# BioCatalystFeed (pypi · biocatalystfeed)

Biotech catalyst feed: ClinicalTrials.gov, openFDA, NIH grants, PubMed/Europe PMC, SEC EDGAR.

- Trust score: 65/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-18

## Components

- pypi · `biocatalystfeed`: 65/100 (this document), [markdown](https://verifymcp.io/servers/biocatalystfeed-biocatalystfeed/biocatalystfeed.md), [page](https://verifymcp.io/servers/biocatalystfeed-biocatalystfeed/biocatalystfeed)

## Channel facts

- Registry: `pypi`
- Package: `biocatalystfeed`
- Version: `0.2.2`
- 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 2026-10-18.

- **Supply Chain Security**: 100/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - Runs setuptools.build_meta at install time, a recognised build step with no custom scripting around it.
  - 1 of 32 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 48/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (Apache-2.0).
  - Actively maintained (last published 3 days ago).
  - Publishes a security disclosure policy (SECURITY.md).
- **Schema Quality & AI Usability**: 55/100
  - AI-judged instruction clarity (fair).
  - Tool/resource definitions use about 1309 tokens (~81/item across 16 items; 16 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 0/100
  - Stability not yet verified: not enough scan history yet (needs a 30-day window).
- **Tool Coverage**: 71/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 0% of tool parameters carry a description.
  - Structured output schemas are declared (56% 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 16 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 16 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (2026-07-28).

**Unverified: 1 category.** A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.

## Install

### How do I install the BioCatalystFeed MCP server?

BioCatalystFeed runs locally as a PyPI package, launched with uvx biocatalystfeed. 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 biocatalystfeed-biocatalystfeed -- uvx biocatalystfeed
```

### Cursor

```json
{
  "mcpServers": {
    "biocatalystfeed-biocatalystfeed": {
      "command": "uvx",
      "args": [
        "biocatalystfeed"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "biocatalystfeed-biocatalystfeed": {
      "command": "uvx",
      "args": [
        "biocatalystfeed"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add biocatalystfeed-biocatalystfeed -- uvx biocatalystfeed
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "biocatalystfeed-biocatalystfeed": {
      "type": "local",
      "command": [
        "uvx",
        "biocatalystfeed"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add biocatalystfeed-biocatalystfeed --command uvx --arg biocatalystfeed
```

### Hermes

```yaml
mcp_servers:
  biocatalystfeed-biocatalystfeed:
    command: "uvx"
    args: ["biocatalystfeed"]
```

### Netclaw

```json
{
  "McpServers": {
    "biocatalystfeed-biocatalystfeed": {
      "Transport": "stdio",
      "Command": "uvx",
      "Arguments": [
        "biocatalystfeed"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add biocatalystfeed-biocatalystfeed -t stdio -c uvx -a biocatalystfeed
```

### Other

