Skip to main content
Glama
comet-ml

Opik MCP Server

by comet-ml

get-trace-stats

Retrieve trace statistics by specifying project ID, name, date range, or workspace for efficient analysis and monitoring on the Opik platform.

Instructions

Get statistics for traces

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
endDateNoEnd date in ISO format (YYYY-MM-DD)
projectIdNoProject ID to filter traces
projectNameNoProject name to filter traces
startDateNoStart date in ISO format (YYYY-MM-DD)
workspaceNameNoWorkspace name to use instead of the default

Implementation Reference

  • The main handler function for 'get-trace-stats' tool. Constructs API URL with project filtering, date ranges, fetches stats from /v1/private/traces/stats, handles no-project case by fetching first project, formats and returns response as content array.
    async (args: any) => {
      const { projectId, projectName, startDate, endDate, workspaceName } = args;
      let url = `/v1/private/traces/stats`;
    
      // Build query parameters
      const queryParams = [];
    
      // Add project filtering - API requires either project_id or project_name
      if (projectId) {
        queryParams.push(`project_id=${projectId}`);
      } else if (projectName) {
        queryParams.push(`project_name=${encodeURIComponent(projectName)}`);
      } else {
        // If no project specified, we need to find one for the API to work
        const projectsResponse = await makeApiRequest<ProjectResponse>(
          `/v1/private/projects?page=1&size=1`,
          {},
          workspaceName
        );
    
        if (
          projectsResponse.data &&
          projectsResponse.data.content &&
          projectsResponse.data.content.length > 0
        ) {
          const firstProject = projectsResponse.data.content[0];
          queryParams.push(`project_id=${firstProject.id}`);
          logToFile(
            `No project specified, using first available: ${firstProject.name} (${firstProject.id})`
          );
        } else {
          return {
            content: [
              {
                type: 'text',
                text: 'Error: No project ID or name provided, and no projects found',
              },
            ],
          };
        }
      }
    
      if (startDate) queryParams.push(`start_date=${startDate}`);
      if (endDate) queryParams.push(`end_date=${endDate}`);
    
      if (queryParams.length > 0) {
        url += `?${queryParams.join('&')}`;
      }
    
      const response = await makeApiRequest<TraceStatsResponse>(url, {}, workspaceName);
    
      if (!response.data) {
        return {
          content: [{ type: 'text', text: response.error || 'Failed to fetch trace statistics' }],
        };
      }
    
      return {
        content: [
          {
            type: 'text',
            text: `Trace Statistics:`,
          },
          {
            type: 'text',
            text: JSON.stringify(response.data, null, 2),
          },
        ],
      };
    }
  • Input parameters schema defined with Zod validators for projectId, projectName, startDate, endDate, workspaceName.
    {
      projectId: z
        .string()
        .optional()
        .describe(
          'Project ID to filter traces. If not provided, will use the first available project'
        ),
      projectName: z
        .string()
        .optional()
        .describe('Project name to filter traces (alternative to projectId)'),
      startDate: z
        .string()
        .optional()
        .describe('Start date in ISO format (YYYY-MM-DD). Example: "2024-01-01"'),
      endDate: z
        .string()
        .optional()
        .describe('End date in ISO format (YYYY-MM-DD). Example: "2024-01-31"'),
      workspaceName: z
        .string()
        .optional()
        .describe('Workspace name to use instead of the default workspace'),
    },
  • Registers the 'get-trace-stats' tool on the MCP server with name, description, input schema, and handler function.
    server.tool(
      'get-trace-stats',
      'Get aggregated statistics for traces including counts, costs, token usage, and performance metrics over time',
      {
        projectId: z
          .string()
          .optional()
          .describe(
            'Project ID to filter traces. If not provided, will use the first available project'
          ),
        projectName: z
          .string()
          .optional()
          .describe('Project name to filter traces (alternative to projectId)'),
        startDate: z
          .string()
          .optional()
          .describe('Start date in ISO format (YYYY-MM-DD). Example: "2024-01-01"'),
        endDate: z
          .string()
          .optional()
          .describe('End date in ISO format (YYYY-MM-DD). Example: "2024-01-31"'),
        workspaceName: z
          .string()
          .optional()
          .describe('Workspace name to use instead of the default workspace'),
      },
      async (args: any) => {
        const { projectId, projectName, startDate, endDate, workspaceName } = args;
        let url = `/v1/private/traces/stats`;
    
