Google Knowledge Graph MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| GOOGLE_KNOWLEDGE_GRAPH_API_KEY | Yes | Your Google Knowledge Graph API key |
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 | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| search_knowledge_graphB | Search Google Knowledge Graph for entities by name or topic. Returns structured information about real-world entities like people, places, organizations, and concepts from Google's public knowledge base. |
| lookup_knowledge_graph_entitiesA | Look up specific Knowledge Graph entities by their Machine IDs (MIDs). Use this when you already know the entity IDs from a previous search. MIDs look like /m/0dl567 or /g/11b6vwtjpg. |
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 2 tools
The two tools have clearly distinct purposes: one searches by name/topic, the other retrieves by specific MID. There is no overlap in functionality, and an agent can easily choose the right tool based on whether it has an ID or a query.
Both tools follow a verb + 'knowledge_graph' pattern, with 'search_knowledge_graph' and 'lookup_knowledge_graph_entities'. The second includes an extra noun ('entities'), but the shared prefix and consistent style make them predictable and readable.
With only two tools, the server feels minimal but functional for its stated purpose of querying the Knowledge Graph. It falls into the borderline range where the count is thin but not unreasonable for a focused utility.
The two core operations for a knowledge graph API—search and lookup by ID—are covered. Missing features like batch lookup or relation traversal are minor gaps that can be worked around with repeated calls.