```json
{
  "mcpServers": {
    "biocatalystfeed-biocatalystfeed": {
      "command": "uvx",
      "args": [
        "biocatalystfeed"
      ]
    }
  }
}
```

## 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.

### 2026-10-15 (score 65, +25)

- [security improvement] Injection markers: unverified → pass
- [security] First check of Judged manipulation: pass
- [security] Stability: Stability not yet verified: not enough scan history yet (needs a 30-day window).
- [functional improvement] Tool coverage: unverified → 100
- [functional improvement] MCP protocol: unverified → pass
- [functional] First check of Tool coverage: 0
- [functional] First check of Schema quality: fail
- [functional] First check of Schema quality: fair
- [functional] First check of Tool coverage: 56
- [functional] First check of Destructive annotations: pass
- [functional] First check of Schema quality: pass

### 2026-10-14 (score 40)

First indexed and scored.

## MCP tools (16)

### `search_trials` (~114 tokens)

Search ClinicalTrials.gov. phases e.g. ["PHASE2","PHASE3"]; statuses e.g. ["RECRUITING"]; changed_since YYYY-MM-DD.
exclude drops trials whose title/conditions/interventions contain any term; rank sorts by relevance to the query.

Input parameters:

- `changed_since`
- `condition`
- `exclude`
- `intervention`
- `max_records` (integer)
- `phases`
- `rank` (boolean)
- `sponsor`
- `statuses`

Output parameters:

- `result` (array)

### `get_trial` (~27 tokens)

Get one normalized trial record by NCT ID.

Input parameters:

- `nct_id` (string, required)

### `snapshot_watch` (~55 tokens)

Snapshot a saved query ('watch') into the local DB and return what changed since its previous snapshot.

Input parameters:

- `condition`
- `intervention`
- `name` (string, required)
- `phases`
- `sponsor`

### `trial_changes_since` (~46 tokens)

List detected changes (new trials, status/phase/enrollment/date changes) since an ISO date, optionally for one watch.

Input parameters:

- `since` (string, required)
- `watch`

Output parameters:

- `result` (array)

### `sponsor_pipeline` (~44 tokens)

Summarize a sponsor's trial pipeline by phase and status, with active trials sorted by primary completion.

Input parameters:

- `max_records` (integer)
- `sponsor` (string, required)

### `fda_approvals` (~105 tokens)

Drugs@FDA submissions/approvals from openFDA (ORIG + supplements), newest first. sponsor is alias-resolved
(e.g. 'Lilly', 'MDGL'); since/until filter submission status date YYYY-MM-DD; novel_only = original NME/BLA approvals.

Input parameters:

- `application_number`
- `max_results` (integer)
- `novel_only` (boolean)
- `since`
- `sponsor`
- `until`

Output parameters:

- `result` (array)

### `company_profile` (~157 tokens)

Merged company view: ClinicalTrials.gov pipeline (lead sponsor, alias-resolved) + FDA applications, novel approvals,
recent FDA actions and label updates, plus (unless basic=True) NIH grants, PubMed papers (affiliation + key drugs),
bioRxiv/medRxiv preprints via Europe PMC (last preprint_days; 0 = skip) and SEC 8-K PDUFA-date
candidates (UNVERIFIED). Accepts name or ticker (e.g. 'Viking Therapeutics', 'TERN').

Input parameters:

- `basic` (boolean)
- `company` (string, required)
- `include_collaborations` (boolean)
- `preprint_days` (integer)
- `recent_days` (integer)

### `fda_changes_since` (~46 tokens)

List detected FDA changes (new submissions, approvals, label revisions) since an ISO date (from fdawatch watches).

Input parameters:

- `since` (string, required)
- `watch`

Output parameters:

- `result` (array)

### `search_grants` (~184 tokens)

NIH RePORTER grants by organization (wildcard unless org_exact), PI name ('Jane A. Doe' or 'Doe, Jane A'; middle
initials respected, pi_exact for strict), keyword (title/terms/abstract; quote phrases, OR allowed) and award notice
date window YYYY-MM-DD. Newest award notice first; future-dated awards flagged and listed after current ones
(include_future=False drops them). exclude drops grants mentioning any term; rank sorts by relevance.

Input parameters:

- `exclude`
- `fiscal_years`
- `include_future` (boolean)
- `keyword`
- `max_results` (integer)
- `org`
- `org_exact` (boolean)
- `pi`
- `pi_exact` (boolean)
- `rank` (boolean)
