cortex-mcp

cortex_list_jobs

List recent analysis jobs with filters for data type, analyzer name, status, and maximum results.

Instructions

List recent analysis jobs with optional filters

Input Schema

TableJSON Schema

Name	Required	Description
`dataType`	No	Filter by data type
`analyzerName`	No	Filter by analyzer name
`limit`	No	Maximum number of jobs to return (default: 50)
`status`	No	Filter by status (Waiting, InProgress, Success, Failure, Deleted)

Implementation Reference

src/tools/jobs.ts:5-405 (registration)

The registerJobTools function is where all job tools (including cortex_list_jobs) are registered on the MCP server via server.tool() calls.

export function registerJobTools(
  server: McpServer,
  client: CortexClient,
): void {
  server.tool(
    "cortex_get_job",
    "Get the status and details of an analysis job",
    {
      jobId: z.string().describe("The job ID to look up"),
    },
    async ({ jobId }) => {
      try {
        const job = await client.getJob(jobId);
        return {
          content: [
            {
              type: "text" as const,
              text: JSON.stringify(job, null, 2),
            },
          ],
        };
      } catch (error) {
        return {
          content: [
            {
              type: "text" as const,
              text: `Error getting job: ${error instanceof Error ? error.message : String(error)}`,
            },
          ],
          isError: true,
        };
      }
    },
  );

  server.tool(
    "cortex_get_job_report",
    "Get the full report of a completed analysis job",
    {
      jobId: z.string().describe("The job ID to get the report for"),
    },
    async ({ jobId }) => {
      try {
        const report = await client.getJobReport(jobId);
        return {
          content: [
            {
              type: "text" as const,
              text: JSON.stringify(report, null, 2),
            },
          ],
        };
      } catch (error) {
        return {
          content: [
            {
              type: "text" as const,
              text: `Error getting job report: ${error instanceof Error ? error.message : String(error)}`,
            },
          ],
          isError: true,
        };
      }
    },
  );

  server.tool(
    "cortex_wait_and_get_report",
    "Wait for a job to complete and return the full report (with polling timeout)",
    {
      jobId: z.string().describe("The job ID to wait for"),
      timeout: z
        .number()
        .int()
        .min(1)
        .max(3600)
        .default(300)
        .describe("Timeout in seconds (default: 300, max: 3600)"),
    },
    async ({ jobId, timeout }) => {
      try {
        const report = await client.waitAndGetReport(jobId, timeout);

        const taxonomies = report.report?.summary?.taxonomies ?? [];
        const taxonomySummary = taxonomies.map(
          (t) => `[${t.level}] ${t.namespace}:${t.predicate} = ${t.value}`,
        );

        return {
          content: [
            {
              type: "text" as const,
              text: JSON.stringify(
                {
                  jobId: report.id,
                  status: report.status,
                  analyzerName: report.analyzerName,
                  taxonomies: taxonomySummary,
                  fullReport: report.report,
                },
                null,
                2,
              ),
            },
          ],
        };
      } catch (error) {
        return {
          content: [
            {
              type: "text" as const,
              text: `Error waiting for report: ${error instanceof Error ? error.message : String(error)}`,
            },
          ],
          isError: true,
        };
      }
    },
  );

  server.tool(
    "cortex_list_jobs",
    "List recent analysis jobs with optional filters",
    {
      dataType: z
        .string()
        .optional()
        .describe("Filter by data type"),
      analyzerName: z
        .string()
        .optional()
        .describe("Filter by analyzer name"),
      limit: z
        .number()
        .int()
        .min(1)
        .max(500)
        .default(50)
        .describe("Maximum number of jobs to return (default: 50)"),
      status: z
        .string()
        .optional()
        .describe(
          "Filter by status (Waiting, InProgress, Success, Failure, Deleted)",
        ),
    },
    async ({ dataType, analyzerName, limit, status }) => {
      try {
        const must: Record<string, unknown>[] = [];

        if (dataType) {
          must.push({ _field: "dataType", _value: dataType });
        }
        if (analyzerName) {
          must.push({ _field: "analyzerName", _value: analyzerName });
        }
        if (status) {
          must.push({ _field: "status", _value: status });
        }

        const query: Record<string, unknown> =
          must.length > 0
            ? { _and: must }
            : { _field: "status", _value: "*" };

        const jobs = await client.searchJobs({
          query,
          range: `0-${limit}`,
          sort: ["-createdAt"],
        });

        const summary = jobs.map((j) => ({
          id: j.id,
          analyzerName: j.analyzerName,
          dataType: j.dataType,
          data: j.data,
          status: j.status,
          startDate: j.startDate
            ? new Date(j.startDate).toISOString()
            : undefined,
          endDate: j.endDate
            ? new Date(j.endDate).toISOString()
            : undefined,
        }));

