# pubmed-stream (pypi · pubmed-stream)

Search PubMed and PMC, read full texts, map evidence and build Obsidian knowledge graphs

- Trust score: 52/100 (low)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-23

## Components

- pypi · `pubmed-stream`: 52/100 (this document), [markdown](https://verifymcp.io/servers/melhzy-pubmed-stream/pubmed-stream.md), [page](https://verifymcp.io/servers/melhzy-pubmed-stream/pubmed-stream)

## Channel facts

- Registry: `pypi`
- Package: `pubmed-stream`
- Version: `0.4.4`
- 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 2026-10-23.

- **Supply Chain Security**: 50/100
  - Malware scan not yet available for this package.
  - 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.
  - 0 of 5 dependencies flagged as unhealthy.
- **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 0 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 63/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 1326 tokens (~147/item across 9 items; 9 tools + 0 resources), over budget; trim descriptions and params.
  - 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**: 89/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 66% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 9 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 10 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.

**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 pubmed-stream MCP server?

pubmed-stream runs locally as a PyPI package, launched with uvx pubmed-stream. 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 melhzy-pubmed-stream -- uvx pubmed-stream
```

### Cursor

```json
{
  "mcpServers": {
    "melhzy-pubmed-stream": {
      "command": "uvx",
      "args": [
        "pubmed-stream"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "melhzy-pubmed-stream": {
      "command": "uvx",
      "args": [
        "pubmed-stream"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add melhzy-pubmed-stream -- uvx pubmed-stream
```

### opencode

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

### OpenClaw

```bash
openclaw mcp add melhzy-pubmed-stream --command uvx --arg pubmed-stream
```

### Hermes

```yaml
mcp_servers:
  melhzy-pubmed-stream:
    command: "uvx"
    args: ["pubmed-stream"]
```

### Netclaw

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

### Vellum

```bash
assistant mcp add melhzy-pubmed-stream -t stdio -c uvx -a pubmed-stream
```

### Other

```json
{
  "mcpServers": {
    "melhzy-pubmed-stream": {
      "command": "uvx",
      "args": [
        "pubmed-stream"
      ]
    }
  }
}
```

## 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.

### 2026-10-23 (score 52)

First indexed and scored.

## MCP tools (9)

### `search_pmc` (~112 tokens)

Size a PMC search

Count a PubMed Central search and list its newest matches, without downloading. Use PubMed field tags: [Title], [Title/Abstract], [mh] for MeSH, "open access"[filter]. Plain words match anywhere in the full text, so most results are off topic.

Input parameters:

- `query` (string, required): PMC search, e.g. "gut microbiota"[Title] AND parkinson[Title]
- `show` (integer): How many of the newest matches to list (0 for the count)

### `download` (~89 tokens)

Download full texts

Download the newest matches of a PMC search as JSON files, one per article, into <output_dir>/<folder named after the search>. Existing files are skipped. Articles whose publishers forbid downloading are counted as unavailable.

Input parameters:

- `max_results` (integer)
- `output_dir` (string): Folder of downloads, relative to the project
- `query` (string, required): PMC search, checked first with search_pmc

### `fetch_abstracts` (~108 tokens)

Save PubMed abstracts

Save the abstracts of a PubMed search's newest matches, including articles whose full text is not free in PMC, into the same folder download uses. list_articles then shows them marked [abstract only]. Use it when search_pmc reports many more articles in PubMed than in PMC.

Input parameters:

- `max_results` (integer)
- `output_dir` (string): Folder of downloads, relative to the project
- `query` (string, required): The same search as for search_pmc and download

### `list_articles` (~106 tokens)

List downloaded articles

Downloaded articles, newest first, each once: identifiers, year, journal, title and length. With ids, only those articles; with abstracts, their abstracts too. Scan titles first, then read the abstracts of the articles that bear on the question.

Input parameters:

- `abstracts` (boolean)
- `ids` (array): PubMed IDs or PMC IDs
- `limit` (integer): Only the newest N articles
- `path` (string): Folder of downloads, relative to the project

### `most_cited` (~53 tokens)

Most cited works

The works the downloaded articles cite most: the field's foundations, and good key papers for the neighborhood tool.

Input parameters:

- `n` (integer)
- `path` (string): Folder of downloads, relative to the project

### `read_article` (~99 tokens)

Read one article's full text

The full text of one downloaded article. With find, only the paragraphs that contain the term, numbered, which is usually enough; without it, the text up to max_chars.

Input parameters:

- `find` (string): Term to search for, case-insensitive
- `id` (string, required): PubMed ID or PMC ID of a downloaded article
- `max_chars` (integer)
- `path` (string): Folder of downloads, relative to the project

### `neighborhood` (~94 tokens)

Evidence around one paper

Similar, citing and cited papers of one PubMed article, with counts of reviews, retractions and NIH funding, and the retracted papers named. Saved as <output_dir>/neighborhood_<pmid>/neighborhood.json.

Input parameters:

- `max_per_relation` (integer)
- `output_dir` (string): Folder of downloads, relative to the project
- `pmid` (string, required): PubMed ID, not a PMC ID

### `export_citations` (~100 tokens)

Export citations

Write the downloaded articles, or chosen ones, as a BibTeX or RIS file that Zotero, EndNote or Mendeley imports. Give the researcher the file's path.

Input parameters:

- `file` (string): File to write, relative to the project
- `format` (string)
- `ids` (array): PubMed or PMC IDs; all articles when omitted
- `path` (string): Folder of downloads, relative to the project

### `build_knowledge_graph` (~143 tokens)

Build or refresh a knowledge graph

Link a study's searches and key papers into an Obsidian vault, kg_<topic>, with notes for papers, MeSH concepts and searches. Later calls with the same topic add to it; refresh reruns every recorded search and key paper.

Input parameters:

- `abstracts` (boolean): Also save PubMed abstracts, so articles without free full text join
- `max_per_relation` (integer)
- `max_results` (integer)
- `queries` (array)
- `refresh` (boolean)
- `seeds` (array): PubMed IDs of key papers
- `topic` (string, required): Short study name, e.g. gut microbiome parkinson

## Diagnostics

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

## Score history

- 2026-10-23: 52

## Common questions

### What is the pubmed-stream MCP server?

pubmed-stream is an MCP server listed in the public MCP registry as io.github.melhzy/pubmed-stream. Search PubMed and PMC, read full texts, map evidence and build Obsidian knowledge graphs. This page covers its PyPI package (pubmed-stream).

### Is the pubmed-stream MCP server safe to use?

pubmed-stream scores 52 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 23 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 pubmed-stream MCP server expose?

pubmed-stream exposes 9 tools: search_pmc, download, fetch_abstracts, list_articles, most_cited, and 4 more. Their descriptions and schemas cost roughly 904 tokens of context every time the server is loaded.

### Is the pubmed-stream MCP server still maintained?

pubmed-stream is still listed as active in the MCP registry. We last reached this channel on 23 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 pubmed-stream MCP server under?

pubmed-stream declares the MIT 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/pubmed-stream/
- Socket report: https://socket.dev/pypi/package/pubmed-stream
- Repository: https://github.com/melhzy/pubmed-stream
- Website: https://melhzy.github.io/pubmed-stream/
- Changelog RSS feed: https://verifymcp.io/servers/melhzy-pubmed-stream/pubmed-stream.xml
- Changelog JSON feed: https://verifymcp.io/servers/melhzy-pubmed-stream/pubmed-stream.json
- HTML version of this page: https://verifymcp.io/servers/melhzy-pubmed-stream/pubmed-stream