# io.github.OrchestraPrime/orchestraprime (npm · @orchestraprime/mcp-server)

Regulatory intelligence (FDA, ICH, EMA) and sanctions screening (OFAC, EU, UK) for Claude

- Trust score: 71/100 (medium)
- Change this week: +18
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- npm · `@orchestraprime/mcp-server`: 71/100 (this document), [markdown](https://verifymcp.io/servers/orchestraprime-orchestraprime/orchestraprime-mcp-server.md), [page](https://verifymcp.io/servers/orchestraprime-orchestraprime/orchestraprime-mcp-server)

## Channel facts

- Registry: `npm`
- Package: `@orchestraprime/mcp-server`
- Version: `2.0.1`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, 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 2026-08-03.

- **Supply Chain Security**: 88/100
  - No malware found by supply-chain analysis.
  - Only part of the dependency tree could be resolved (113 of 114), so this covers what we could see, not the whole tree.
  - No install/post-install scripts declared.
  - Only part of the dependency tree could be resolved (113 of 114), so this covers what we could see, not the whole tree.
- **Provenance & Transparency**: 45/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 175 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 83/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 1175 tokens (~90/item across 13 items; 9 tools + 4 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 27/100
  - Stability observed for 8 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### Claude

```bash
claude mcp add orchestraprime-orchestraprime -- npx -y @orchestraprime/mcp-server
```

### Codex

```bash
codex mcp add orchestraprime-orchestraprime -- npx -y @orchestraprime/mcp-server
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "orchestraprime-orchestraprime": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "@orchestraprime/mcp-server"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add orchestraprime-orchestraprime --command npx --arg -y --arg @orchestraprime/mcp-server
```

### Hermes

```yaml
mcp_servers:
  orchestraprime-orchestraprime:
    command: "npx"
    args: ["-y", "@orchestraprime/mcp-server"]
```

### Other

```json
{
  "mcpServers": {
    "orchestraprime-orchestraprime": {
      "command": "npx",
      "args": [
        "-y",
        "@orchestraprime/mcp-server"
      ]
    }
  }
}
```

## 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.

### 2026-08-03 (score 71, +1)

No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-08-02 (score 70, +65)

- [security regression] Provenance: unverified → fail
- [security improvement] Known CVEs: unverified → partial
- [security improvement] Install scripts: unverified → pass
- [security improvement] Malware scan: unverified → pass
- [security] Stability: Stability not yet verified: not enough scan history yet (needs a 30-day window).
- [functional regression] Security disclosure: unverified → fail
- [functional improvement] Stability: unverified → 0.23
- [functional improvement] Maintenance: unverified → pass
- [functional improvement] Dependency health: unverified → partial
- [functional improvement] License: unverified → pass
- [functional improvement] MCP protocol: unverified → pass
- [functional improvement] Schema quality: unverified → 100
- [functional improvement] Tool coverage: unverified → 100
- [functional] Licence: MIT

### 2026-08-01 (score 5, −32)

- [security] Stability: Stability not yet verified: we do not have a sandbox capture of the MCP schema this version of the package serves yet.
- [functional regression] Security disclosure: fail → unverified
- [functional regression] Capabilities: pass → unverified
- [functional regression] Tool coverage: 100 → unverified
- [functional regression] Schema quality: 100 → unverified

### 2026-07-31 (score 37, −27)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-30 (score 64, −11)

- [security regression] Malware scan: pass → unverified
- [functional improvement] Schema quality: unverified → good

### 2026-07-29 (score 75, +50)

- [security regression] Provenance: unverified → fail
- [security improvement] Install scripts: unverified → pass
- [security improvement] Known CVEs: unverified → partial
- [functional regression] Security disclosure: unverified → fail
- [functional improvement] Schema quality: unverified → 100
- [functional improvement] License: unverified → pass
- [functional improvement] Tool coverage: unverified → 100
- [functional improvement] Maintenance: unverified → pass
- [functional] Licence: MIT

### 2026-07-28 (score 25, −28)

- [functional regression] Tool coverage: 100 → unverified
- [functional regression] Security disclosure: fail → unverified
- [functional regression] Schema quality: 100 → unverified
- [functional improvement] Dependency health: unverified → partial

### 2026-07-27 (score 53)

First indexed and scored.

## MCP tools (9)

### `check_cds_classification` (~200 tokens)

Analyze software against FDA Clinical Decision Support (CDS) 4-criteria
to determine if it qualifies for the CDS exemption under the 21st Century
Cures Act Section 3060.

When to use: When you need to assess whether a software product requires
FDA clearance/approval or qualifies as exempt CDS. Evaluates all 4 criteria:
1\. Not intended to acquire/process medical images or signals
2\. Intended to display, analyze, or print medical information
3\. Intended for healthcare professionals (not patients)
4\. Does not provide specific diagnostic/treatment recommendations

Classification: EXEMPT (all 4 met) or DEVICE (any criterion failed)

Input parameters:

- `intended_use` (string, required): Intended use statement for the software
- `software_description` (string, required): Detailed description of the software's functionality and features
- `target_user` (string): Primary target user of the software (inferred from text if not provided)

### `check_protocol_compliance` (~136 tokens)

Analyze a clinical trial protocol against ICH GCP E6(R2) required elements.
Checks for presence and completeness of 8 essential protocol sections:
background, objectives, design, subjects, treatment, safety, statistical, ethics.

