# Hipa.ai Clinical Trials (remote · hipa.ai)

Search recruiting US clinical trials by city, condition, phase and patient eligibility.

- Trust score: 79/100 (medium)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- remote · `hipa.ai`: 79/100 (this document), [markdown](https://verifymcp.io/servers/ai-hipa-clinical-trials/api-mcp-mcp.md), [page](https://verifymcp.io/servers/ai-hipa-clinical-trials/api-mcp-mcp)

## Channel facts

- Endpoint: `https://hipa.ai/api/mcp/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.0.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-05.

- **Endpoint Security**: 80/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - No authorisation is required to call this server. Every tool declares its destructiveHint and none is destructive, so open access doesn't expose one.
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 76/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 2455 tokens (~306/item across 8 items; 8 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 40/100
  - Stability observed for 12 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 93/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 75% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 8 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 9 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the Hipa.ai Clinical Trials MCP server?

Hipa.ai Clinical Trials is a hosted endpoint at https://hipa.ai/api/mcp/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http ai-hipa-clinical-trials 'https://hipa.ai/api/mcp/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "ai-hipa-clinical-trials": {
      "url": "https://hipa.ai/api/mcp/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "ai-hipa-clinical-trials": {
      "type": "http",
      "url": "https://hipa.ai/api/mcp/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.ai-hipa-clinical-trials]
url = "https://hipa.ai/api/mcp/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "ai-hipa-clinical-trials": {
      "type": "remote",
      "url": "https://hipa.ai/api/mcp/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add ai-hipa-clinical-trials --url 'https://hipa.ai/api/mcp/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  ai-hipa-clinical-trials:
    url: "https://hipa.ai/api/mcp/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "ai-hipa-clinical-trials": {
      "Transport": "http",
      "Url": "https://hipa.ai/api/mcp/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add ai-hipa-clinical-trials -t streamable-http -u 'https://hipa.ai/api/mcp/mcp'
```

### Other

```json
{
  "mcpServers": {
    "ai-hipa-clinical-trials": {
      "type": "http",
      "url": "https://hipa.ai/api/mcp/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-11-05 (score 79, +1)

No change was recorded against any check on this day. Stability & Change Management went from 37 to 40. That category is still filling its 30-day observation window: 11 days of observed history at the previous scan, 12 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-03 (score 78, +1)

No change was recorded against any check on this day. Stability & Change Management went from 30 to 33. That category is still filling its 30-day observation window: 9 days of observed history at the previous scan, 10 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-01 (score 77, +1)

- [security improvement] Authorization: unverified → partial
- [security improvement] Injection markers: unverified → pass
- [security improvement] HSTS header: unverified → pass
- [security improvement] Transport: fail → pass
- [functional improvement] Endpoint reachability: unreachable → reachable
- [functional improvement] Tool coverage: unverified → 100
- [functional improvement] Stability: unverified → 0.27
- [functional improvement] Schema quality: unverified → 100
- [functional improvement] MCP protocol: unverified → pass

### 2026-10-31 (score 76, 0)

- [security regression] Endpoint reachability: reachable → unreachable
- [security regression] Authorization: partial → unverified
- [security regression] Tool safety: pass → unverified
- [security regression] HSTS header: pass → unverified
- [security regression] Stability: 0.20 → unverified
- [security regression] Transport: pass → fail
- [functional regression] Schema quality: 100 → unverified
- [functional regression] Capabilities: pass → unverified
- [functional regression] Tool coverage: 100 → unverified

### 2026-10-29 (score 76, +1)

No change was recorded against any check on this day. Stability & Change Management went from 13 to 17. That category is still filling its 30-day observation window: 4 days of observed history at the previous scan, 5 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-27 (score 75, +1)

No change was recorded against any check on this day. Stability & Change Management went from 7 to 10. That category is still filling its 30-day observation window: 2 days of observed history at the previous scan, 3 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-25 (score 74, +1)

- [functional improvement] Stability: unverified → 0.03

### 2026-10-24 (score 73)

First indexed and scored.

## MCP tools (8)

### `clinicaltrials_count_trials` (~411 tokens)

Count Trials

Return only the count of active US clinical trials matching the same filter set accepted by clinicaltrials_search_trials. Use this when the caller needs a population estimate (e.g. 'how many trials are recruiting in California for type 2 diabetes?') without fetching trial records. Far cheaper than calling search and discarding the results.

