Skip to main content
Glama
BACH-AI-Tools

Clinical Trials MCP Server

get_trial_statistics

Analyze clinical trial data by grouping aggregate statistics across phases, statuses, study types, conditions, or sponsors to identify research trends and patterns.

Instructions

Get aggregate statistics about clinical trials

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
groupByNoField to group statistics by
filtersNoOptional filters to apply

Implementation Reference

  • Handler implementation for the get_trial_statistics tool.
    private async handleGetTrialStatistics(args: any) {
      // For statistics, we'll make a broader search and analyze the results
      const params: any = {
        format: "json",
        pageSize: 100, // Get more results for better statistics
      };
    
      // Apply filters if provided
      if (args?.filters?.condition) {
        params["query.cond"] = args.filters.condition;
      }
      if (args?.filters?.phase) {
        params["filter.phase"] = args.filters.phase;
      }
      if (args?.filters?.status) {
        params["filter.overallStatus"] = args.filters.status;
      }
    
      try {
        const response: AxiosResponse<StudySearchResponse> =
          await this.axiosInstance.get("/studies", { params });
    
        const studies = response.data.studies || [];
        const stats = this.calculateStatistics(studies, args?.groupBy);
    
        return {
          content: [
            {
              type: "text",
              text: JSON.stringify(
                {
                  totalStudies: response.data.totalCount || 0,
                  analyzedStudies: studies.length,
                  groupBy: args?.groupBy || "none",
                  filters: args?.filters || {},
                  statistics: stats,
                },
                null,
                2
              ),
            },
          ],
        };
      } catch (error) {
        if (axios.isAxiosError(error)) {
          return {
            content: [
              {
                type: "text",
                text: `Clinical Trials API error: ${
                  error.response?.data?.message || error.message
                }`,
              },
            ],
            isError: true,
          };
        }
        throw error;
      }
    }
  • src/index.ts:277-298 (registration)
    Tool definition and schema registration for get_trial_statistics.
      name: "get_trial_statistics",
      description: "Get aggregate statistics about clinical trials",
      inputSchema: {
        type: "object",
        properties: {
          groupBy: {
            type: "string",
            description: "Field to group statistics by",
            enum: ["phase", "status", "studyType", "condition", "sponsor"],
          },
          filters: {
            type: "object",
            description: "Optional filters to apply",
            properties: {
              condition: { type: "string" },
              phase: { type: "string" },
              status: { type: "string" },
            },
          },
        },
      },
    },
  • Helper functions to calculate statistics from study data.
    private calculateStatistics(studies: Study[], groupBy?: string) {
      if (!groupBy) {
        return {
          totalStudies: studies.length,
          byStatus: this.groupByField(studies, "status"),
          byPhase: this.groupByField(studies, "phase"),
          byStudyType: this.groupByField(studies, "studyType"),
        };
      }
    
      return this.groupByField(studies, groupBy);
    }
    
    private groupByField(studies: Study[], field: string) {
      const groups: { [key: string]: number } = {};
    
      studies.forEach((study) => {
        let value: string | string[];
    
        switch (field) {
          case "status":
            value = study.protocolSection.statusModule.overallStatus;
            break;
          case "phase":
            value =
              study.protocolSection.designModule?.phases?.[0] || "Not specified";
            break;
          case "studyType":
            value = study.protocolSection.designModule?.studyType || "Unknown";
            break;
          case "condition":
            value =
              study.protocolSection.conditionsModule?.conditions?.[0] ||
              "Not specified";
            break;
          case "sponsor":
            value =
              study.protocolSection.sponsorCollaboratorsModule?.leadSponsor
                ?.name || "Not specified";
            break;
          default:
            value = "Unknown";
        }
    
        const key = Array.isArray(value) ? value[0] : value;
        groups[key] = (groups[key] || 0) + 1;
      });
    
      return groups;
    }

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.1

TDQS

C2.9/5.0
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 only says 'Get aggregate statistics' which implies a read operation, but it does not explain what statistics are returned, how filters affect results, or any limitations. This is insufficient for a tool with no additional structured behavioral metadata.

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?

The description is a single concise sentence that is front-loaded with the action and resource. It has no unnecessary words or repetition, though it could arguably provide more detail without becoming verbose.

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?

The tool has moderate complexity with a nested filters object and no output schema, but the description does not explain return values, what 'statistics' means (e.g., counts, distributions), or how groupBy affects the output. This leaves significant gaps for an agent trying to use it effectively.

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 input schema already provides 100% coverage for both parameters, including descriptions for filters and groupBy, and an enum for groupBy. The description adds no extra meaning beyond what the schema provides, so the baseline of 3 is appropriate.

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 tool's function: getting aggregate statistics about clinical trials. It uses a specific verb and resource, and while it doesn't explicitly distinguish itself from sibling tools, 'statistics' sets it apart from the search/detail-focused siblings.

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 given about when to use this tool versus alternatives like search_studies or get_study_details. The description does not mention any context in which aggregate statistics would be preferred, nor any exclusions.

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