- `since`
- `until`

Output parameters:

- `result` (array)

### `snapshot_grants` (~67 tokens)

Snapshot a grant query into the local DB; returns new awards / amount / end-date changes since the previous snapshot.

Input parameters:

- `keyword`
- `name` (string, required)
- `org`
- `org_exact` (boolean)
- `pi`
- `since`

### `grant_changes_since` (~40 tokens)

Detected grant changes (new_award, award_amount_change, ...) since an ISO date.

Input parameters:

- `since` (string, required)
- `watch`

Output parameters:

- `result` (array)

### `search_papers` (~162 tokens)

Papers from PubMed, Europe PMC and bioRxiv/medRxiv preprints (via Europe PMC keyword search; bioRxiv API as
fallback), deduplicated by DOI/PMID. sources subset of ["pubmed","europepmc","preprints"] (default all).
affiliation/drug lists are OR'd; keyword is raw query syntax; since = YYYY-MM-DD. exclude drops titles containing
any term; rank sorts by relevance. Metadata + links only.

Input parameters:

- `affiliation`
- `drug`
- `exclude`
- `keyword`
- `max_results` (integer)
- `preprint_days` (integer)
- `rank` (boolean)
- `since`
- `sources`

### `snapshot_papers` (~66 tokens)

Snapshot a paper query (PubMed + optional preprints) and return papers new since the previous snapshot.

Input parameters:

- `affiliation`
- `drug`
- `keyword`
- `name` (string, required)
- `preprint_days` (integer)
- `since`

### `paper_changes_since` (~31 tokens)

New papers/preprints detected since an ISO date.

Input parameters:

- `since` (string, required)
- `watch`

Output parameters:

- `result` (array)

### `sec_pdufa_mentions` (~89 tokens)

SEC EDGAR 8-K documents mentioning "PDUFA" for a company (name, ticker or CIK), with candidate PDUFA dates and
source links. Candidates are UNVERIFIED regex extractions; best=True marks the date nearest each mention.

Input parameters:

- `company` (string, required)
- `max_docs` (integer)
- `since`
- `until`

Output parameters:

- `result` (array)

### `changes_feed` (~76 tokens)

Digest of detected changes as a feed document (format 'json' = JSON Feed 1.1, 'rss' = RSS 2.0).
tool: trials | fda | grants | papers | sec.

Input parameters:

- `format` (string)
- `since`
- `tool` (string)
- `watch`

Output parameters:

- `result` (string)

## Diagnostics

Captured diagnostic sections: Provenance, Install scripts, Dependencies. The full working is on the page: https://verifymcp.io/servers/biocatalystfeed-biocatalystfeed/biocatalystfeed#diagnostics

## Score history

- 2026-10-18: 65
- 2026-10-17: 65
- 2026-10-16: 65
- 2026-10-15: 65
- 2026-10-14: 40

## Common questions

### What is the BioCatalystFeed MCP server?

BioCatalystFeed is an MCP server listed in the public MCP registry as io.github.biocatalystfeed/biocatalystfeed. Biotech catalyst feed: ClinicalTrials.gov, openFDA, NIH grants, PubMed/Europe PMC, SEC EDGAR. This page covers its PyPI package (biocatalystfeed).

### Is the BioCatalystFeed MCP server safe to use?

BioCatalystFeed scores 65 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 18 October 2026. 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 BioCatalystFeed MCP server expose?

BioCatalystFeed exposes 16 tools: search_trials, get_trial, snapshot_watch, trial_changes_since, sponsor_pipeline, and 11 more. Their descriptions and schemas cost roughly 1,309 tokens of context every time the server is loaded.

### Is the BioCatalystFeed MCP server still maintained?

BioCatalystFeed is still listed as active in the MCP registry. We last reached this channel on 18 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What licence is the BioCatalystFeed MCP server under?

BioCatalystFeed declares the Apache-2.0 licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

## Links

- PyPI project: https://pypi.org/project/biocatalystfeed/
- Socket report: https://socket.dev/pypi/package/biocatalystfeed
- Repository: https://github.com/biocatalystfeed/biocatalystfeed
- Changelog RSS feed: https://verifymcp.io/servers/biocatalystfeed-biocatalystfeed/biocatalystfeed.xml
- Changelog JSON feed: https://verifymcp.io/servers/biocatalystfeed-biocatalystfeed/biocatalystfeed.json
- HTML version of this page: https://verifymcp.io/servers/biocatalystfeed-biocatalystfeed/biocatalystfeed