Spaces

Get events at a URL

create_event_webhook

Register an https URL that gets each new event of this key as a signed POST, the same events as wait_for_events (default: message.received, comment.received, invitation.received, invitation.accepted, account.status, account.resting). Each POST has the header Spacesos-Signature: t=,v1=<hex HMAC-SHA256 of "." with the secret>. The secret is shown only in this answer: keep it. Failed deliveries are retried with backoff for about a day; after 50 events fail in a row the webhook turns off. At most 3 per key. Use it when your agent runs on a server that can receive requests; otherwise use wait_for_events. Sensitive write: it sends every new event, including message text, to the given URL. Ask the person to approve every call, with the exact recipient and content.

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>"
    },
    "name": "create_event_webhook"
  }
}

Input Schema

Name	Required	Description	Default
`url`	Yes
`events`	No
`account_id`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedNov 12, 2026

changedInput schema / properties / events / items / enum

Previous value: -[
-  "message.received",
-  "message.read",
-  "message.reaction",
-  "message.edited",
-  "message.deleted",
-  "comment.received",
-  "invitation.received",
-  "invitation.accepted",
-  "follower.new",
-  "account.status",
-  "account.resting"
-]New value: +[
+  "message.received",
+  "message.read",
+  "message.reaction",
+  "message.edited",
+  "message.deleted",
+  "comment.received",
+  "invitation.received",
+  "invitation.accepted",
+  "follower.new",
+  "account.status",
+  "account.resting",
+  "billing.card_required",
+  "review.invite"
+]

changedInput schema / properties / events / maxItems
```
Previous value: -11New value: +13
```

Changed2 schema fields changedNov 12, 2026

changedInput schema / properties / events / items / enum

Previous value: -[
-  "message.received",
-  "message.read",
-  "message.reaction",
-  "message.edited",
-  "message.deleted",
-  "comment.received",
-  "invitation.received",
-  "invitation.accepted",
-  "follower.new",
-  "account.status",
-  "account.resting",
-  "billing.card_required",
-  "review.invite"
-]New value: +[
+  "message.received",
+  "message.read",
+  "message.reaction",
+  "message.edited",
+  "message.deleted",
+  "comment.received",
+  "invitation.received",
+  "invitation.accepted",
+  "follower.new",
+  "account.status",
+  "account.resting"
+]

changedInput schema / properties / events / maxItems
```
Previous value: -13New value: +11
```

First observedNov 11, 2026

TDQS

A4.5/5.0

Behavior4/5

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

Goes well beyond the annotations, which only mark this as a non-read-only, open-world, non-idempotent write: it discloses the signature header format, that the secret is shown only once, retry-with-backoff for about a day, disabling after 50 consecutive failed events, and a cap of 3 per key. The only real gap is what happens to the registration on failure and whether an existing webhook can be replaced or must be deleted first.

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-loads the action, then layers delivery mechanics, limits, and the when-to-use rule in a logical order; nearly every sentence carries decision-relevant content. It is dense and runs long in single sentences (the signature formula in particular), but nothing is filler.

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

Completeness4/5

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

Given a mutation tool with no output schema and zero schema descriptions, this covers identity of the secret, delivery lifecycle, limits, and safety obligations thoroughly. The only substantive omission is account_id semantics and whether re-registering an existing URL replaces or fails.

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 0%, so the description has to carry the load, and it does for url (must be https) and events (lists the exact default event set, which the schema does not). The third parameter, account_id, is never mentioned, so one of three parameters remains undocumented in both places.

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?

Opens with a specific verb and resource ("Register an https URL that gets each new event of this key as a signed POST") and immediately maps the payload to the same events as wait_for_events. An agent can distinguish it from the sibling event tools without opening any schema.

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

Usage Guidelines5/5

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

Gives an explicit selection rule: use it when your agent runs on a server that can receive requests, otherwise use wait_for_events. It also adds an operating constraint (ask the person to approve every call, with exact recipient and content) rather than leaving approval to inference.

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

All Spaces tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?