Skip to main content
Glama
Sign In

Opsphere — DevOps & SRE Intelligence

by io.opsphere.mcp-cursor
OverviewDiscussionsAdmin

Cloudflare: WAF custom rules replace

cf_waf_custom_rules_replace
Destructive

Replace ALL WAF custom rules for the zone (http_request_firewall_custom entrypoint PUT). Sends the full rules array; this is not a partial patch. Requires Firewall Services > Write. Use with care.

Input Schema

NameRequiredDescriptionDefault
zoneYesZone name (e.g. your-tenant.com) or zone ID
rulesYesComplete Cloudflare WAF custom rules array
context_idNoOptional explicit Connection Hub work context (ctx_*). Omit to use the conversation's active workspace; global Hub tools ignore it.
descriptionNo
account_slugNoCloudflare account slug. Required when the workspace has multiple accounts and the zone is not yet cataloged.
environment_slugNoCloud Catalog environment used as an account-routing preference when no zone is provided.

Output Schema

NameRequiredDescriptionDefault
okYes
dataYes
contractVersionYes
dataSchemaVersionYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed25 schema fields changed
    • changedOutput schema / properties / data / additionalProperties
      Previous value: -trueNew value: +false
    • removedOutput schema / properties / data / properties / count
      Removed value: -{
-  "type": "number"
-}
    • addedOutput schema / properties / data / properties / description
      Added value: +{
+  "type": "string"
+}
    • removedOutput schema / properties / data / properties / errors / items / $ref
      Removed value: -"#/properties/data/properties/result/anyOf/0/items"
    • addedOutput schema / properties / data / properties / errors / items / additionalProperties
      Added value: +false
    • addedOutput schema / properties / data / properties / errors / items / properties
      Added value: +{
+  "code": {
+    "type": "integer"
+  },
+  "message": {
+    "type": "string"
+  }
+}
    • addedOutput schema / properties / data / properties / errors / items / required
      Added value: +[
+  "message"
+]
    • addedOutput schema / properties / data / properties / errors / items / type
      Added value: +"object"
    • addedOutput schema / properties / data / properties / gaps
      Added value: +{
+  "items": {
+    "type": "string"
+  },
+  "type": "array"
+}
    • addedOutput schema / properties / data / properties / id
      Added value: +{
+  "type": "string"
+}
    • removedOutput schema / properties / data / properties / items
      Removed value: -{
-  "$ref": "#/properties/data/properties/result/anyOf/0"
-}
    • addedOutput schema / properties / data / properties / lastUpdated
      Added value: +{
+  "format": "date-time",
+  "type": "string"
+}
    • removedOutput schema / properties / data / properties / messages
      Removed value: -{
-  "items": {
-    "anyOf": [
-      {
-        "type": "string"
-      },
-      {
-        "$ref": "#/properties/data/properties/result/anyOf/0/items"
-      }
-    ]
-  },
-  "type": "array"
-}
    • addedOutput schema / properties / data / properties / name
      Added value: +{
+  "type": "string"
+}
    • addedOutput schema / properties / data / properties / partial
      Added value: +{
+  "type": "boolean"
+}
    • addedOutput schema / properties / data / properties / phase
      Added value: +{
+  "type": "string"
+}
    • removedOutput schema / properties / data / properties / result
      Removed value: -{
-  "anyOf": [
-    {
-      "items": {
-        "additionalProperties": true,
-        "properties": {},
-        "type": "object"
-      },
-      "type": "array"
-    },
-    {
-      "$ref": "#/properties/data/properties/result/anyOf/0/items"
-    }
-  ]
-}
    • removedOutput schema / properties / data / properties / result_info
      Removed value: -{
-  "$ref": "#/properties/data/properties/result/anyOf/0/items"
-}
    • addedOutput schema / properties / data / properties / rules
      Added value: +{
+  "items": {
+    "additionalProperties": false,
+    "properties": {
+      "action": {
+        "type": "string"
+      },
+      "childRulesetId": {
+        "type": "string"
+      },
+      "description": {
+        "type": "string"
+      },
+      "enabled": {
+        "type": "boolean"
+      },
+      "expression": {
+        "type": "string"
+      },
+      "id": {
+        "type": "string"
+      },
+      "ref": {
+        "type": "string"
+      }
+    },
+    "required": [
+      "id",
+      "enabled"
+    ],
+    "type": "object"
+  },
+  "type": "array"
+}
    • addedOutput schema / properties / data / properties / truncated
      Added value: +{
+  "type": "boolean"
+}
    • addedOutput schema / properties / data / properties / version
      Added value: +{
+  "type": "string"
+}
    • addedOutput schema / properties / data / properties / warnings
      Added value: +{
+  "items": {
+    "type": "string"
+  },
+  "type": "array"
+}
    • addedOutput schema / properties / data / required
      Added value: +[
+  "rules",
+  "partial",
+  "truncated",
+  "warnings",
+  "gaps"
+]
    • addedOutput schema / properties / dataSchemaVersion
      Added value: +{
+  "const": 2,
+  "type": "number"
+}
    • changedOutput schema / required
      Previous value: -[
-  "contractVersion",
-  "ok",
-  "data"
-]New value: +[
+  "contractVersion",
+  "dataSchemaVersion",
+  "ok",
+  "data"
+]
  2. First observed

TDQS

A4/5.0
Behavior4/5

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

Annotations already flag destructiveHint=true, but the description adds substantive context: the operation is a full overwrite of the entire rules array, so rules omitted from the payload are lost. It also discloses the required permission (Firewall Services > Write), which annotations cannot express. It could go further by stating rate limits or that the prior ruleset is unrecoverable.

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

Conciseness5/5

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

Three short sentences, front-loaded with the destructive scope and the full-replacement constraint before the permission note. No filler or repetition.

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?

For a destructive replace tool with an output schema and destructiveHint already set, the description covers scope, semantics and auth. The main gap is that it gives no guidance on retrieving existing rules before overwriting, which matters for a call that silently drops anything not resubmitted.

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

Parameters3/5

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

Schema description coverage is 83%, so the schema already documents zone, rules, context_id, account_slug and environment_slug. The description reinforces that 'rules' must be the complete array but adds no syntax, ordering, or field-level detail for individual rule objects, which are left as opaque additionalProperties.

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 ('Replace ALL WAF custom rules for the zone'), names the underlying API entrypoint and method, and explicitly rules out partial-patch semantics. An agent can distinguish this from cf_waf_custom_rules_list and cf_ruleset_entrypoint_update 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 Guidelines3/5

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

'Use with care' plus 'this is not a partial patch' implies caution and excludes the partial-update case, but no alternative tool is named for that case (e.g., fetching current rules first via cf_waf_custom_rules_list, or using cf_ruleset_entrypoint_update). The agent must infer the safe workflow.

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

All Opsphere — DevOps & SRE Intelligence toolsInspect
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