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

Modkeel

Modded Minecraft: which mod crashed, where to get a mod for your version, which mods work together.

Checks passed
13 / 22

1 failed · 8 not measured

Median response
1481 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
7

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?
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 1481 ms.

  • Pass
    Valid handshake

    protocolVersion 2025-11-25, serverInfo.name modkeel.

  • Pass
    Lists tools

    tools/list returned 7 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 1481 ms over 1 samples in 7 days. The bar is 1000 ms. Need at least 5 samples.

  • Not measured
    Consistent (p95)

    95th percentile 1481 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

    16 of 16 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 2026-10-16T21:16:39.517451Z, within 180 days.

  • Not measured
    Open-source licence

    No GitHub repository to ask about a licence.

Start using Modkeel

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 modkeel https://api.modkeel.com/mcp

Capabilities

Tools 7

check_mod_list

A whole mod list or modpack checked against the Modkeel lab at once: every pair in it that clashed, the mods whose jar crashed, the pairs that ran together, and the mods the lab has no data on. Use it for "will these mods work together?" or before updating a pack; for two mods, check_mod_pair is enough. Takes up to 300 mod ids (from names, search_mods first; unknown ids just land in untested_mods). With mc, only runs on that version count, and each crashed mod also gets the author's current build for it, since the crash is about the exact file the lab ran. verdict is problems_found when anything clashed or crashed, else no_known_problem, which is not a guarantee: pairs.tested out of pairs.total says how much of the list the lab covered.

Discovered
check_mod_pair

Whether two Minecraft mods ran together in the Modkeel lab, clashed, or were never tested together. Use it for "can I use X with Y?" or to check two suspects from diagnose_crash; for one mod's whole record, use get_mod_runs. Takes two mod ids in any order (from names, call search_mods first). Unknown ids are not an error: the verdict is untested, meaning no lab run, never a known conflict. With mc, only runs on that version count. clash wins if any run clashed. Returns the verdict and the runs behind it.

Discovered
diagnose_crash

Find the mod most likely behind a modded Minecraft crash (Fabric, NeoForge, Forge). Use it whenever the user shares a crash report or latest.log or says the game will not start. It is the only tool that reads logs, and it adds what the file does not hold: it checks every installed mod against the Modkeel lab (pairs in the pack that clashed, jars that crashed on that Minecraft version), says how many other players hit the same crash and which fix worked for them (when 10+ did), counts lab runs of each suspect, and ranks suspects by evidence (mixin, trace, missing class) with a confidence level (NONE when nothing points at a mod). It also returns a fix guide and, when the log names the Minecraft version and loader, the build to install for the suspect and for every installed mod the lab saw crash on that version, so no follow-up call is needed. Pass the whole file as text, unedited: trimming it loses the mod list; or, when the user gave a link to a paste (mclo.gs, pastebin.com, paste.ee, gist.github.com, modkeel.com), pass url instead and Modkeel fetches it. Text with no crash in it comes back as an error to fix and retry. Up to 4 MB; read and dropped, never stored.

Discovered
find_mod_download

The exact file to install for one mod on one Minecraft version and loader, with its download link. Use it for "where do I get X for 26.2 Fabric?", after diagnose_crash names a mod that needs another build, or when updating a pack to a new version. Checks, best first: the author's own build on Modrinth (status official: file, required mods, and lab runs of that exact file), a community port the Modkeel lab verified in one of its modpacks (port), the author's file for an earlier version that the lab ran on this one and saw start (older_build), a port the lab built from its public source and saw start but does not host (build_from_source: the repo, branch and how to build it), the loaders the author does build for that version (other_loader), else none; when that older file crashed in the lab instead, older_build says so and next_step warns against it. next_step says what the user can do in each case. For what the mod is, use get_mod_info; for whether it ran in the lab, get_mod_runs. Takes the mod's name as the user wrote it ("YUNG's Better Mineshafts"), a lab mod id or a Modrinth slug: no search_mods call needed first. Asks Modrinth live (two to five calls, nothing cached), so it can fail when Modrinth is down: retry.

Discovered
get_mod_info

What one Minecraft mod is and where to get it: its Modrinth page (title, summary, categories, loaders, the Minecraft releases its author lists, client/server side, licence, downloads, source and issue links) next to a short Modkeel lab record (tested versions, run and pair counts). Use it for "what does this mod do?", "is it client-only?", "where do I download it?" or to link a suspect from diagnose_crash. The versions here are what the author declares; for what the lab saw run or crash, use get_mod_runs, and for two mods together, check_mod_pair. Takes a lab mod id or a Modrinth slug; from a name, call search_mods first. The project is matched by the SHA-1 of a jar the lab ran (source: jar_hash, exact), else by slug (source: slug); a mod on neither returns found: false, not an error. Asks Modrinth live on each call (nothing cached here), so it can fail when Modrinth is down: retry later.

Discovered
get_mod_runs

Everything the Modkeel lab saw one Minecraft mod do: each Minecraft version where it ran on a server or a client, or crashed, and every mod it ran with or clashed with. Use it for "does this mod work on 1.21.1?", "which versions was it tested on?" or to check a suspect from diagnose_crash. For one specific pair of mods, check_mod_pair gives a direct verdict; for what the mod is and where to get it, get_mod_info. Takes a mod id; from a name, call search_mods first. A mod the lab never ran returns tested: false with empty lists, not an error. Returns every matching row, unpaginated: a few dozen at most per mod.

Discovered
search_mods

Turn a mod's display name or part of its id into the exact mod id the other lab tools take, and see which mods the Modkeel lab has data on. Use it first when you only have a name ("Entity Culling", "Sodium") or are unsure of the id; skip it when you already have the id. To download a mod, call find_mod_download with its name instead: it finds the mod itself. Matching ignores case, spaces and punctuation; best match first, then the mods with more lab data. An empty query lists every mod the lab tested. Returns each mod's id, the Minecraft versions it was tested on and how many runs and pairs it has, plus the total number of matches. No match means the lab has no data on that mod, not that it is broken (get_mod_info still finds it on Modrinth by slug). mc keeps only mods with a run on that exact version; limit caps the list, and total says how many matched.

Discovered

Recent measurements

Probe history

View status
Latest stored probes. Raw probe rows are kept for 14 days.
CheckedResultResponseTools
Connected1481 ms7