Pubmed

Name: Pubmed
Author: pipeworx-io

Server Details

PubMed MCP — wraps the NCBI E-utilities API (biomedical literature, free, no auth)

Glama couldn't complete the latest health check. If this server requires authentication, missing or expired test credentials may be the cause. A test profile lets Glama authenticate for health checks and discover tools; it is separate from your personal connections.

If you are the author, claim ownership, then add or update a test profile under Admin → Test Profile.

Status: Unhealthy
Uptime: 40.6% over 42 days
Last Tested: 2026-09-28 18:58
Transport: Streamable HTTP
URL
Repository: pipeworx-io/mcp-pubmed
GitHub Stars: 1
Server Listing: mcp-pubmed

TDQS

A3.8/5.0

Scored 2026-09-12 19:00 across 43 tools

Disambiguation3/5

Most tools have long, carefully differentiated descriptions, but the set contains literal duplicates: the deprecated aliases get_citations/get_full_text/get_related_articles behave identically to their pubmed_* counterparts, and ask_pipeworx / ask_pipeworx_beta / ask_pipeworx_grounded / deep_research form a cluster of overlapping 'ask' entry points. An agent can still pick correctly if it reads carefully, but the aliasing and near-duplicate routers invite misselection.

Naming Consistency3/5

Names are predominantly snake_case, but conventions are mixed: some are verb_noun (get_abstract, search_pubmed, compare_entities) while others are noun_verb (entity_profile, polymarket_edges, pipeworx_feedback), and the PubMed tools split between prefixed (pubmed_get_citations) and unprefixed (get_summary, get_abstract) forms. Readable, but not a single predictable pattern.

Tool Count2/5

43 tools is far above a well-scoped set, and the surface is wildly over-broad for a server named 'Pubmed' — it bundles Polymarket arbitrage, npm dependency scanning, AI-visibility auditing, memory, and subscriptions alongside the PubMed tools. Each tool is individually plausible, but the count and scope mismatch is severe.

Completeness3/5

The PubMed subset is reasonably complete for read-only literature work (search, summary, abstract, full text, citations, related articles, integrity, trends, evidence landscape), and the gateway extras add breadth. However, the coexistence of deprecated alias tools rather than a clean surface, plus an unclear overall domain, leaves the set feeling like an incomplete grab-bag rather than a coherent, finished API.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

1 tool updateSep 11, 2026

Changedbet_research2 fields changed

changedInput schema / examples

Previous value: -[
-  {
-    "market": "when-will-bitcoin-hit-150k"
-  },
-  {
-    "market": "https://polymarket.com/event/when-will-bitcoin-hit-150k"
-  }
-]New value: +[
+  {
+    "market": "will-kristi-noem-win-the-2028-republican-presidential-nomination"
+  },
+  {
+    "market": "https://polymarket.com/event/will-kristi-noem-win-the-2028-republican-presidential-nomination"
+  }
+]

changedInput schema / properties / market / description

Previous value: -"Polymarket slug (\"when-will-bitcoin-hit-150k\"), full URL (\"https://polymarket.com/event/...\"), or question text (\"Will Bitcoin hit $150k?\"). Dated slugs stop resolving once they settle — Polymarket de-indexes resolved markets — so prefer an undated one."New value: +"Polymarket slug (\"will-kristi-noem-win-the-2028-republican-presidential-nomination\"), full URL (\"https://polymarket.com/event/...\"), or question text (\"Will Bitcoin hit $150k?\"). Dated slugs stop resolving once they settle — Polymarket de-indexes resolved markets — so prefer an undated one."

1 tool updateSep 11, 2026

Changedpolymarket_kalshi_spread1 field changed

changedInput schema / examples

Previous value: -[
-  {
-    "topic": "fed"
-  },
-  {
-    "topic": "btc"
-  }
-]New value: +[
+  {
+    "topic": "fed"
+  },
+  {
+    "topic": "btc"
+  },
+  {
+    "topic": "bitcoin"
+  },
+  {
+    "topic": "fed rate decision"
+  }
+]

