Skip to main content
Glama
Signal8 MCP Server

Signal8 MCP Server

Official

Search Clinical Trials

search_clinical_trials
Read-only

Search clinical trials across companies by phase, indication, sponsor, status, and date window. Filter, sort, and paginate trial results to compare pipelines market-wide.

Instructions

Search clinical trials market-wide (across companies), filtered by phase, indication, sponsor, status and date window, with sorting and pagination. An unrecognised phase, status, dateField or sort value is rejected with the allowed list (it is never silently ignored). A result's ticker is the company whose trial list the row was collected under, which may be the lead sponsor or only a collaborator; metadata.sponsor is the lead sponsor, so a row is that ticker's own trial only when metadata.sponsor is that company.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "search_clinical_trials"
  }
}

Input Schema

NameRequiredDescriptionDefault
toNoInclusive end: YYYY, YYYY-MM or YYYY-MM-DD (a partial date covers its whole year/month)
fromNoInclusive start: YYYY, YYYY-MM or YYYY-MM-DD
sortNoSort column (default primary_completion_date)
limitNoMaximum results to return (1-100, default: 50)
orderNoSort direction
phaseNoComma-separated phases, matching ANY of them. Allowed tokens: EARLY_PHASE1, PHASE1, PHASE2, PHASE3, PHASE4 (also accepted: "Phase 2", "2", "Early Phase 1"). Example: "PHASE2,PHASE3". A combined "Phase 2/Phase 3" string is rejected; each phase is a separate token.
offsetNoOffset for pagination (default: 0)
statusNoONE ClinicalTrials.gov overall status
sponsorNoCase-insensitive substring of the LEAD sponsor name (collaborators are not searched)
dateFieldNoDate column the from/to window applies to (default primary_completion_date)
indicationNoComma-separated condition names, exact match (case-sensitive), e.g. "Breast Cancer"

Output Schema

NameRequiredDescriptionDefault
dataNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed11 schema fields changedv0.20.0
    • changedInput schema / properties / dateField / description
      Previous value: -"Date field to filter/sort on"New value: +"Date column the from/to window applies to (default primary_completion_date)"
    • addedInput schema / properties / dateField / enum
      Added value: +[
      +  "primary_completion_date",
      +  "completion_date",
      +  "start_date",
      +  "last_update_date"
      +]
    • changedInput schema / properties / from / description
      Previous value: -"Start date (YYYY-MM-DD)"New value: +"Inclusive start: YYYY, YYYY-MM or YYYY-MM-DD"
    • changedInput schema / properties / indication / description
      Previous value: -"Condition / indication filter"New value: +"Comma-separated condition names, exact match (case-sensitive), e.g. \"Breast Cancer\""
    • changedInput schema / properties / phase / description
      Previous value: -"Trial phase filter (e.g., \"Phase 3\")"New value: +"Comma-separated phases, matching ANY of them. Allowed tokens: EARLY_PHASE1, PHASE1, PHASE2, PHASE3, PHASE4 (also accepted: \"Phase 2\", \"2\", \"Early Phase 1\"). Example: \"PHASE2,PHASE3\". A combined \"Phase 2/Phase 3\" string is rejected; each phase is a separate token."
    • changedInput schema / properties / sort / description
      Previous value: -"Sort field"New value: +"Sort column (default primary_completion_date)"
    • addedInput schema / properties / sort / enum
      Added value: +[
      +  "primary_completion_date",
      +  "completion_date",
      +  "start_date",
      +  "last_update_date",
      +  "updated_at"
      +]
    • changedInput schema / properties / sponsor / description
      Previous value: -"Sponsor name filter"New value: +"Case-insensitive substring of the LEAD sponsor name (collaborators are not searched)"
    • changedInput schema / properties / status / description
      Previous value: -"Trial status filter"New value: +"ONE ClinicalTrials.gov overall status"
    • addedInput schema / properties / status / enum
      Added value: +[
      +  "ACTIVE_NOT_RECRUITING",
      +  "COMPLETED",
      +  "ENROLLING_BY_INVITATION",
      +  "NOT_YET_RECRUITING",
      +  "RECRUITING",
      +  "SUSPENDED",
      +  "TERMINATED",
      +  "WITHDRAWN",
      +  "AVAILABLE",
      +  "NO_LONGER_AVAILABLE",
      +  "TEMPORARILY_NOT_AVAILABLE",
      +  "APPROVED_FOR_MARKETING",
      +  "WITHHELD",
      +  "UNKNOWN"
      +]
    • changedInput schema / properties / to / description
      Previous value: -"End date (YYYY-MM-DD)"New value: +"Inclusive end: YYYY, YYYY-MM or YYYY-MM-DD (a partial date covers its whole year/month)"
  2. First observedv0.1.0

TDQS

A3.8/5.0
Behavior4/5

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

Annotations already establish readOnly, non-destructive, closed-world behavior, and the description adds two things they do not: strictly-validated inputs that are rejected with the allowed list rather than silently ignored, and the attribution caveat that a row's ticker is the collection bucket, not necessarily the lead sponsor. These are genuinely non-obvious behavioral traits that materially affect interpretation. It lacks any note on result volume, pagination limits beyond the schema, or ordering of returned rows.

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?

Three sentences, front-loaded with scope and capabilities before the two caveats. Every sentence earns its place, though the final ticker/sponsor sentence is dense and could be tightened. No filler or marketing language.

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

Completeness4/5

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

An output schema exists, so return-value explanation is not needed, and all 11 parameters are documented in the schema. The description covers scope, validation strictness, and the one output-semantics trap (ticker vs lead sponsor). It would be complete at 5 with a brief pointer to get_clinical_trials for the single-company case.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3 and the schema already carries enum lists and defaults. The description still adds cross-parameter meaning the schema cannot express: rejected-but-not-ignored validation behavior and the relationship between the result ticker and metadata.sponsor, which changes how a caller should read the filter output. Marginal gain is real, though most per-parameter detail is duplicated from the 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?

The description opens with a specific verb+resource ("Search clinical trials") and immediately scopes it as "market-wide (across companies)", which implicitly separates it from the per-company get_clinical_trials sibling. It also enumerates the filter dimensions (phase, indication, sponsor, status, date window) plus sorting and pagination, so an agent knows the surface precisely. It falls just short of 5 because the sibling it is not (get_clinical_trials) is never named, leaving the reader to infer the contrast.

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?

Usage context is implied by the "market-wide (across companies)" phrasing and the filter list, but there is no explicit when-to-use / when-not-to-use statement and no named alternative such as get_clinical_trials for single-company lookups. The ticker-versus-sponsor explanation does function as practical guidance for interpreting results. Adequate but the routing decision is left to inference.

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

Deploy Server

Other Tools