Glimind

Official12 tools

by shawndei

Live reliability for AI agent tools: is it working right now, and how do I call it correctly?

Monitor tool reliability and verify correct API usage for AI agent integrations.

Captured live from the server via tools/list.

route_task

Give a task in plain language and get the SINGLE BEST live tool to do it, ready to call: the chosen tool's verdict + reliability score, its input schema and a known-good recipe, call hints (timeout/retry), PLUS a ranked fallback chain to try if it fails. One call replaces discover_tools + check_tool_reliability + prepare_tool_call + find_alternatives. Call this at the start of a task when you don't already know which tool to use — it picks the best one and tells you exactly how to call it.

Parameters (3)

taskstringrequired
Plain-language description of what you want to do (e.g. 'send a slack message').
categorystring
Optional capability category to narrow the choice.
fallbacksnumber
How many backup tools to return (default 3, max 8).

check_tool_reliability

Call this BEFORE invoking any external MCP tool or API to check if it is working RIGHT NOW. Returns a verdict (healthy | degraded | down | unknown) plus the live success rate from real agent usage in the last hour, typical p50/p95 latency, top current error signatures, and any active breakage. Use it to decide whether to call a tool, choose a fallback, or tune timeouts and retries — it prevents wasted calls and dead-ends on broken tools. Cheap and fast; safe to call routinely before tool use.

Parameters (1)

toolIdstringrequired
Identifier of the tool to check: a server id (e.g. 'mcp-registry/acme') or 'server/tool_name' for a specific tool.

get_working_recipe

Get a CURRENTLY-WORKING call pattern (input shape) for a tool, distilled from real successful calls by other agents. Call this when you are unsure how to shape a tool's inputs, or right after a tool call failed and you want a structure known to succeed now. Returns value-free shape skeletons (privacy-preserving — never real argument values), ranked by recent success, with observed success rate and latency. Optionally filter by a coarse task tag.

Parameters (2)

toolIdstringrequired
Tool identifier ('server' or 'server/tool_name').
taskstring
Optional coarse task tag to narrow the recipe.

prepare_tool_call

The one call to make right before using a tool. Returns, in a single round-trip: is it healthy now (verdict + recommendation), a known-good input shape (recipe) for it, and — if it is down or risky — LIVE alternative tools that do the same job. Use this instead of calling check + recipe + alternatives separately. It tells you whether to proceed, how to call it, or what to call instead.

Parameters (2)

toolIdstringrequired
Tool you are about to call ('server' or 'server/tool_name').
taskstring
Optional coarse task tag to tailor the recipe/alternatives.

discover_tools

Find LIVE tools that can accomplish a task you describe in plain language — call this when you do NOT yet know which tool to use. Unlike find_alternatives / find_related_tools (which need a tool id you already have), this takes a free-text capability query (e.g. 'send a slack message', 'convert currency', 'search arxiv papers') and returns ready-to-use tool ids ranked by semantic similarity, filtered to tools that are live right now. The discovery entry point at the start of a new task.

Parameters (3)

querystringrequired
Plain-language description of the capability you need (e.g. 'send an email').
categorystring
Optional capability category to narrow results.
limitnumber
Max results (default 8, max 25).

find_alternatives

Find LIVE tools that do a similar job to a given tool — call this when a tool is down, rate-limited, or missing, to get a working substitute ranked by capability similarity and real traffic. Returns ready-to-use tool ids you can switch to immediately.

Parameters (2)

toolIdstringrequired
The tool you want a substitute for.
taskstring
Optional coarse task tag.

preflight_tools

Pre-flight a WHOLE task in one call: pass every tool you might use and get a compact verdict + recommendation (proceed | proceed_with_caution | avoid) for each, so you can plan around broken tools before you start. Call this once at the beginning of a multi-tool task instead of checking tools one at a time.

Parameters (1)

toolIdsarrayrequired
Tool identifiers you plan to use (up to 50).

find_related_tools

Discover tools that other agents commonly use TOGETHER with a given tool (from real usage). Call this to find the complementary tools you'll likely need next for a task, or to discover better-fitting tools you didn't know existed.

Parameters (1)

toolIdstringrequired
The tool to find companions for.

watch_tool

Subscribe to reliability alerts for one or more tools (or all critical outages). Provide a `webhook` URL (generic, Slack, or Discord — auto-detected) to receive PUSH alerts, or omit it to get a pull `token` you poll with get_notifications (no inbound URL needed — ideal for agents). Call this to be told the moment a tool you depend on breaks or recovers. Returns a token to manage/poll the subscription.

Parameters (5)

toolIdstring
A tool to watch ('server' or 'server/tool_name').
toolsarray
Multiple tools to watch.
webhookstring
Optional push URL (generic/Slack/Discord). Omit for a pull token.
allCriticalboolean
Watch ALL critical breakages across the ecosystem.
minSeveritystring
'warning' (default) or 'critical'.

get_notifications

Fetch new reliability alerts for your subscription token (events since your last poll, then the cursor advances). Use this after watch_tool without a webhook to react to outages/recoveries — no public endpoint required. Returns events with tool id, severity, and a link.

Parameters (2)

tokenstringrequired
The token returned by watch_tool.
limitnumber
Max events (default 50).

unwatch

Cancel a subscription created by watch_tool, using its token.

Parameters (1)

tokenstringrequired
The subscription token.

list_breakages

List tools across the MCP ecosystem whose real-world success rate just dropped sharply (active outages/regressions), newest and most severe first. Call this to steer away from tools that are currently broken, or to monitor the health of tools your task depends on. Backed by real-usage outcome data, so it catches breakages before status pages do.

Parameters (1)

limitnumber
Max results (default 25).

Install

Tools (12)

route_taskcheck_tool_reliabilityget_working_recipeprepare_tool_calldiscover_toolsfind_alternativespreflight_toolsfind_related_tools

Remote endpoint

Streamable HTTP

Hosted server - connect over the network, no local install.

url

https://glimind.com/mcp

Add to VS Code Add to Cursor

claude_desktop_config.json

json

{
  "mcpServers": {
    "glimind": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://glimind.com/mcp"
      ]
    }
  }
}

Desktop config is stdio-only; this bridges via mcp-remote. Native remote: Settings > Connectors.