YourAITools MCP Hub

ToolFit: Watch a remote MCP server for tool or grade changes

watch_mcp_server

Hosted watch for a remote MCP server: ToolFit re-audits it for 30 days and POSTs an HMAC-SHA256 signed JSON webhook to your https endpoint when its tools/list fingerprint or grade changes, or it goes unreachable or recovers. tier watch = every 24 h ($0.25 per watch, 30 days), tier watch6h = every 6 h ($0.60 per watch). Leave "every" out (the tier sets it). Returns watch_id and the signing secret once (store it: it verifies webhooks and authorizes watch_status and watch_cancel). Not charged if the server is unreachable, a URL or webhook is blocked, or the watch list is full.

[ToolFit via YourAITools MCP Hub] No free tier (paid route only). Paid: watch $0.25 / watch6h $0.60 per call, with a credits key (Authorization: Bearer yatc_...) or x402 (USDC; the hub returns the payment terms). Failed tool calls aren't charged: credits are refunded automatically and x402 payments only settle on success.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "url": "<url>",
      "webhook": "<webhook>"
    },
    "name": "watch_mcp_server"
  }
}

Input Schema

Name	Required	Description
`url`	Yes	Public remote MCP server URL (Streamable HTTP, https), e.g. https://api.youraitools.co/mcp/hub. ToolFit only lists its tools.
`tier`	No	Paid tier: watch $0.25, watch6h $0.60. Default watch.
`every`	No	Optional; this route is the 24 h interval (POST /v1/watch/6h for every 6 h).
`webhook`	Yes	Your https endpoint (public host, port 443) that receives the signed JSON change notifications. A query string is allowed.

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedOct 30, 2026
- addedInput schema / properties / url / examples
```
Added value: +[
+  "https://api.youraitools.co/mcp/hub"
+]
```
- addedInput schema / properties / webhook / examples
```
Added value: +[
+  "https://example.com/hooks/toolfit"
+]
```
AddedOct 24, 2026

TDQS

A4.6/5.0

Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Adds substantial behavior beyond the annotations: HMAC-SHA256 signed JSON webhook delivery, the secret being returned exactly once, 30-day expiry, per-tier pricing, and explicit no-charge conditions (unreachable server, blocked URL/webhook, full watch list) plus refund semantics. It also discloses side effects an agent must plan for — an external POST target and a credential that must be stored — which the readOnly/openWorld hints alone do not convey.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the core action and result, then pricing and billing caveats. The tier prices ($0.25 / $0.60) appear twice — once in the body and again in the appended hub note — which is mild redundancy rather than bloat.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Despite no output schema, it tells the agent exactly what comes back (watch_id and one-time signing secret), what to do with it, how long it lives, what events trigger notification, and the failure/billing matrix. That is everything needed to invoke it correctly and to manage the resulting resource.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so baseline is 3, but the description adds real meaning: tier drives both interval and price ('Leave "every" out (the tier sets it)'), and the webhook must be a public https host on port 443. It could still clarify what happens when the same URL is watched twice, given idempotentHint=false.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Hosted watch for a remote MCP server') plus the exact observable behavior: a signed webhook fires when the tools/list fingerprint or grade changes, or the server goes unreachable/recovers. This clearly separates it from one-shot siblings like check_mcp_server or audit_tools without needing either schema opened.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives concrete operating context: 30-day duration, two cadence tiers, when 'every' should be omitted, and that the returned secret authorizes watch_status and watch_cancel. It never explicitly says 'use this instead of check_mcp_server when you need ongoing monitoring', so the alternative-selection rule is implied rather than stated.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All YourAITools MCP Hub tools Inspect

Try in Browser

Claude Code, inside the Godot 4 editorFlockbay puts an AI agent in the real Godot 4 editor: it writes GDScript, runs your game and fixes what breaks. Free, or bring your own Claude Code or Codex.flockbay.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?