Connect Health Research to Codex
Query Health Research directly from Codex. Arlet links the two through one MCP connection and takes care of API keys.
Separates 'what the synthesized literature says', 'what is still being tested' and 'what the population-level statistics show'.
Tools:
- search_health_evidence: Europe PMC filtered to reviews, meta-analyses and cohort studies, so results rest on synthesized or population-level evidence rather than one small trial.
- search_clinical_trials: ClinicalTrials.gov API v2. Returns NCT ID, recruitment status, phase, study type, planned enrollment and start date — the fastest way to see whether an intervention is still under investigation rather than established.
- find_who_indicators: search WHO GHO indicators by name to get an indicator_code.
- get_who_indicator_values: fetch data points for that code, optionally filtered to one country (ISO3), for international comparison.
The WHO tools are deliberately two steps: indicator codes are opaque strings, and guessing them produces silently wrong data, so the code must come from a search.
Abstracts are returned only for open-access articles under a CC license; other records carry metadata and a link.
This server reports published findings, trial registrations and official statistics. It does not diagnose, recommend treatment, or replace a clinician — anyone with symptoms or a medical condition should consult a physician.
How to connect Health Research to Codex
- 1
In the Arlet dashboard, open Data tools, find Health Research and switch it on. No API key setup is needed.
- 2
In your terminal, run codex mcp add arlet --url https://mcp.arlet.dev/mcp/ to add Arlet as an MCP server.
- 3
Codex detects OAuth support and opens your browser. Sign in with Google and click Allow on the consent screen.
- 4
Once connected, both the CLI and the IDE extension can call Arlet tools (the configuration is shared).
If the browser does not open, run codex mcp login arlet to redo the authentication.