2 tool updatesSep 11, 2026

Changedbet_research2 fields changed

changedInput schema / examples

Previous value: -[
-  {
-    "market": "will-bitcoin-reach-100k-in-july-2026"
-  },
-  {
-    "market": "https://polymarket.com/event/will-bitcoin-hit-150k-by-june-30-2026"
-  }
-]New value: +[
+  {
+    "market": "when-will-bitcoin-hit-150k"
+  },
+  {
+    "market": "https://polymarket.com/event/when-will-bitcoin-hit-150k"
+  }
+]

changedInput schema / properties / market / description

Previous value: -"Polymarket slug (\"will-bitcoin-hit-150k-by-june-30-2026\"), full URL (\"https://polymarket.com/event/...\"), or question text (\"Will Bitcoin hit $150k by June 30?\")"New value: +"Polymarket slug (\"when-will-bitcoin-hit-150k\"), full URL (\"https://polymarket.com/event/...\"), or question text (\"Will Bitcoin hit $150k?\"). Dated slugs stop resolving once they settle — Polymarket de-indexes resolved markets — so prefer an undated one."

Changedpolymarket_kalshi_spread1 field changed

changedInput schema / properties / topic / description

Previous value: -"Pre-mapped: fed | btc | cpi | gdp | sp500 | recession | next_pope | next_uk_pm | next_israel_pm | 2028_president"New value: +"Subject to compare. Canonical keys: fed | btc | eth | cpi | gdp | sp500 | recession | next_pope | next_uk_pm | next_israel_pm | 2028_president — but aliases and keywords resolve too (\"bitcoin\", \"fed rate decision\", \"ethereum\", \"inflation\", \"s&p 500\", \"us recession\", \"next pope\", \"2028 election\"). Check resolution.topic_matched_by in the response: \"exact\"/\"alias\" is a curated pairing, \"phrase\"/\"token\" is a keyword guess."

1 tool updateSep 11, 2026

Changedget_summary6 fields changed

addedOutput schema / properties / articles / items / properties / author_details

Added value: +{
+  "description": "Per-author detail, index-aligned with authors[]: name, affiliations (verbatim from efetch XML), and any emails found inside them",
+  "items": {
+    "properties": {
+      "affiliations": {
+        "description": "Verbatim AffiliationInfo/Affiliation strings from efetch XML; empty if the record has none",
+        "items": {
+          "type": "string"
+        },
+        "type": "array"
+      },
+      "emails": {
+        "description": "Email addresses found inside this author's affiliation strings by plain regex; empty if none present",
+        "items": {
+          "type": "string"
+        },
+        "type": "array"
+      },
+      "name": {
+        "description": "Author name as indexed by esummary (e.g. \"Smith JA\")",
+        "type": "string"
+      }
+    },
+    "required": [
+      "name",
+      "affiliations",
+      "emails"
+    ],
+    "type": "object"
+  },
+  "type": "array"
+}

changedOutput schema / properties / articles / items / properties / authors / description

Previous value: -"Per-author name, affiliations (verbatim from efetch XML), and any emails found inside them"New value: +"Author names as plain strings, e.g. \"Smith JA\" (unchanged shape; see author_details for affiliations/emails)"

removedOutput schema / properties / articles / items / properties / authors / items / properties

Removed value: -{
-  "affiliations": {
-    "description": "Verbatim AffiliationInfo/Affiliation strings from efetch XML; empty if the record has none",
-    "items": {
-      "type": "string"
-    },
-    "type": "array"
-  },
-  "emails": {
-    "description": "Email addresses found inside this author's affiliation strings by plain regex; empty if none present",
-    "items": {
-      "type": "string"
-    },
-    "type": "array"
-  },
-  "name": {
-    "description": "Author name as indexed by esummary (e.g. \"Smith JA\")",
-    "type": "string"
-  }
-}

removedOutput schema / properties / articles / items / properties / authors / items / required
```
Removed value: -[
-  "name",
-  "affiliations",
-  "emails"
-]
```
changedOutput schema / properties / articles / items / properties / authors / items / type
```
Previous value: -"object"New value: +"string"
```

changedOutput schema / properties / articles / items / required

Previous value: -[
-  "pmid",
-  "title",
-  "authors",
-  "journal",
-  "pub_date",
-  "volume",
-  "issue",
-  "pages",
-  "pub_types",
-  "doi",
-  "url"
-]New value: +[
+  "pmid",
+  "title",
+  "authors",
+  "author_details",
+  "journal",
+  "pub_date",
+  "volume",
+  "issue",
+  "pages",
+  "pub_types",
+  "doi",
+  "url"
+]

