Skip to main content
Glama
TsvetanG2

cognigy-ai-mcp-management-server

by TsvetanG2
OverviewSchemaSourceRelated ServersDiscussions(1)Admin
TypeScript

create_knowledge_connector

Creates a Cognigy.AI knowledge connector to automate content ingestion from sources like SharePoint or Confluence. Set dryRun=false to create.

Instructions

Creates a new Cognigy.AI knowledge connector for automated content ingestion from external sources like SharePoint or Confluence. MUTATING: Set dryRun=false to create.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
nameYesName for the connector
typeYesConnector type as defined by the extension
configNoConnector-specific configuration, including any connection reference the connector requires
dryRunNoIf true (default), validates without creating. Set to false to actually create.
versionYesVersion of the extension's connector to use
scheduleNoRun schedule. Defaults to disabled (run manually with run_knowledge_connector).
extensionYesName of the extension that provides the knowledge connector (see list_extensions)
knowledgeStoreIdYesThe knowledge store ID to create the connector in

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed12 schema fields changedv0.2.1
    • addedInput schema / properties / config
      Added value: +{
+  "additionalProperties": {},
+  "default": {},
+  "description": "Connector-specific configuration, including any connection reference the connector requires",
+  "propertyNames": {
+    "type": "string"
+  },
+  "type": "object"
+}
    • removedInput schema / properties / connectionId
      Removed value: -{
-  "description": "Connection ID for authentication",
-  "type": "string"
-}
    • addedInput schema / properties / extension
      Added value: +{
+  "description": "Name of the extension that provides the knowledge connector (see list_extensions)",
+  "type": "string"
+}
    • addedInput schema / properties / schedule / default
      Added value: +{
+  "enabled": false,
+  "hour": 0,
+  "minute": 0,
+  "weekDays": []
+}
    • changedInput schema / properties / schedule / description
      Previous value: -"Cron expression for scheduled runs"New value: +"Run schedule. Defaults to disabled (run manually with run_knowledge_connector)."
    • addedInput schema / properties / schedule / properties
      Added value: +{
+  "enabled": {
+    "description": "Whether scheduled runs are enabled",
+    "type": "boolean"
+  },
+  "hour": {
+    "maximum": 23,
+    "minimum": 0,
+    "type": "integer"
+  },
+  "minute": {
+    "maximum": 59,
+    "minimum": 0,
+    "type": "integer"
+  },
+  "weekDays": {
+    "description": "Days to run on (0 = Sunday ... 6 = Saturday)",
+    "items": {
+      "maximum": 6,
+      "minimum": 0,
+      "type": "integer"
+    },
+    "type": "array"
+  }
+}
    • addedInput schema / properties / schedule / required
      Added value: +[
+  "enabled",
+  "weekDays",
+  "hour",
+  "minute"
+]
    • changedInput schema / properties / schedule / type
      Previous value: -"string"New value: +"object"
    • removedInput schema / properties / settings
      Removed value: -{
-  "additionalProperties": {},
-  "description": "Type-specific connector settings",
-  "propertyNames": {
-    "type": "string"
-  },
-  "type": "object"
-}
    • changedInput schema / properties / type / description
      Previous value: -"Connector type (e.g., 'sharepoint', 'confluence', 'custom')"New value: +"Connector type as defined by the extension"
    • addedInput schema / properties / version
      Added value: +{
+  "description": "Version of the extension's connector to use",
+  "type": "string"
+}
    • changedInput schema / required
      Previous value: -[
-  "knowledgeStoreId",
-  "name",
-  "type"
-]New value: +[
+  "knowledgeStoreId",
+  "name",
+  "extension",
+  "type",
+  "version"
+]
  2. First observedv0.1.4

TDQS

A3.6/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=false, idempotentHint=false, destructiveHint=false, and openWorldHint=true, so the write/safety profile is covered. The description's 'MUTATING' and dryRun note largely restate the annotation and the schema's own dryRun description rather than adding new behavioral context (side effects, required permissions, or what gets created).

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?

Two tight sentences with the purpose front-loaded and the critical mutation/dryRun note second. Every clause earns its place with no 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?

For a create tool with a fully documented schema and no output schema, the description covers purpose and the crucial dryRun gotcha. It omits what is returned and any permission/precondition details, but these are minor given the rich schema.

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 100%, so all eight parameters (including nested schedule and config) are already documented in the schema. The description only echoes the dryRun semantics, adding no meaning beyond the structured field.

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

Purpose4/5

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

States a specific verb and resource ('Creates a new Cognigy.AI knowledge connector') and adds purpose context ('automated content ingestion from external sources like SharePoint or Confluence'). It distinguishes the resource from create_knowledge_store/create_knowledge_source by name, but never explicitly contrasts with those siblings.

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?

Provides actionable invocation guidance ('MUTATING: Set dryRun=false to create'), which is important given the default dryRun=true. However, it gives no when-to-use-vs-alternatives guidance relative to update_knowledge_connector or the other create_* tools; usage is only implied by the verb.

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

Deploy Server

Other Tools