        return {
          content: [
            {
              type: "text" as const,
              text: JSON.stringify(summary, null, 2),
            },
          ],
        };
      } catch (error) {
        return {
          content: [
            {
              type: "text" as const,
              text: `Error listing jobs: ${error instanceof Error ? error.message : String(error)}`,
            },
          ],
          isError: true,
        };
      }
    },
  );

  server.tool(
    "cortex_get_job_artifacts",
    "Get artifacts (extracted observables/IOCs) from a completed analysis job",
    {
      jobId: z.string().describe("The job ID to get artifacts for"),
    },
    async ({ jobId }) => {
      try {
        const artifacts = await client.getJobArtifacts(jobId);
        return {
          content: [
            {
              type: "text" as const,
              text: JSON.stringify(artifacts, null, 2),
            },
          ],
        };
      } catch (error) {
        return {
          content: [
            {
              type: "text" as const,
              text: `Error getting job artifacts: ${error instanceof Error ? error.message : String(error)}`,
            },
          ],
          isError: true,
        };
      }
    },
  );

  server.tool(
    "cortex_delete_job",
    "Delete a specific analysis job by ID",
    {
      jobId: z.string().describe("The job ID to delete"),
    },
    async ({ jobId }) => {
      try {
        await client.deleteJob(jobId);
        return {
          content: [
            {
              type: "text" as const,
              text: `Job "${jobId}" deleted successfully.`,
            },
          ],
        };
      } catch (error) {
        return {
          content: [
            {
              type: "text" as const,
              text: `Error deleting job: ${error instanceof Error ? error.message : String(error)}`,
            },
          ],
          isError: true,
        };
      }
    },
  );

  server.tool(
    "cortex_cleanup_jobs",
    "Delete multiple jobs by status or age. Useful for cleaning up failed or old jobs.",
    {
      status: z
        .enum(["Failure", "Deleted", "Success", "Waiting", "InProgress"])
        .optional()
        .describe("Delete jobs with this status"),
      olderThanDays: z
        .number()
        .int()
        .min(1)
        .optional()
        .describe("Delete jobs older than this many days"),
      dryRun: z
        .boolean()
        .default(true)
        .describe("If true (default), only count matching jobs without deleting them"),
      limit: z
        .number()
        .int()
        .min(1)
        .max(500)
        .default(100)
        .describe("Maximum jobs to process (default: 100)"),
    },
    async ({ status, olderThanDays, dryRun, limit }) => {
      try {
        if (!status && !olderThanDays) {
          return {
            content: [
              {
                type: "text" as const,
                text: "Please specify at least one filter: status or olderThanDays.",
              },
            ],
            isError: true,
          };
        }

        const must: Record<string, unknown>[] = [];
        if (status) {
          must.push({ _field: "status", _value: status });
        }

        const query: Record<string, unknown> =
          must.length > 0
            ? must.length === 1 ? must[0] : { _and: must }
            : { _field: "status", _value: "*" };

        const jobs = await client.searchJobs({
          query,
          range: `0-${limit}`,
          sort: ["-createdAt"],
        });

        let matchingJobs = jobs;
        if (olderThanDays) {
          const cutoff = Date.now() - olderThanDays * 24 * 60 * 60 * 1000;
          matchingJobs = jobs.filter(
            (j) => (j.createdAt ?? 0) < cutoff,
          );
        }

        if (dryRun) {
          return {
            content: [
              {
                type: "text" as const,
                text: JSON.stringify(
                  {
                    dryRun: true,
                    matchingJobs: matchingJobs.length,
                    message: `Found ${matchingJobs.length} jobs matching criteria. Set dryRun=false to delete them.`,
                    jobs: matchingJobs.map((j) => ({
                      id: j.id,
                      status: j.status,
                      analyzer: j.analyzerName,
                      data: j.data,
                      createdAt: j.createdAt
                        ? new Date(j.createdAt).toISOString()
                        : undefined,
                    })),
                  },
                  null,
                  2,
                ),
              },
            ],
          };
        }

        // Actually delete
        const results = await Promise.allSettled(
          matchingJobs.map((j) => client.deleteJob(j.id)),
        );

        const deleted = results.filter((r) => r.status === "fulfilled").length;
        const failed = results.filter((r) => r.status === "rejected").length;

        return {
          content: [
            {
              type: "text" as const,
              text: JSON.stringify(
                {
                  dryRun: false,
                  deleted,
                  failed,
                  total: matchingJobs.length,
                  message: `Deleted ${deleted}/${matchingJobs.length} jobs.${failed > 0 ? ` ${failed} deletions failed.` : ""}`,
                },
                null,
                2,
              ),
            },
          ],
        };
      } catch (error) {
        return {
          content: [
            {
              type: "text" as const,
              text: `Error cleaning up jobs: ${error instanceof Error ? error.message : String(error)}`,
            },
          ],
          isError: true,
        };
      }
    },
  );
}

src/tools/jobs.ts:125-210 (handler)

