pubmed-search-mcp

Overview Schema Source Related Servers Discussions Admin

build_research_chronicle

Create a persisted, versioned, evidence-backed research chronicle to track how a topic evolves, diff revisions, and inspect citations, branches, confidence, and audit coverage.

Instructions

Build a persisted, versioned, evidence-backed Research Chronicle.

A chronicle is the durable record of how a research topic evolved, and the single entry point for research-evolution work (it replaces the older one-shot timeline tools). It is stored with a monotonic revision number, so re-running it later produces revision N+1 and you can diff revisions to see exactly what changed.

The primary axis is chronological; research branches are a secondary organizing dimension. Both come from the same stored snapshot, and preserve shared provenance in output="timeline" and output="tree". Agreement between projections is not independent evidence verification.

Every entry carries:

a one-sentence claim with inline citations
supporting / contradicting / updating evidence articles
a research branch (lineage) assignment
provenance and a confidence score

The typed provenance graph links Topic → Branch → Entry → EvidenceArticle and is validated against edge invariants. The audit reports evidence coverage, identifier coverage, branch coverage, graph integrity, and chronology gaps, so you always know how complete the picture is.

Args: topic: Research topic (drug, gene, disease, intervention). Required unless pmids or a stored chronicle_id is supplied. pmids: Delimited PMIDs, a string array or JSON array string, or "last" to chronicle the previous search results instead of running a new search. max_events: Maximum timeline events to consider (topic mode). Omit to inherit the continued revision's value, else 30. min_year: Earliest publication year to include (topic mode). max_year: Latest publication year to include (topic mode). chronicle_id: Continue an existing chronicle (creates revision N+1) instead of deriving the ID from the topic. Passing it alone re-runs the stored scope, so the resulting diff shows research movement rather than a changed window. output: "summary" (default compact Markdown with the chronological spine), "json", "chronicle_map", "timeline", "tree", "graph", "evidence", "milestones", "mermaid" (horizontal time spine with lineage branches), or "narrative". "json", "chronicle_map", "timeline", "tree", "graph", "evidence", and "milestones" return JSON; the rest return Markdown.

Returns: The requested rendering plus an artifact locator when durable artifact persistence is enabled and succeeds. The artifact contains the full snapshot, projections, evidence table, milestone analysis, and audit regardless of output. Artifact failure is reported but does not roll back the already saved Chronicle revision.

Examples: build_research_chronicle(topic="remimazolam") build_research_chronicle(pmids="last", topic="My Reading List") build_research_chronicle(topic="CAR-T therapy", output="mermaid") build_research_chronicle(chronicle_id="remimazolam-9f2b1c4d")

Input Schema

TableJSON Schema

Name	Required	Default
`pmids`	No
`topic`	No
`output`	No	summary
`max_year`	No
`min_year`	No
`max_events`	No
`chronicle_id`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed7 schema fields changedv0.7.7Oct 7, 2026

changedInput schema / properties / max_events / anyOf

Previous value: -[
-  {
-    "description": "Maximum Chronicle events",
-    "maximum": 200,
-    "minimum": 1,
-    "type": "integer"
-  },
-  {
-    "type": "null"
-  }
-]New value: +[
+  {
+    "description": "Maximum Chronicle events",
+    "maximum": 200,
+    "minimum": 1,
+    "type": "integer"
+  },
+  {
+    "type": "null"
+  },
+  {
+    "description": "ASCII decimal integer; the integer branch's bounds apply after conversion.",
+    "maxLength": 32,
+    "pattern": "^[ \\t\\r\\n]*-?(?:0|[1-9][0-9]*)[ \\t\\r\\n]*$",
+    "type": "string"
+  }
+]

changedInput schema / properties / max_year / anyOf

Previous value: -[
-  {
-    "description": "Four-digit publication year",
-    "maximum": 2100,
-    "minimum": 1000,
-    "type": "integer"
-  },
-  {
-    "type": "null"
-  }
-]New value: +[
+  {
+    "description": "Four-digit publication year",
+    "maximum": 2100,
+    "minimum": 1000,
+    "type": "integer"
+  },
+  {
+    "type": "null"
+  },
+  {
+    "description": "ASCII decimal integer; the integer branch's bounds apply after conversion.",
+    "maxLength": 32,
+    "pattern": "^[ \\t\\r\\n]*-?(?:0|[1-9][0-9]*)[ \\t\\r\\n]*$",
+    "type": "string"
+  }
+]

changedInput schema / properties / min_year / anyOf

Previous value: -[
-  {
-    "description": "Four-digit publication year",
-    "maximum": 2100,
-    "minimum": 1000,
-    "type": "integer"
-  },
-  {
-    "type": "null"
-  }
-]New value: +[
+  {
+    "description": "Four-digit publication year",
+    "maximum": 2100,
+    "minimum": 1000,
+    "type": "integer"
+  },
+  {
+    "type": "null"
+  },
+  {
+    "description": "ASCII decimal integer; the integer branch's bounds apply after conversion.",
+    "maxLength": 32,
+    "pattern": "^[ \\t\\r\\n]*-?(?:0|[1-9][0-9]*)[ \\t\\r\\n]*$",
+    "type": "string"
+  }
+]

