Skip to main content
Glama
configcat

ConfigCat MCP Server

Official
by configcat
OverviewSchemaRelated ServersScoreDiscussions
TypeScript
Remote

create-integration

Create a new integration in a ConfigCat product by specifying integration type, name, parameters, and connected environments or configs.

Instructions

This endpoint creates a new Integration in a specified Product identified by the productId parameter, which can be obtained from the List Products endpoint.

The Parameters dictionary differs for each IntegrationType:

  • Datadog

    • apikey: Required. Datadog API key.

    • site: Datadog site. Available values: Us, Eu, Us1Fed, Us3, Us5. Default: Us.

  • Slack
    Connecting the Slack integration through the Public Management API will not post messages with the ConfigCat Feature Flags Slack app but with an incoming webhook.

    • incoming_webhook.url: Required. The incoming webhook URL where the integration should post messages.

    • includeSensitiveData: Set to "true" to include sensitive (hashed) comparison values. By default, the integration will mask these values in the posted messages. We recommend hiding sensitive comparison values for shared or public Slack channels.

  • Amplitude

    • apiKey: Required. Amplitude API Key.

    • secretKey: Required. Amplitude Secret Key.

  • Mixpanel

    • serviceAccountUserName: Required. Mixpanel Service Account Username.

    • serviceAccountSecret: Required. Mixpanel Service Account Secret.

    • projectId: Required. Mixpanel Project ID.

    • server: Mixpanel Server. Available values: StandardServer, EUResidencyServer. Default: StandardServer.

  • Twilio Segment

    • writeKey: Required. Twilio Segment Write Key.

    • server: Twilio Segment Server. Available values: Us, Eu. Default: Us.

  • PubNub (work in progress)

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
productIdYesThe identifier of the Product.
requestBodyYes

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. Changed2 schema fields changedv0.1.9
    • addedInput schema / properties / requestBody / properties / integrationType / description
      Added value: +"The type of the Integration."
    • changedInput schema / properties / requestBody / properties / parameters / additionalProperties / type
      Previous value: -[
-  "string",
-  "null"
-]New value: +"string"
  2. First observedv0.1.7

TDQS

A4.5/5.0
Behavior4/5

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

With no annotations present, the description carries the transparency burden. It discloses meaningful behavioral traits beyond the obvious create operation: Slack integrations use an incoming webhook rather than the ConfigCat Slack app, PubNub is flagged as a work in progress, and defaults like Datadog site and Mixpanel server are specified. It does not mention response format or authorization requirements, but the behavioral caveats provided are substantial.

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?

The description is long but every section earns its place: the opener states purpose and source of productId, and the provider bullets supply necessary parameter semantics and caveats. It is front-loaded with the core purpose and structured clearly enough for an agent to parse per-integration requirements.

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?

The description covers the essential context: what the tool does, how to get the product identifier, what parameters each integration type requires, defaults, and notable caveats. However, there is no output schema and the description does not state what a successful response contains or what error conditions may arise, leaving a minor but real completeness gap.

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

Parameters5/5

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

The schema only describes parameters as a generic object with string values, which would leave an agent unable to construct valid requests. The description fully compensates by enumerating every provider's required and optional keys, valid values, and defaults. This is far more valuable than the schema alone and directly enables correct invocation.

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?

The description states a specific verb and resource: 'creates a new Integration in a specified Product identified by the productId parameter.' It clearly distinguishes this from sibling tools like get-integration, list-integrations, update-integration, and delete-integration by focusing on creation.

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?

The description gives clear practical context by explaining where to obtain productId (from List Products) and by detailing integration-type-specific parameter requirements. It does not explicitly contrast this with update-integration or get-integration, so it stops short of fully explicit when-to-use versus alternatives, but the creation context is unambiguous.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/configcat/mcp-server'

If you have feedback or need assistance with the MCP directory API, please join our Discord server