mcpField
T
Trials & Drug Resolver

Trials & Drug Resolver

Local
biolytai.comOther
RepositoryVisit website

About Trials & Drug Resolver

Harmonise drug names and clinical trials using public licence-clean APIs.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "postlytllp-trials-drug-resolver": {
      "command": "npx",
      "args": [
        "-y",
        "trials-drug-resolver-mcp"
      ],
      "env": {
        "BIOLYT_CTA": "<BIOLYT_CTA>",
        "RESOLVER_LLM": "<RESOLVER_LLM>",
        "RESOLVER_LLM_API_KEY": "<RESOLVER_LLM_API_KEY>",
        "RESOLVER_LLM_MODEL": "<RESOLVER_LLM_MODEL>",
        "RESOLVER_LLM_BASE_URL": "<RESOLVER_LLM_BASE_URL>",
        "RESOLVER_EMBEDDINGS": "<RESOLVER_EMBEDDINGS>",
        "RESOLVER_EMBEDDINGS_URL": "<RESOLVER_EMBEDDINGS_URL>",
        "RESOLVER_EMBEDDINGS_API_KEY": "<RESOLVER_EMBEDDINGS_API_KEY>"
      }
    }
  }
}
Run commandnpx -y trials-drug-resolver-mcp
Environment variables to set
BIOLYT_CTASet to 1 to append the optional static Biolyt AI footer. Default off. Does not generate news.
RESOLVER_LLMOptional candidate picker: off (default), openai, anthropic, or http.
RESOLVER_LLM_API_KEYSecretAPI key for the optional LLM picker. Unused when RESOLVER_LLM=off.
RESOLVER_LLM_MODELModel name for the optional LLM picker.
RESOLVER_LLM_BASE_URLOpenAI-compatible or custom HTTP base URL for the optional LLM picker.
RESOLVER_EMBEDDINGSOptional embedding retriever: off (default) or http.
RESOLVER_EMBEDDINGS_URLHTTP endpoint for the optional embedding retriever.
RESOLVER_EMBEDDINGS_API_KEYSecretBearer token for the optional embedding retriever.

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npmtrials-drug-resolver-mcp1.0.0

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

The maintainer has not added details yet. Check the README in the repository.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.