addedInput schema / properties / output / anyOf

Added value: +[
+  {
+    "default": "summary",
+    "enum": [
+      "summary",
+      "json",
+      "chronicle_map",
+      "timeline",
+      "tree",
+      "graph",
+      "evidence",
+      "milestones",
+      "mermaid",
+      "narrative"
+    ],
+    "title": "Output",
+    "type": "string"
+  },
+  {
+    "pattern": "^[ \\t\\r\\n]*(?:[sS][uU][mM][mM][aA][rR][yY]|[jJ][sS][oO][nN]|[cC][hH][rR][oO][nN][iI][cC][lL][eE]_[mM][aA][pP]|[tT][iI][mM][eE][lL][iI][nN][eE]|[tT][rR][eE][eE]|[gG][rR][aA][pP][hH]|[eE][vV][iI][dD][eE][nN][cC][eE]|[mM][iI][lL][eE][sS][tT][oO][nN][eE][sS]|[mM][eE][rR][mM][aA][iI][dD]|[nN][aA][rR][rR][aA][tT][iI][vV][eE])[ \\t\\r\\n]*$",
+    "type": "string"
+  }
+]

removedInput schema / properties / output / enum

Removed value: -[
-  "summary",
-  "json",
-  "chronicle_map",
-  "timeline",
-  "tree",
-  "graph",
-  "evidence",
-  "milestones",
-  "mermaid",
-  "narrative"
-]

removedInput schema / properties / output / type
```
Removed value: -"string"
```

changedInput schema / properties / pmids / anyOf

Previous value: -[
-  {
-    "maxLength": 10000,
-    "type": "string"
-  },
-  {
-    "type": "null"
-  }
-]New value: +[
+  {
+    "anyOf": [
+      {
+        "description": "Complete PMID(s): delimited text, JSON string array, or Markdown list; optional JSON code fence. last only where supported.",
+        "examples": [
+          "33053718,36170657",
+          "[\"33053718\",\"36170657\"]",
+          "- 33053718\n- 36170657"
+        ],
+        "format": "pubmed-pmid-batch",
+        "maxLength": 100000,
+        "minLength": 1,
+        "type": "string"
+      },
+      {
+        "items": {
+          "description": "One PMID string, or last as the sole batch item for tools supporting session reuse.",
+          "examples": [
+            "33053718"
+          ],
+          "format": "pubmed-pmid",
+          "maxLength": 512,
+          "minLength": 1,
+          "type": "string",
+          "x-pubmed-input": "pmid"
+        },
+        "maxItems": 1000,
+        "minItems": 1,
+        "type": "array"
+      }
+    ],
+    "x-pubmed-input": "pmid_batch"
+  },
+  {
+    "type": "null"
+  }
+]

Addedv0.7.2Sep 13, 2026

TDQS

A4.7/5.0

Behavior5/5

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

Annotations only declare readOnlyHint=false, idempotentHint=false, destructiveHint=false, and the description adds substantial side-effect context beyond them: the chronicle is persisted with a monotonic revision number, re-runs create revision N+1, and artifact persistence failure 'is reported but does not roll back the already saved Chronicle revision'. That is exactly the write/persistence semantics an agent needs.

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 the core purpose, then organized into description, Args, Returns, and Examples – a clean structure where each section is useful. It is longer than strictly necessary; lines like 'Agreement between projections is not independent evidence verification' and the Topic → Branch → Entry → EvidenceArticle walkthrough are informative but add bulk for an agent that mainly needs mode and output selection.

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 7-parameter, zero-required tool with no output schema, the description covers everything needed: entry conditions, parameter interactions, the artifact-plus-locator return shape, what the audit reports, and four concrete invocation examples. Nothing essential to correct invocation 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?

With schema description coverage reported at 0%, the description carries the full burden and does so thoroughly: it explains the topic/pmids/chronicle_id mutual fallbacks, the max_events inheritance rule and default of 30, min/max_year scoping to topic mode, and enumerates all ten output values, noting which return JSON vs Markdown. This meaningfully exceeds anything the schema conveys.

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 precise verb and artifact ('Build a persisted, versioned, evidence-backed Research Chronicle') and defines what a chronicle is (durable record of how a topic evolved). It explicitly positions itself against siblings, noting it 'replaces the older one-shot timeline tools' and is 'the single entry point for research-evolution work', so an agent can distinguish it from read_research_chronicle and build_citation_tree.

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

Usage Guidelines4/5

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

Gives clear context for each mode: topic mode for new searches, pmids='last' to reuse prior search results, and chronicle_id to 're-run the stored scope' as revision N+1 so the diff shows research movement. It does not explicitly state when NOT to use the tool or name read_research_chronicle as the read-only alternative, so it stops short of full when/when-not coverage.

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

Deploy Server

build_research_chronicle

Instructions

Input Schema

Schema Changelog

TDQS

Other Tools