Google Knowledge Panel MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| GOOGLE_KG_API_KEY | No | Optional Google Knowledge Graph Search API key. Without it the server runs on Wikidata only. Get a free key from Google Cloud Console by enabling the Knowledge Graph Search API. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| find_entitiesA | Find all Knowledge Graph entities associated with a name (the entities behind Google's knowledge panels). Returns each match's Knowledge Graph ID, type, description, and Google's result score, highest first. Google data needs GOOGLE_KG_API_KEY; without it, results come from Wikidata only. |
| analyze_entity_prominenceA | Analyze the entities matched for a name and determine which has the strongest Knowledge Graph presence. Ranks them on a transparent 0-100 prominence score combining Google's result score, knowledge panel completeness, Wikipedia coverage, Wikidata depth, and linked official profiles, with a plain-English reason for each. Google data needs GOOGLE_KG_API_KEY; without it, results come from Wikidata only. |
| compare_entitiesA | Compare 2-5 entities side by side: types, descriptions, prominence and readiness scores, what each is missing, key facts and connections, and official profiles. Use it for same-name entities (pass their IDs from find_entities) or for competitors (pass names like "hubspot" and "salesforce"). Google data needs GOOGLE_KG_API_KEY; without it, results come from Wikidata only. |
| get_entityA | Full profile of one entity: description, detailed description, image, official site, Wikipedia/Wikidata links, facts, real-world connections (founders, CEO, HQ, products, parent company...), official social profiles, an entity-readiness checklist, and ready-to-paste JSON-LD schema. Pass an id for a specific entity, or a query to profile the top match. Google data needs GOOGLE_KG_API_KEY; without it, results come from Wikidata only. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 4 tools
Tools are mostly distinct: find_entities for discovery, analyze_entity_prominence for ranking, compare_entities for side-by-side comparison, and get_entity for full profiles. However, find_entities and analyze_entity_prominence both take a name and return entities, which could cause slight confusion if an agent just wants entity matches without prominence scoring.
All names use snake_case and follow a verb_noun pattern (find_entities, analyze_entity_prominence, compare_entities, get_entity). The only minor deviation is analyze_entity_prominence, which adds a qualifier to the noun, but it remains predictable and readable.
Four tools is well-scoped for a focused read-only domain; each tool has a clear purpose and no tool feels redundant. It covers discovery, analysis, comparison, and detail without bloat.
The set covers the main lifecycle: finding entities, assessing prominence, comparing, and retrieving full profiles with readiness checklists. Minor gaps exist, such as searching by entity type or domain, but these are not critical for the stated purpose.