Skip to main content
Glama
nnnkkk7

Bucketeer MCP Server

by nnnkkk7

createFeatureFlag

Create a new feature flag in Bucketeer to control feature releases, define variations, and manage rollout strategies.

Instructions

Create a new feature flag in the specified environment

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
idYesUnique identifier for the feature flag (alphanumeric, hyphens, underscores)
nameYesHuman-readable name for the feature flag
descriptionNoDescription of the feature flag
environmentIdNoEnvironment ID (uses default if not provided)
variationsYesList of variations (at least 2 required)
tagsNoTags for the feature flag
defaultOnVariationIndexYesIndex of the variation to serve when flag is on (0-based)
defaultOffVariationIndexYesIndex of the variation to serve when flag is off (0-based)
variationTypeNoType of the variation values (default: STRING)

Implementation Reference

  • The async handler function that parses and validates input with Zod schema, creates a BucketeerClient instance, constructs the CreateFeatureRequest, calls the createFeature API method, logs the result, and returns structured success or error content.
    handler: async (input: unknown) => {
      try {
        // Validate input
        const params = createFlagSchema.parse(input);
        
        // Validate variation indices
        if (params.defaultOnVariationIndex >= params.variations.length) {
          throw new Error(`defaultOnVariationIndex ${params.defaultOnVariationIndex} is out of bounds. Must be less than ${params.variations.length}`);
        }
        if (params.defaultOffVariationIndex >= params.variations.length) {
          throw new Error(`defaultOffVariationIndex ${params.defaultOffVariationIndex} is out of bounds. Must be less than ${params.variations.length}`);
        }
        
        logger.debug('Creating feature flag', params);
        
        // Create API client
        const client = new BucketeerClient(config.bucketeerHost, config.bucketeerApiKey);
        
        // Prepare request
        const request: CreateFeatureRequest = {
          id: params.id,
          name: params.name,
          description: params.description,
          environmentId: getEnvironmentId(params.environmentId),
          variations: params.variations,
          tags: params.tags,
          defaultOnVariationIndex: params.defaultOnVariationIndex,
          defaultOffVariationIndex: params.defaultOffVariationIndex,
          variationType: params.variationType,
        };
        
        // Make API call
        const response = await client.createFeature(request);
        
        logger.info(`Successfully created feature flag: ${response.feature.id}`);
        
        return {
          content: [{
            type: 'text',
            text: JSON.stringify({
              success: true,
              feature: response.feature,
            }, null, 2),
          }],
        };
      } catch (error) {
        logger.error('Failed to create feature flag', error);
        
        if (error instanceof z.ZodError) {
          return {
            content: [{
              type: 'text',
              text: JSON.stringify({
                success: false,
                error: 'Invalid input parameters',
                details: error.errors,
              }, null, 2),
            }],
            isError: true,
          };
        }
        
        return {
          content: [{
            type: 'text',
            text: JSON.stringify({
              success: false,
              error: error instanceof Error ? error.message : 'Unknown error',
            }, null, 2),
          }],
          isError: true,
        };
      }
  • Zod schema used for runtime input validation within the handler, defining properties like id, name, variations, indices, and variationType.
    export const createFlagSchema = z.object({
      id: z.string()
        .min(1, 'Feature flag ID is required')
        .regex(/^[a-zA-Z0-9-_]+$/, 'ID must contain only alphanumeric characters, hyphens, and underscores'),
      name: z.string().min(1, 'Feature flag name is required'),
      description: z.string().optional().default(''),
      environmentId: z.string().optional(),
      variations: z.array(variationSchema).min(2, 'At least 2 variations are required'),
      tags: z.array(z.string()).optional(),
      defaultOnVariationIndex: z.number().min(0),
      defaultOffVariationIndex: z.number().min(0),
      variationType: z.nativeEnum(VariationType).optional().default(VariationType.STRING),
    });
  • JSON Schema object defined within the tool for MCP protocol input validation and documentation.
    inputSchema: {
      type: 'object' as const,
      properties: {
        id: {
          type: 'string',
          description: 'Unique identifier for the feature flag (alphanumeric, hyphens, underscores)',
        },
        name: {
          type: 'string',
          description: 'Human-readable name for the feature flag',
        },
        description: {
          type: 'string',
          description: 'Description of the feature flag',
        },
        environmentId: {
          type: 'string',
          description: 'Environment ID (uses default if not provided)',
        },
        variations: {
          type: 'array',
          description: 'List of variations (at least 2 required)',
          items: {
            type: 'object',
            properties: {
              value: {
                type: 'string',
                description: 'The value returned when this variation is served',
              },
              name: {
                type: 'string',
                description: 'Name of the variation',
              },
              description: {
                type: 'string',
                description: 'Description of the variation',
              },
            },
            required: ['value', 'name'],
          },
        },
        tags: {
          type: 'array',
          items: { type: 'string' },
          description: 'Tags for the feature flag',
        },
        defaultOnVariationIndex: {
          type: 'number',
          description: 'Index of the variation to serve when flag is on (0-based)',
        },
        defaultOffVariationIndex: {
          type: 'number',
          description: 'Index of the variation to serve when flag is off (0-based)',
        },
        variationType: {
          type: 'string',
          enum: ['STRING', 'BOOLEAN', 'NUMBER', 'JSON'],
          description: 'Type of the variation values (default: STRING)',
        },
      },
      required: ['id', 'name', 'variations', 'defaultOnVariationIndex', 'defaultOffVariationIndex'],
    },
  • The tools array registers createFlagTool alongside other flag management tools, likely used for MCP server toolset initialization.
    export const tools = [
      listFlagsTool,
      createFlagTool,
      getFlagTool,
      updateFlagTool,
      archiveFlagTool,
    ];
Behavior2/5

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It states this is a creation operation but doesn't mention any behavioral traits like required permissions, whether the flag becomes active immediately, rate limits, or what happens on duplicate IDs. For a mutation tool with zero annotation coverage, this leaves significant gaps in understanding how the tool behaves.

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 a single, clear sentence that immediately states the tool's purpose without unnecessary words. It's perfectly front-loaded and wastes no space, making it easy for an agent to parse quickly while scanning available tools.

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

Completeness2/5

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

For a creation tool with 9 parameters, no annotations, and no output schema, the description is insufficient. It doesn't explain what happens after creation, error conditions, or how this tool fits into the broader feature flag lifecycle with its siblings. The agent would need to rely heavily on the schema alone, missing important contextual information.

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?

The schema description coverage is 100%, so the schema already documents all 9 parameters thoroughly. The description adds no additional parameter semantics beyond what's in the schema, not explaining relationships between parameters or providing usage examples. This meets the baseline expectation when schema coverage is complete.

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?

The description clearly states the action ('Create') and resource ('feature flag in the specified environment'), making the purpose immediately understandable. However, it doesn't differentiate this tool from its siblings like 'updateFeatureFlag' or 'archiveFeatureFlag' beyond the basic verb difference, missing an opportunity to clarify the specific creation context.

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

Usage Guidelines2/5

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

The description provides no guidance on when to use this tool versus alternatives like 'updateFeatureFlag' or 'archiveFeatureFlag'. It mentions 'specified environment' but doesn't explain prerequisites, dependencies, or typical use cases, leaving the agent to infer usage from the tool name alone.

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/nnnkkk7/bucketeer-mcp'

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