The cortex_list_jobs tool handler: defines input schema (dataType, analyzerName, limit, status), builds an Elasticsearch-style query, calls client.searchJobs(), and returns a summary array of jobs.

server.tool(
  "cortex_list_jobs",
  "List recent analysis jobs with optional filters",
  {
    dataType: z
      .string()
      .optional()
      .describe("Filter by data type"),
    analyzerName: z
      .string()
      .optional()
      .describe("Filter by analyzer name"),
    limit: z
      .number()
      .int()
      .min(1)
      .max(500)
      .default(50)
      .describe("Maximum number of jobs to return (default: 50)"),
    status: z
      .string()
      .optional()
      .describe(
        "Filter by status (Waiting, InProgress, Success, Failure, Deleted)",
      ),
  },
  async ({ dataType, analyzerName, limit, status }) => {
    try {
      const must: Record<string, unknown>[] = [];

      if (dataType) {
        must.push({ _field: "dataType", _value: dataType });
      }
      if (analyzerName) {
        must.push({ _field: "analyzerName", _value: analyzerName });
      }
      if (status) {
        must.push({ _field: "status", _value: status });
      }

      const query: Record<string, unknown> =
        must.length > 0
          ? { _and: must }
          : { _field: "status", _value: "*" };

      const jobs = await client.searchJobs({
        query,
        range: `0-${limit}`,
        sort: ["-createdAt"],
      });

      const summary = jobs.map((j) => ({
        id: j.id,
        analyzerName: j.analyzerName,
        dataType: j.dataType,
        data: j.data,
        status: j.status,
        startDate: j.startDate
          ? new Date(j.startDate).toISOString()
          : undefined,
        endDate: j.endDate
          ? new Date(j.endDate).toISOString()
          : undefined,
      }));

      return {
        content: [
          {
            type: "text" as const,
            text: JSON.stringify(summary, null, 2),
          },
        ],
      };
    } catch (error) {
      return {
        content: [
          {
            type: "text" as const,
            text: `Error listing jobs: ${error instanceof Error ? error.message : String(error)}`,
          },
        ],
        isError: true,
      };
    }
  },
);

src/tools/jobs.ts:128-150 (schema)

Input schema for cortex_list_jobs: optional dataType (string), optional analyzerName (string), optional limit (int, 1-500, default 50), optional status (string filter).

{
  dataType: z
    .string()
    .optional()
    .describe("Filter by data type"),
  analyzerName: z
    .string()
    .optional()
    .describe("Filter by analyzer name"),
  limit: z
    .number()
    .int()
    .min(1)
    .max(500)
    .default(50)
    .describe("Maximum number of jobs to return (default: 50)"),
  status: z
    .string()
    .optional()
    .describe(
      "Filter by status (Waiting, InProgress, Success, Failure, Deleted)",
    ),
},

src/client.ts:302-307 (helper)

The client.searchJobs() helper method that sends a POST request to /job/_search with the query body.

async searchJobs(query: JobSearchQuery): Promise<Job[]> {
  return this.request<Job[]>("/job/_search", {
    method: "POST",
    body: JSON.stringify(query),
  });
}

src/index.ts:35-36 (registration)
Registration call in the main entry point: registerJobTools(server, client) wires the job tools into the MCP server during startup.
```
registerJobTools(server, client);
registerResponderTools(server, client);
```

Tool Definition Quality

B3.1/5.0

Behavior2/5

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

No annotations provided, so description should disclose behavior. It says 'List recent analysis jobs' but omits ordering, pagination, scope (user vs all), or whether only completed jobs. The limit parameter is defined in schema but not highlighted in description.

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

Conciseness4/5

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

Single sentence, concise and front-loaded. No unnecessary words, but could be slightly more informative without harm.

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?

With no output schema or annotations, description is minimal. It does not explain return format, pagination details, or common usage patterns for a 4-parameter tool.

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 coverage is 100% so baseline is 3. Description adds no extra meaning beyond 'with optional filters'; each parameter is already well-described in schema.

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?

Description clearly states 'List recent analysis jobs with optional filters', using specific verb and resource. It differentiates from sibling tools like cortex_get_job (single job) by implying a batch list, but does not clarify what 'recent' means.

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?

No explicit when-to-use or alternatives are given. The phrase 'with optional filters' implies it is for filtered browsing, but no mention of when to use cortex_get_job for a specific job or exclude other list tools.

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

Install Server

Latest Blog Posts

Lightport: Open-Sourcing Glama's AI Gateway
By punkpeye on April 27, 2026.
open source
OpenAI
Tool Definition Quality Score (TDQS)
By punkpeye on April 3, 2026.
mcp
The Hackers Who Tracked My Sleep Cycle
By punkpeye on March 26, 2026.
security

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