diffbot-mcp

Official

by diffbot

Overview Schema Source Related Servers Discussions Admin

Python

Hybrid

Search News

search_news

Read-onlyIdempotent

Search structured news and articles in the Diffbot Knowledge Graph, filtering by mentioned entities, topic, publisher, language, country, date range, or sentiment.

Instructions

News and article structured search over the Diffbot Knowledge Graph. Prefer for highly relevant results on named entities or uncommon keywords. Filter by mentioned organization/person/brand/product, topic, publisher, language, country, date range, or sentiment. Results are chronological newest first, with no semantic reranking. Prefer over a generic web search for any news, including breaking stories. mentions is the strongest signal filter; if it returns nothing, retry the same words as text. API docs: https://www.diffbot.com/docs/dql/

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "search_news"
  }
}

Input Schema

Name	Required	Description
`size`	No	Max rows
`text`	No	Phrase in article body. Use for uncommon phrases or as a fallback to mentions
`since`	No	Earliest date, YYYY-MM-DD
`title`	No	Phrase in the headline
`topic`	No	Topic category; free text ok
`until`	No	Latest date, YYYY-MM-DD
`offset`	No	Rows to skip
`language`	No	ISO code, e.g. en
`mentions`	No	Organizations, people, brand, product or entities the article must mention (OR)
`publisher`	No	Publisher site, e.g. Reuters
`sentiment_max`	No	Document sentiment ceiling, -1..1
`sentiment_min`	No	Document sentiment floor, -1..1
`quoted_speaker`	No	Person quoted in the article
`publisher_country`	No	Publisher's country, e.g. United States
`mention_sentiment_max`	No	Sentiment ceiling toward the one mention

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Nov 9, 2026

TDQS

A4.6/5.0

Behavior4/5

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

Annotations already cover read-only, idempotent, open-world and non-destructive traits, but the description adds real behavioral context beyond them: result ordering ('chronological newest first'), absence of semantic reranking, and the mentions-first/retry-as-text strategy. It stops short of stating result caps or pagination interplay with size/offset, which keeps it off a 5.

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 and the strongest routing advice, and the fallback tip is easy to scan. The middle enumeration of filter dimensions ('organization/person/brand/product, topic, publisher, language, country, date range, sentiment') largely duplicates the schema and could be trimmed for a perfect score.

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 15-parameter tool with full schema coverage, rich annotations and an output schema, the description supplies everything the remaining prose needs to: what it searches, when to choose it, result ordering, and a recovery path when filters miss.

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 earns one more by adding operator guidance the schema lacks ('mentions is the strongest signal filter', 'use text as a fallback to mentions') rather than merely restating the filter list.

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 ('News and article structured search over the Diffbot Knowledge Graph') and immediately scopes it against alternatives ('prefer over a generic web search for any news'), so an agent can distinguish it from search_web without opening any schema.

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?

Gives explicit selection criteria ('highly relevant results on named entities or uncommon keywords'), an explicit alternative and when it wins ('prefer over a generic web search for any news, including breaking stories'), and a concrete fallback procedure when the primary filter fails ('if it returns nothing, retry the same words as text').

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

Deploy Server