pubmed-mcp

Overview Schema Source Related Servers Discussions Admin

links

Retrieve database associations and citation tracking for PMIDs, including PMC, Gene, Nucleotide, PubMed, citing articles, and references, to support record linking and citation snowballing.

Instructions

查 PMID 的数据库关联或引文追踪。pmids 用逗号/空格分隔，去重后最多 50 个。

to: pmc（默认）/ gene / nucleotide / pubmed / citedin（施引）/ refs（参考文献），大小写不敏感。每行列直接关联号；方括号是其它关联计数。citedin/refs 供滚雪球追踪（0 条仅限 PubMed 已录入关系，不等于无引文）。 to=pubmed 是相关文献，含自身；to=pmc 是 PMC 关联，不保证开放许可或此刻可下载。无关联、元数据不可用与存在性未知分开报告；esummary 缺失不证明 PMID 不存在。 search 已给 PMC 时无需重复查询 links。内部逐 PMID 请求以保留归属，失败明确标注。

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "pmids": "<pmids>"
    },
    "name": "links"
  }
}

Input Schema

Name	Required	Description	Default
`to`	No		pmc
`pmids`	Yes

Output Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv1.4.0Nov 12, 2026

TDQS

A4.7/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full behavioral burden and does so well: it explains dedup/max-50 handling, case-insensitive `to`, bracket counts for other links, the caveat that 0 citedin/refs only reflects PubMed-recorded relationships, that to=pubmed includes the PMID itself, and that to=pmc doesn't guarantee open license or current availability. It also notes internal per-PMID requests to preserve attribution with failures explicitly marked. Slightly short of 5 only because error/auth profile (e.g., rate limits, network failure semantics) isn't fully spelled out.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with purpose then mode semantics, and every line adds operational value. Some sentences are semicolon-dense (the no-links / metadata-unavailable / existence-unknown distinction) and could be split for faster scanning, but nothing is wasted.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a two-parameter tool with an output schema, the description covers input formatting, mode semantics, output line structure, caveats on zero results, and cross-tool routing. Little an agent needs to call it correctly is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0% and the schema has no enum for `to`, so the description must compensate — it does: it defines the comma/space separator, dedup, and 50 cap for `pmids`, and lists every meaningful `to` value with its semantics and default.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource: query PMID database links or citation tracking, with the pmids dedup/max-50 scope stated up front. It also anchors the tool against the 'search' sibling by saying links need not be re-queried when search already returned PMC.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Enumerates the `to` modes with the default (pmc) and explains which ones are for snowball citation tracking (citedin/refs). It gives an explicit when-not rule: if search already returned PMC, don't call links again.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server