1 tool updateSep 11, 2026

Changedget_summary4 fields changed

changedOutput schema / properties / articles / items / properties / authors / description

Previous value: -"List of author names"New value: +"Per-author name, affiliations (verbatim from efetch XML), and any emails found inside them"

addedOutput schema / properties / articles / items / properties / authors / items / properties

Added value: +{
+  "affiliations": {
+    "description": "Verbatim AffiliationInfo/Affiliation strings from efetch XML; empty if the record has none",
+    "items": {
+      "type": "string"
+    },
+    "type": "array"
+  },
+  "emails": {
+    "description": "Email addresses found inside this author's affiliation strings by plain regex; empty if none present",
+    "items": {
+      "type": "string"
+    },
+    "type": "array"
+  },
+  "name": {
+    "description": "Author name as indexed by esummary (e.g. \"Smith JA\")",
+    "type": "string"
+  }
+}

addedOutput schema / properties / articles / items / properties / authors / items / required
```
Added value: +[
+  "name",
+  "affiliations",
+  "emails"
+]
```
changedOutput schema / properties / articles / items / properties / authors / items / type
```
Previous value: -"string"New value: +"object"
```

1 tool updateSep 10, 2026

Changedget_summary4 fields changed

changedInput schema / examples

Previous value: -[
-  {
-    "ids": "33579999,34567890"
-  }
-]New value: +[
+  {
+    "ids": [
+      "33301246",
+      "32000001"
+    ]
+  },
+  {
+    "ids": "33579999,34567890"
+  }
+]

changedInput schema / properties / ids / description

Previous value: -"Comma-separated PubMed IDs (e.g., \"33579999,34567890\")"New value: +"PubMed IDs, either as an array ([\"33579999\",\"34567890\"] — what search_pubmed returns) or as a comma-separated string (\"33579999,34567890\")."

addedInput schema / properties / ids / items
```
Added value: +{
+  "type": "string"
+}
```

changedInput schema / properties / ids / type

Previous value: -"string"New value: +[
+  "string",
+  "array"
+]

Related MCP Connectors

PubMed / MEDLINE Literature Search A
com.olyport
Search biomedical literature, get article details, find related articles, and explore MeSH terms
Research & Data Biology & Medicine Search
52
Crossref A
io.github.pipeworx-io
Crossref MCP — wraps the Crossref REST API (academic papers, free, no auth)
Search Research & Data Open Data
392
Ncbi Eutils C
io.github.pipeworx-io
NCBI E-utilities MCP — federated Entrez search/fetch.
Biology & Medicine Search Research & Data
2
Nobel A
io.github.pipeworx-io
Nobel MCP — wraps the Nobel Prize API v2 (free, no auth)
Open Data Government Data Research & Data
382

Related MCP Servers

ryogena-pubmed-mcp
Research & Data Biology & Medicine
KyleVick4
A
license
A
quality
D
maintenance
Exposes NCBI PubMed as MCP tools for searching literature, fetching abstracts, exploring citation graphs, and finding author publications without requiring an API key.
Updated 5 months ago (2026-05-04 15:23 UTC)
4
MIT
pubmed-proxy-mcp
dingyifei
F
license
Not graded
quality
D
maintenance
MCP server for NCBI PubMed E-utilities with rate limiting, enabling article search, metadata retrieval, full-text access, BibTeX generation, and bibliography management.
Updated 6 months ago (2026-03-22 07:48 UTC)
-
PubMed MCP Server
Research & Data Search Biology & Medicine
ncukondo
A
license
Not graded
quality
D
maintenance
MCP server for searching PubMed scientific articles using NCBI E-utilities API. Supports query, fetch summaries, and full text retrieval with caching and rate limiting.
Updated a year ago (2025-08-05 04:16 UTC)
30 npm
ISC
PubMed MCP Server
Search Biology & Medicine Research & Data
masa061580
A
license
A
quality
D
maintenance
A local MCP server enabling PubMed, PMC, and iCite API access via stdio for tools like search, fetch, full text, and citation counts.
Updated 4 months ago (2026-05-18 11:35 UTC)
10
70 npm
2
MIT

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Server Details

TDQS

Tool Schema Changelog

Related MCP Connectors

Related MCP Servers

ryogena-pubmed-mcp

pubmed-proxy-mcp

PubMed MCP Server

PubMed MCP Server

Glama MCP Gateway

Resources