Input parameters:

- `age` (string): Age bucket for eligibility matching. 'child' = 0-17 years, 'adult' = 18-64 years, 'senior' = 65+ years. Maps to AACT minimum_age/maximum_age boundaries server-side.
- `city` (string): US city name. Allows letters, spaces, hyphens, apostrophes, and periods. Examples: "San Francisco", "St. Louis", "O'Fallon", "Wilkes-Barre". Surrounding whitespace is trimmed; maximum 100 characters.
- `condition` (string): Condition to filter by: a curated slug ('breast-cancer'), its label ('Breast Cancer') or a condition name as it appears in trial records ('Breast Neoplasms'). Case-insensitive. Call clinicaltrials_li…
- `facility` (string): Exact facility name match. Scopes results to trials running at this named site.
- `healthyVolunteersOnly` (boolean)
- `interventionType` (array)
- `phase` (array)
- `sex` (string): Biological sex eligibility filter. Use 'female' or 'male'. Trials open to both sexes are returned regardless of this filter.
- `state` (string, required): Two-letter US state code (e.g. CA, NY, TX, FL). Case-insensitive on input; normalized to uppercase. DC is accepted. Full state names like 'California' are not accepted - use 'CA' instead.
- `status` (array)
- `studyType` (array)

Output parameters:

- `count` (integer): Number of active US trials matching every applied filter.
- `searchCriteria` (object): Echo of the applied filter set so the caller can confirm what the server interpreted.

### `clinicaltrials_find_eligible_trials` (~408 tokens)

Find Eligible Trials

Match patient demographics (age, sex, conditions, location) to currently recruiting US clinical trials. Conditions are curated slugs, labels or trial-record condition names (discover them via clinicaltrials_list_conditions). Maps ageYears to the AACT eligibility bucket (child 0-17, adult 18-64, senior 65+). Returns up to 50 trials per page with an opaque cursor for further pagination. State scope is required; city is optional for facility-level narrowing.

Input parameters:

- `ageYears` (integer, required): Patient age in years. Integer in [0, 120]. Maps to the AACT eligibility bucket: 0-17 child, 18-64 adult, 65+ senior.
- `city` (string): US city name. Allows letters, spaces, hyphens, apostrophes, and periods. Examples: "San Francisco", "St. Louis", "O'Fallon", "Wilkes-Barre". Surrounding whitespace is trimmed; maximum 100 characters.
- `conditions` (array, required): One or more conditions. Unrecognized values are rejected as invalid_input with suggested slugs.
- `cursor` (string): Opaque pagination cursor returned by a previous call's nextCursor field. Omit to start from the beginning of the result set. Cursors are tied to the exact filter set used to issue them - reusing a cu…
- `pageSize` (integer): Number of results per page. Integer in [1, 50]. Default 20.
- `sex` (string): Biological sex eligibility filter. Use 'female' or 'male'. Trials open to both sexes are returned regardless of this filter.
- `state` (string, required): Two-letter US state code (e.g. CA, NY, TX, FL). Case-insensitive on input; normalized to uppercase. DC is accepted. Full state names like 'California' are not accepted - use 'CA' instead.

Output parameters:

- `nextCursor` (string): Opaque cursor to fetch the next page. Absent when no more pages are available.
- `noMatchHints` (array): Actionable suggestions to broaden the eligibility match, present only when totalMatching is zero.
- `searchCriteria` (object): Echo of the applied eligibility criteria so the caller can confirm what the server interpreted.
- `totalMatching` (integer): Total eligible trials matching the criteria across all pages.
- `trials` (array): Trial records that match the eligibility filters, sorted newest first by start_date.

### `clinicaltrials_get_data_freshness` (~54 tokens)

Get Data Freshness

Returns the timestamp at which the underlying ClinicalTrials.gov dataset was last refreshed on the server. Use this to disclose the data age to end users or to decide whether to re-query for fresher results.

Output parameters:

- `humanReadable` (string): Human-readable rendering of the same timestamp in en-US.
- `refreshedAtIso` (string): ISO-8601 UTC timestamp of the last AACT index refresh.