When to use: During protocol review to identify missing or incomplete
sections before submission. Provides gap analysis with specific recommendations.

Overall status: compliant (0 gaps), gaps_found (1-2 gaps), major_gaps (3+)

Input parameters:

- `check_categories` (array): Specific protocol categories to check (default all 8)
- `protocol_text` (string, required): The clinical trial protocol text to analyze

### `get_recent_updates` (~122 tokens)

Get recent regulatory updates and guidance changes from FDA, ICH, EMA,
WHO, and CDISC. Shows new guidance documents, rule changes, and announcements.

When to use: To check what regulatory changes have happened recently,
or to stay current on guidance updates in specific areas.

Note: Currently uses curated sample data. Real-time API integration coming soon.

Input parameters:

- `days_back` (number): Number of days to look back for updates
- `limit` (number): Maximum number of updates to return
- `sources` (array): Filter updates to specific regulatory sources

### `get_rule_details` (~82 tokens)

Retrieve the full text, citations, and metadata for a specific regulatory rule.
Use rule IDs obtained from search_regulations results.

When to use: After finding a relevant rule via search_regulations, use this tool
to get the complete rule text, effective dates, and citation information.

Input parameters:

- `rule_id` (string, required): Unique rule identifier from search_regulations results

### `list_sanctions_lists` (~75 tokens)

List all available sanctions lists with entity counts and coverage details.
Includes OFAC SDN, OFAC Consolidated, EU Sanctions, UK HMT, UN Consolidated,
and BIS DPL.

When to use: To see which sanctions lists are available for screening,
or to check entity coverage and last update dates.

### `list_sources` (~51 tokens)

List all available regulatory data sources in CTWise, including rule counts
and last update timestamps.

When to use: To see what regulatory databases are available for searching,
or to check how many rules each source contains.

### `screen_batch` (~145 tokens)

Screen multiple individuals or organizations against global sanctions lists
in a single batch operation. Supports up to 100 entities per batch.

When to use: For bulk compliance screening during due diligence processes,
onboarding multiple counterparties, or periodic re-screening of entity lists.

IMPORTANT: Results are NEVER cached and always reflect real-time data.
Results should be reviewed by compliance professionals.

Input parameters:

- `entities` (array, required): Array of entities to screen (each with id, name, and optional entity_type)
- `lists` (array): Sanctions lists to screen against
- `max_results_per_entity` (number): Maximum matches per entity
- `threshold` (number): Match confidence threshold for all entities

### `screen_entity` (~169 tokens)

Screen an individual or organization against global sanctions lists including
OFAC SDN, OFAC Consolidated, EU Sanctions, UK HMT, UN Consolidated, and BIS DPL.

When to use: For compliance checks on counterparties, customers, or business
partners. Results include match confidence scores and source evidence.

IMPORTANT: Results are NEVER cached and always reflect real-time data.
Results should be reviewed by compliance professionals.

Input parameters:

- `entity_type` (string): Type of entity being screened
- `lists` (array): Specific sanctions lists to screen against
- `max_results` (number): Maximum number of matches to return
- `name` (string, required): Full name of the individual or organization to screen
- `threshold` (number): Match confidence threshold (0.5 to 1.0)

### `search_regulations` (~131 tokens)

Search across FDA, ICH, EMA, WHO, and CDISC regulatory databases using natural language.
Returns relevant rules with citations, summaries, and reference links.

When to use: When you need to find specific regulatory requirements, guidance documents,
or rules related to a topic. Supports queries like "What FDA requirements apply to AI
diagnostic software?" or "ICH GCP informed consent requirements".

Input parameters:

- `limit` (number): Maximum number of results to return
- `query` (string, required): Natural language search query for regulatory content
- `sources` (array): Filter results to specific regulatory sources (default all)

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/orchestraprime-orchestraprime/orchestraprime-mcp-server#diagnostics

## Score history

- 2026-08-03: 71
- 2026-08-02: 70
- 2026-08-01: 5
- 2026-07-31: 37
- 2026-07-30: 64
- 2026-07-29: 75
- 2026-07-28: 25
- 2026-07-27: 53

## Links

- npm package: https://www.npmjs.com/package/@orchestraprime/mcp-server
- Socket report: https://socket.dev/npm/package/@orchestraprime/mcp-server
- Repository: https://github.com/OrchestraPrime/mcp-server
- Changelog RSS feed: https://verifymcp.io/servers/orchestraprime-orchestraprime/orchestraprime-mcp-server/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/orchestraprime-orchestraprime/orchestraprime-mcp-server/changelog.json
- HTML version of this page: https://verifymcp.io/servers/orchestraprime-orchestraprime/orchestraprime-mcp-server