Add resolve_entities, crawl, dql, and dql_ontology tools

Ports four capabilities from diffbot-skills to the MCP server:

- resolve_entities: NLP entity recognition and Knowledge Graph resolution,
  compacted to name, types, confidence, salience, sentiment, and id
- crawl: the Crawlbot job lifecycle (start, status, results, list, delete),
  since a crawl runs asynchronously and cannot block a single tool call
- dql: Knowledge Graph queries, read through the csv export with a per-type
  column spec because one entity record is ~75kb of json, plus a separate
  facet path and hits_only for probing a query's selectivity
- dql_ontology: types, fields, taxonomies, and enums, cached in process

The dql description carries the query syntax and a field cheatsheet for the
four main entity types, every path verified against the live graph, because
field names rarely match the name a caller would guess.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>

Author: jeromechoo

README.md

@@ -15,6 +15,18 @@ Diffbot is a small research company building AI that structure the web. Our prod
 #### 🪄 enhance
 **Web lookup tool for organizations and people.** Unlike web search, `enhance` will return structured data from the Diffbot Knowledge Graph on an organization or person (by name, url, or other acceptable input). Helpful for verifying facts, market research, or sales intelligence workflows.
 
+#### 🧠 resolve_entities
+**Recognize and resolve entities in text.** Uses Diffbot NLP to recognize organizations, people, places, addresses, and other proper nouns in text. Entities are resolved to entity IDs in the Diffbot Knowledge Graph from which more context can be retrieved using `dql`. Keeps hallucinations in check and gives AI the context it needs to navigate deep research.
+
+#### 🕷️ crawl
+**Find all links on a web page (the seed) and extracts them all.** A classic web crawl, with a ontological web extraction bonus. Use crawl to archive documentation, take snapshots of web projects, or site mapping. 
+
+#### 🎯 dql
+**Queries Diffbot Knowledge Graph for organization, person, article, place, and product entities.** Diffbot Knowledge Graph contains a Wikipedian scale linked graph database of organizations, people, (news) articles, places, and products. Diffbot MCP converts your prompt into structured queries (`dql`) and return structured records for post-analysis.
+
+#### 🧭 dql_ontology
+**Helper utility for accurate dql ontology navigation.** Holds the keys to Diffbot's entire ontology and taxonomy reference. Used by Diffbot MCP to craft accurate `dql` queries. Humans don't need to touch this, but feel free to satisfy your curiosity.
+
 ## Authentication
 A free Diffbot token is required for tool use. [Get one here.](https://app.diffbot.com/get-started)