https://relay.clearly.sh/mcp ↗
Your workspace as agent tools — docs, canvases, slides, sheets, projects, tickets, and a shell.
Clearly is a remote MCP server published at relay.clearly.sh. It has been probed 7 times since 9/12/2026. It answered in 7 of them (100.0%), a near-uninterrupted record. Median response time is 1,549 ms, a delay an agent will notice. It offers a narrow, focused set of 3 tools. On the protocol side it still runs 2025-11-25 and has not moved to the newer spec.
Can an LLM agent pick the right tool here — names, descriptions and parameter clarity are assessed.
Risk: low
| Run | Era | Modern | ms | Legacy | ms | Versions |
|---|---|---|---|---|---|---|
| 2026-09-13 04:35:29 | Legacy | 200 | 1549 | 200 | 797 | 2025-06-18 |
| 2026-09-13 01:33:33 | Legacy | 200 | 1452 | 200 | 1061 | 2025-06-18 |
| 2026-09-12 23:31:36 | Legacy | 200 | 1257 | 200 | 1144 | 2025-06-18 |
| 2026-09-12 21:29:15 | Legacy | 200 | 1687 | 200 | 1996 | 2025-06-18 |
| 2026-09-12 19:27:29 | Legacy | 200 | 2342 | 200 | 1827 | 2025-06-18 |
| 2026-09-12 17:24:09 | Legacy | 200 | 2635 | 200 | 2845 | 2025-06-18 |
| 2026-09-12 15:21:42 | Legacy | 200 | 1021 | 200 | 1020 | 2025-06-18 |
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.
clearly_search_projectsSearch the Clearly directory of public projects (real estate listings, courses, startup data rooms, professional services, products, events, etc.). Returns ranked matches. Each result includes a public_slug usable with clearly_ask_project to chat with that project's AI agent. No auth required.
querystringrequiredcategorystringlimitnumberclearly_ask_projectTalk to a public Clearly project's AI agent. The agent has the owner-curated context (deck content, listing details, course material, product specs, etc.) and answers questions in natural language. No auth required. Pair with clearly_search_projects to discover projects, then ask follow-ups here. Pass a stable sessionId across calls to keep conversation memory.
publicSlugstringrequiredmessagestringrequiredsessionIdstringvisitorobjectclearly_capture_leadTell a Clearly project owner that you (or your user) want to be contacted. Use when the visitor signals real intent (wants a meeting, demo, pricing, tour, purchase). Owner receives a notification with the contact details. No auth required, but providing visitor email/phone is required so the owner can reach back.
publicSlugstringrequiredconversationIdstringcontactobjectrequiredintentstringrequiredmessagestringEach 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.
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/sh-clearly-clearly)<a href="https://mcpmetrics.io/servers/sh-clearly-clearly"><img src="https://mcpmetrics.io/badge/sh.clearly/clearly/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.
Carrier MCP — natural language control of your MVNO/eSIM fleet. 52 tools (43 OCS API wrappers + 8 AI intelligence + 1 OCS event history), 5 prompts, OAuth 2.1 + PKCE. Streamable HTTP on Cloudflare Workers.
Agent supply-chain security, scanner consensus, x402 reliability, and commerce MCP tools.
Multiple Gmail accounts, editable Google Sheets & Docs for AI agents. Deny-by-default access rules.
Agent-Native Google Slides - generate and edit React presentations
Free selector plus read-only GitHub bounty, agent harness, Actions, flake, and MCP drift decisions.
Read-only GitHub bounty, agent harness, Actions failure, flake, and MCP tool-drift decisions.
Comments
Sign in to write a comment
No comments yet. Be the first.