### `clinicaltrials_get_trial` (~171 tokens)

Get Trial

Fetch the full clinical trial record by NCT ID. Returns title, status, sponsor, summary, conditions, interventions, arms, design, eligibility (age, sex, healthy volunteers and the full inclusion/exclusion criteria text), primary outcomes, central contacts, every US site location with its contacts, and links to the trial's Hipa.ai page and ClinicalTrials.gov record. Use this after clinicaltrials_search_trials surfaces a candidate NCT id and the caller needs the complete record - the search tool only returns a paginated summary.

Input parameters:

- `nctId` (string, required): ClinicalTrials.gov identifier. Canonical form: 'NCT' followed by exactly 8 digits (e.g. NCT12345678). Case-insensitive on input; normalized to uppercase. Surrounding whitespace is trimmed.

Output parameters:

- `study` (object): Full clinical trial record: protocol summary, design, eligibility criteria, primary outcomes, central contacts, and every US site location.

### `clinicaltrials_list_conditions` (~172 tokens)

List Conditions

List the curated conditions the trial search tools filter on, with the slug to pass as `condition` (clinicaltrials_search_trials, clinicaltrials_count_trials) or in `conditions` (clinicaltrials_find_eligible_trials). Pass `query` to find a condition by name or synonym (e.g. 'lung', 'diabetes', 'NSCLC'). Ordered by how many recruiting US trials study the condition. Specialty entries (e.g. 'oncology') are roll-ups covering many conditions.

Input parameters:

- `limit` (integer): Maximum conditions to return. Integer in [1, 250]. Default 50.
- `query` (string): Case-insensitive search over condition labels, slugs and synonyms (the raw condition names trial records use). Omit to list the most common conditions.

Output parameters:

- `conditions` (array): Matching conditions, most-studied first.
- `totalMatching` (integer): Matching conditions before the limit was applied.

### `clinicaltrials_list_top_conditions` (~260 tokens)

List Top Conditions

List the most common conditions across active US clinical trials in a US state or city, with trial counts. Use this when the caller wants to see what is well-represented in a region before searching. Each entry carries the curated `slug` to pass to clinicaltrials_search_trials as `condition` (null when the label has no curated match - use clinicaltrials_list_conditions to find a close one). Counts come from AACT condition aggregations and refresh daily.

Input parameters:

- `city` (string): US city name. Allows letters, spaces, hyphens, apostrophes, and periods. Examples: "San Francisco", "St. Louis", "O'Fallon", "Wilkes-Barre". Surrounding whitespace is trimmed; maximum 100 characters.
- `limit` (integer): Maximum number of buckets to return from a top-N aggregation. Integer in [1, 25]. Default 10. Aggregator returns buckets sorted by descending count.
- `state` (string, required): Two-letter US state code (e.g. CA, NY, TX, FL). Case-insensitive on input; normalized to uppercase. DC is accepted. Full state names like 'California' are not accepted - use 'CA' instead.

Output parameters:

- `conditions` (array): Conditions sorted by descending trial count.
- `scope` (object): Echo of the resolved scope so the caller can confirm what the server interpreted.

### `clinicaltrials_list_top_facilities` (~244 tokens)

List Top Facilities

List named research facilities running active US clinical trials in a city, ranked by trial count. Returns each facility's name, ZIP, the top conditions they study, and one example NCT ID for quick verification. Use this when the caller asks where studies are happening in a specific city, or wants to surface named local clinics for a downstream clinicaltrials_search_trials call with the facility filter.

Input parameters:

- `city` (string, required): US city name. Allows letters, spaces, hyphens, apostrophes, and periods. Examples: "San Francisco", "St. Louis", "O'Fallon", "Wilkes-Barre". Surrounding whitespace is trimmed; maximum 100 characters.
- `limit` (integer): Maximum number of buckets to return from a top-N aggregation. Integer in [1, 25]. Default 10. Aggregator returns buckets sorted by descending count.
- `state` (string, required): Two-letter US state code (e.g. CA, NY, TX, FL). Case-insensitive on input; normalized to uppercase. DC is accepted. Full state names like 'California' are not accepted - use 'CA' instead.

Output parameters:

- `facilities` (array): Facilities sorted by descending trial count.
- `scope` (object): Echo of the resolved scope so the caller can confirm what the server interpreted.

