Skip to main content
Glama

cortex_list_responder_definitions

Lists all installed responder definitions with filters for data type, free-only responders, and search by name or description.

Instructions

List all available responder definitions (installed but not necessarily enabled). Filter by data type or find responders that require no API keys.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
dataTypeNoFilter by supported data type (case, case_task, case_artifact, alert, etc.)
freeOnlyNoIf true, only return responders that require no configuration/API keys
searchNoSearch responder names and descriptions (case-insensitive)
limitNoMaximum results to return (default: 50)

Implementation Reference

  • The async handler function for cortex_list_responder_definitions. It calls client.listResponderDefinitions(), filters by dataType, freeOnly, and search, limits results, and returns formatted JSON with responder definition details.
    async ({ dataType, freeOnly, search, limit }) => {
      try {
        let defs = await client.listResponderDefinitions();
    
        if (dataType) {
          defs = defs.filter((d) => d.dataTypeList.includes(dataType));
        }
    
        if (freeOnly) {
          defs = defs.filter(
            (d) => !d.configurationItems.some((c) => c.required),
          );
        }
    
        if (search) {
          const q = search.toLowerCase();
          defs = defs.filter(
            (d) =>
              d.name.toLowerCase().includes(q) ||
              d.description.toLowerCase().includes(q),
          );
        }
    
        const total = defs.length;
        defs = defs.slice(0, limit);
    
        const summary = defs.map((d) => ({
          id: d.id,
          name: d.name,
          version: d.version,
          description: d.description,
          dataTypes: d.dataTypeList,
          author: d.author,
          requiresConfig: d.configurationItems.some((c) => c.required),
          configFields: d.configurationItems.map((c) => ({
            name: c.name,
            required: c.required,
            type: c.type,
            description: c.description,
          })),
          dockerImage: d.dockerImage,
        }));
    
        return {
          content: [
            {
              type: "text" as const,
              text: JSON.stringify(
                {
                  total,
                  returned: summary.length,
                  definitions: summary,
                },
                null,
                2,
              ),
            },
          ],
        };
      } catch (error) {
        return {
          content: [
            {
              type: "text" as const,
              text: `Error listing responder definitions: ${error instanceof Error ? error.message : String(error)}`,
            },
          ],
          isError: true,
        };
      }
    },
  • Zod schema for input parameters: optional dataType string, freeOnly boolean, search string, and limit (1-500, default 50).
    {
      dataType: z
        .string()
        .optional()
        .describe("Filter by supported data type (case, case_task, case_artifact, alert, etc.)"),
      freeOnly: z
        .boolean()
        .optional()
        .describe("If true, only return responders that require no configuration/API keys"),
      search: z
        .string()
        .optional()
        .describe("Search responder names and descriptions (case-insensitive)"),
      limit: z
        .number()
        .int()
        .min(1)
        .max(500)
        .default(50)
        .describe("Maximum results to return (default: 50)"),
    },
  • Registration function registerResponderDefinitionTools which registers the tool using server.tool() with the name 'cortex_list_responder_definitions'.
    export function registerResponderDefinitionTools(
      server: McpServer,
      client: CortexClient,
    ): void {
      server.tool(
  • src/index.ts:9-41 (registration)
    Import and call site where registerResponderDefinitionTools is imported from responder-definitions.ts and invoked in main().
    import { registerResponderDefinitionTools } from "./tools/responder-definitions.js";
    import { registerBulkTools } from "./tools/bulk.js";
    import { registerStatusTools } from "./tools/status.js";
    import { registerOrganizationTools } from "./tools/organizations.js";
    import { registerUserTools } from "./tools/users.js";
    import { registerResources } from "./resources.js";
    import { registerPrompts } from "./prompts.js";
    
    async function main(): Promise<void> {
      const config = getConfig();
    
      if (!config.verifySsl) {
        process.env.NODE_TLS_REJECT_UNAUTHORIZED = "0";
      }
    
      const server = new McpServer({
        name: "cortex-mcp",
        version: "1.2.0",
        description:
          "MCP server for Cortex - observable analysis and active response engine by StrangeBee/TheHive Project",
      });
    
      const client = new CortexClient(config);
    
      // Core analysis tools
      registerAnalyzerTools(server, client);
      registerJobTools(server, client);
      registerResponderTools(server, client);
      registerBulkTools(server, client);
    
      // Administration tools
      registerAnalyzerDefinitionTools(server, client);
      registerResponderDefinitionTools(server, client);
  • The CortexClient.listResponderDefinitions() method that makes the actual HTTP GET request to the /responderdefinition API endpoint.
    async listResponderDefinitions(): Promise<ResponderDefinition[]> {
      return this.request<ResponderDefinition[]>("/responderdefinition", {}, true);
    }
Behavior3/5

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

With no annotations, the description carries full burden. It clarifies the tool lists installed but not necessarily enabled definitions, implying a read-only operation. However, it does not disclose authentication requirements, permission needs, or output format, leaving some behavioral gaps.

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 15-word sentence that is front-loaded with the core purpose, immediately followed by filtering options. Every word contributes meaning with no redundancy or filler.

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

Completeness3/5

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

The description covers the tool's purpose and key filtering options, but lacks details on output format, pagination behavior (despite a limit parameter), or error handling. Given no output schema, more context about return structure would improve completeness.

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?

Input schema has 100% coverage with descriptions for all 4 parameters. The description adds value by highlighting two parameter use cases (dataType, freeOnly) but does not add meaning beyond schema for search and limit. Baseline 3 is appropriate.

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 clearly states the tool lists responder definitions, specifies they are installed but not necessarily enabled, and mentions filtering by data type and finding ones without API keys. This differentiates it from siblings like cortex_list_responders (likely enabled only) and cortex_list_analyzer_definitions.

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 provides two specific use cases: filtering by data type and finding responders needing no API keys. However, it lacks explicit guidance on when to use this over related tools like cortex_list_responders or cortex_enable_responder, missing a clear when-not-to-use or alternative suggestion.

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/solomonneas/cortex-mcp'

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