2025-11-25, 2026-07-28, 2025-06-18 |
| 2026-09-12 21:29:15 | Dual-era | 200 | 489 | 200 | 493 | 2025-11-25, 2026-07-28, 2025-06-18 |
| 2026-09-12 19:27:29 | Dual-era | 200 | 309 | 200 | 374 | 2025-11-25, 2026-07-28, 2025-06-18 |
| 2026-09-12 17:24:09 | Dual-era | 200 | 433 | 200 | 333 | 2025-11-25, 2026-07-28, 2025-06-18 |
| 2026-09-12 15:21:42 | Dual-era | 200 | 446 | 200 | 489 | 2025-11-25, 2026-07-28, 2025-06-18 |
Each block is one measurement round. Green: working response. Amber: responded but the server was returning errors (5xx). Red: no response at all.
Each cell is one probe run. Faded cells are incomplete probes — one leg did not answer, so the era is inconclusive.
The two probe legs separately: modern server/discover and legacy initialize.
Comments
Sign in to write a comment
No comments yet. Be the first.