### `clinicaltrials_search_trials` (~528 tokens)

Search Trials

Search active US clinical trials by location, condition slug, phase, study type, intervention type, recruitment status, sex eligibility, age bucket, healthy-volunteer flag, and facility name. Returns up to 50 trials per page with an opaque cursor for further pagination. Cursors are tied to the exact filter set used to issue them - reusing a cursor with a different filter set returns invalid_cursor. Use state-only scope first when exploring a region, then narrow to city for facility-level detail.

Input parameters:

- `age` (string): Age bucket for eligibility matching. 'child' = 0-17 years, 'adult' = 18-64 years, 'senior' = 65+ years. Maps to AACT minimum_age/maximum_age boundaries server-side.
- `city` (string): US city name. Allows letters, spaces, hyphens, apostrophes, and periods. Examples: "San Francisco", "St. Louis", "O'Fallon", "Wilkes-Barre". Surrounding whitespace is trimmed; maximum 100 characters.
- `condition` (string): Condition to filter by: a curated slug ('breast-cancer'), its label ('Breast Cancer') or a condition name as it appears in trial records ('Breast Neoplasms'). Case-insensitive. Call clinicaltrials_li…
- `cursor` (string): Opaque pagination cursor returned by a previous call's nextCursor field. Omit to start from the beginning of the result set. Cursors are tied to the exact filter set used to issue them - reusing a cu…
- `facility` (string): Exact facility name match. Scopes results to trials running at this named site.
- `healthyVolunteersOnly` (boolean)
- `interventionType` (array)
- `pageSize` (integer): Number of results per page. Integer in [1, 50]. Default 20.
- `phase` (array)
- `sex` (string): Biological sex eligibility filter. Use 'female' or 'male'. Trials open to both sexes are returned regardless of this filter.
- `state` (string, required): Two-letter US state code (e.g. CA, NY, TX, FL). Case-insensitive on input; normalized to uppercase. DC is accepted. Full state names like 'California' are not accepted - use 'CA' instead.
- `status` (array)
- `studyType` (array)

Output parameters:

- `nextCursor` (string): Opaque cursor to fetch the next page. Absent when no more pages are available.
- `noMatchHints` (array): Actionable suggestions to broaden the search, present only when totalMatching is zero.
- `searchCriteria` (object): Echo of the applied filter set so the caller can confirm what the server interpreted.
- `totalMatching` (integer): Total trials matching the filters across all pages.
- `trials` (array): Trial records for the current page, sorted newest first by start_date.

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/ai-hipa-clinical-trials/api-mcp-mcp#diagnostics

## Score history

- 2026-11-05: 79
- 2026-11-04: 78
- 2026-11-03: 78
- 2026-11-02: 77
- 2026-11-01: 77
- 2026-10-31: 76
- 2026-10-30: 76
- 2026-10-29: 76
- 2026-10-28: 75
- 2026-10-27: 75
- 2026-10-26: 74
- 2026-10-25: 74
- 2026-10-24: 73

## Common questions

### What is the Hipa.ai Clinical Trials MCP server?

Hipa.ai Clinical Trials is an MCP server listed in the public MCP registry as ai.hipa/clinical-trials. Search recruiting US clinical trials by city, condition, phase and patient eligibility. This page covers its hosted endpoint (https://hipa.ai/api/mcp/mcp).

### Is the Hipa.ai Clinical Trials MCP server safe to use?

Hipa.ai Clinical Trials scores 79 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the Hipa.ai Clinical Trials MCP server expose?

Hipa.ai Clinical Trials exposes 8 tools: clinicaltrials_count_trials, clinicaltrials_find_eligible_trials, clinicaltrials_get_data_freshness, clinicaltrials_get_trial, clinicaltrials_list_conditions, and 3 more. Their descriptions and schemas cost roughly 2,248 tokens of context every time the server is loaded.

### Does the Hipa.ai Clinical Trials MCP server require authentication?

No. We connected to Hipa.ai Clinical Trials without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the Hipa.ai Clinical Trials MCP server still maintained?

Hipa.ai Clinical Trials is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://hipa.ai/api/mcp/mcp
- Website: https://hipa.ai/mcp/docs
- Changelog RSS feed: https://verifymcp.io/servers/ai-hipa-clinical-trials/api-mcp-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/ai-hipa-clinical-trials/api-mcp-mcp.json
- HTML version of this page: https://verifymcp.io/servers/ai-hipa-clinical-trials/api-mcp-mcp