Scholar Feed MCP Server

Preview Watch

preview_watch

Read-only

Dry-run a structured filter over recent papers to iterate on criteria like categories, novelty, or similarity before creating a watch. Returns match count and sample scores.

Instructions

Dry-run a structured filter over recent papers WITHOUT creating a watch — the tuning loop. Returns {window_days, needs_similarity, match_count, sample} so you can iterate (add a category, raise min_novelty, switch the collection relation) before saving with create_watch. Structured watches rank by 'rising' (forecasted breakout impact) by default, and tighten with min_impact_pct for an anti-noise watch that surfaces only the breakout papers in your niche. NOTE: for a similarity filter, match_count is capped at 200 (the cosine fetch window) and so saturates at 200 on broad/hot topics — tune by the sample scores and narrow with categories/min_novelty (or a higher similar floor) rather than relying on match_count alone. Read-only. Requires SF_API_KEY.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`criteria`	Yes	The structured filter to test.
`recency_days`	No	Window in days (default 7; the 'cites' relation uses 30).

Output Schema

TableJSON Schema

Name	Required	Description
`window_days`	No
`needs_similarity`	No
`match_count`	No
`sample`	No	A sample of matching papers.
`ok`	No
`message`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields changedv3.8.0Jun 9, 2026

addedInput schema / properties / criteria / properties / min_impact_pct

Added value: +{
+  "description": "Momentum floor: only surface papers in the top of forecasted citation impact within their field (e.g. 80 means roughly the top 20 percent). Only recently-scored papers have an impact percentile, so this also implies recent papers only — exactly right for a what-is-rising-now watch.",
+  "maximum": 100,
+  "minimum": 0,
+  "type": "integer"
+}

addedInput schema / properties / criteria / properties / rank

Added value: +{
+  "description": "How to order matches. 'rising' (default) ranks by forecasted breakout impact first (the impact_pct momentum model), falling back to novelty when a paper is not impact-scored yet; 'novelty' ranks most-novel first; 'recent' ranks newest first; 'relevance' ranks by closeness to a similar target (needs a similar target, else behaves as rising). For a creator or stay-current watch, leave it as rising.",
+  "enum": [
+    "rising",
+    "novelty",
+    "recent",
+    "relevance"
+  ],
+  "type": "string"
+}

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "$schema": "http://json-schema.org/draft-07/schema#",
+  "additionalProperties": false,
+  "properties": {
+    "match_count": {
+      "type": "number"
+    },
+    "message": {
+      "type": "string"
+    },
+    "needs_similarity": {
+      "type": "boolean"
+    },
+    "ok": {
+      "type": "boolean"
+    },
+    "sample": {
+      "description": "A sample of matching papers.",
+      "items": {
+        "additionalProperties": {},
+        "description": "A paper record. Verbose calls add extraction fields (method_name, datasets, baselines, ...).",
+        "properties": {
+          "arxiv_id": {
+            "type": "string"
+          },
+          "arxiv_url": {
+            "type": "string"
+          },
+          "authors": {
+            "items": {
+              "type": "string"
+            },
+            "type": "array"
+          },
+          "categories": {
+            "items": {
+              "type": "string"
+            },
+            "type": "array"
+          },
+          "citation_count": {
+            "type": "number"
+          },
+          "github_stars": {
+            "anyOf": [
+              {
+                "type": "number"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "github_url": {
+            "anyOf": [
+              {
+                "type": "string"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "has_code": {
+            "type": "boolean"
+          },
+          "impact_pct": {
+            "anyOf": [
+              {
+                "type": "number"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "impact_tier": {
+            "anyOf": [
+              {
+                "type": "string"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "institution_tags": {
+            "items": {
+              "type": "string"
+            },
+            "type": "array"
+          },
+          "llm_novelty_score": {
+            "anyOf": [
+              {
+                "type": "number"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "llm_significance": {
+            "anyOf": [
+              {
+                "type": "string"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "llm_summary": {
+            "anyOf": [
+              {
+                "type": "string"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "pdf_url": {
+            "type": "string"
+          },
+          "primary_category": {
+            "type": "string"
+          },
+          "published_date": {
+            "type": "string"
+          },
+          "rank_score": {
+            "type": "number"
+          },
+          "similarity": {
+            "type": "number"
+          },
+          "title": {
+            "type": "string"
+          },
+          "venue_name": {
+            "anyOf": [
+              {
+                "type": "string"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "year": {
+            "type": "number"
+          }
+        },
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "window_days": {
+      "type": "number"
+    }
+  },
+  "type": "object"
+}

Addedv3.7.0Jun 4, 2026

TDQS

A4.8/5.0

Behavior5/5

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

Annotations already declare readOnlyHint and destructiveHint. The description adds crucial context: match_count saturation at 200, return fields, default ranking, impact model, and read-only behavior. No contradictions.

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?

The description is detailed and front-loaded with the core purpose. Though slightly lengthy, it is well-organized and every sentence adds important context, making it effective for agent comprehension.

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?

Given the nested parameter, output schema exists, and complexity of ranking options, the description is fully complete. It covers limitations, ranking behavior, ties to create_watch, and how to interpret results, leaving no gaps.

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

Parameters4/5

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

Schema coverage is 100%, so baseline is 3. The description adds value by explaining the criteria object's role, default recency_days, and the relation field's note about collections and similar predicate, going beyond schema definitions.

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?

The description clearly states the tool's purpose: dry-run a structured filter without creating a watch, positioning it as part of a tuning loop. It differentiates from sibling create_watch by emphasizing preview and iteration.

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?

The description explicitly explains when to use: iterate before saving with create_watch. It provides guidance on using sample scores to tune, avoiding reliance on match_count, and notes read-only and API key requirement.

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