        // Build query parameters
        const queryParams = [];
    
        // Add project filtering - API requires either project_id or project_name
        if (projectId) {
          queryParams.push(`project_id=${projectId}`);
        } else if (projectName) {
          queryParams.push(`project_name=${encodeURIComponent(projectName)}`);
        } else {
          // If no project specified, we need to find one for the API to work
          const projectsResponse = await makeApiRequest<ProjectResponse>(
            `/v1/private/projects?page=1&size=1`,
            {},
            workspaceName
          );
    
          if (
            projectsResponse.data &&
            projectsResponse.data.content &&
            projectsResponse.data.content.length > 0
          ) {
            const firstProject = projectsResponse.data.content[0];
            queryParams.push(`project_id=${firstProject.id}`);
            logToFile(
              `No project specified, using first available: ${firstProject.name} (${firstProject.id})`
            );
          } else {
            return {
              content: [
                {
                  type: 'text',
                  text: 'Error: No project ID or name provided, and no projects found',
                },
              ],
            };
          }
        }
    
        if (startDate) queryParams.push(`start_date=${startDate}`);
        if (endDate) queryParams.push(`end_date=${endDate}`);
    
        if (queryParams.length > 0) {
          url += `?${queryParams.join('&')}`;
        }
    
        const response = await makeApiRequest<TraceStatsResponse>(url, {}, workspaceName);
    
        if (!response.data) {
          return {
            content: [{ type: 'text', text: response.error || 'Failed to fetch trace statistics' }],
          };
        }
    
        return {
          content: [
            {
              type: 'text',
              text: `Trace Statistics:`,
            },
            {
              type: 'text',
              text: JSON.stringify(response.data, null, 2),
            },
          ],
        };
      }
    );
  • src/index.ts:91-94 (registration)
    Conditional registration of trace tools (including get-trace-stats) by calling loadTraceTools when 'traces' toolset is enabled.
    if (config.enabledToolsets.includes('traces')) {
      server = loadTraceTools(server);
      logToFile('Loaded traces toolset');
    }
Behavior2/5

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

With no annotations provided, the description carries full burden but only states it 'gets' statistics without disclosing behavioral traits like read-only nature, potential rate limits, authentication needs, or what happens if parameters are omitted. It fails to compensate for the lack of annotations.

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, efficient sentence with zero waste. It's appropriately sized and front-loaded, making it easy to parse quickly without unnecessary elaboration.

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?

Given the tool's complexity (5 parameters, no output schema, no annotations), the description is incomplete. It doesn't explain what statistics are returned, how they're formatted, or error conditions, leaving significant gaps for the agent to infer behavior.

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 parameters are fully documented in the schema. The description adds no meaning beyond the schema, such as explaining how parameters interact or default behaviors. Baseline 3 is appropriate as the schema does the heavy lifting.

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

Purpose3/5

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

The description 'Get statistics for traces' states a clear verb ('Get') and resource ('statistics for traces'), but it's vague about what specific statistics are retrieved and doesn't distinguish from sibling tools like 'get-metrics' or 'get-trace-by-id'. It provides basic purpose but lacks specificity.

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?

No guidance is provided on when to use this tool versus alternatives like 'get-metrics' or 'list-traces'. The description doesn't mention prerequisites, exclusions, or context for usage, leaving the agent without direction on tool selection.

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

Related 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/comet-ml/opik-mcp'

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