Graforest MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| HOST | No | HTTP server bind address | 0.0.0.0 |
| PORT | No | HTTP server port | 8000 |
| TRANSPORT | No | Transport mode: stdio or http | stdio |
| GRAFOREST_API_KEY | Yes | Your Graforest API key (gf_sk_...) |
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": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| create_knowledge_projectA | Provision a new knowledge graph project. Creates a Neo4j graph database with a knowledge-optimized schema (Topics, Articles, Authors, Concepts) and deploys it to staging. May take 30-60 seconds. |
| list_knowledge_projectsB | List all graph projects. Shows project IDs, names, codes, and status. |
| delete_knowledge_projectA | Delete a graph project and ALL its data. DESTRUCTIVE — cannot be undone. |
| add_knowledge_nodesA | Bulk create entities in the knowledge graph. The LLM extracts entities from content and provides them here. Each entity needs an entity_id (kebab-case), entity_type (matching schema — e.g., 'Topic', 'Article', 'Author', 'Concept'), and properties dict matching that type's schema fields. Use get_knowledge_schema first to see available entity types and their fields. |
| add_knowledge_relationshipsA | Bulk create relationships between entities in the knowledge graph. Each relationship needs from_id, to_id (matching existing entity_ids), rel_type (matching schema — e.g., 'AUTHORED', 'COVERS', 'REFERENCES'), and optional properties. Use get_knowledge_schema first to see available relationship types. |
| search_knowledge_graphA | Full-text search across all string properties in the knowledge graph. Returns matching nodes with their types, properties, and relevance scores. |
| get_knowledge_schemaA | Get the full schema — entity types with fields, relationship types with from/to mappings. CALL THIS FIRST before adding nodes or relationships to understand what types and fields are available. |
| get_knowledge_statisticsA | Get node/relationship counts broken down by type. Useful for understanding the graph's size and composition. |
| traverse_knowledge_graphB | Walk the graph from a starting entity, following relationships up to a specified depth. Returns connected nodes and relationships. |
| list_knowledge_entitiesA | List entities of a specific type. Use get_knowledge_schema first to see available entity types. |
| get_knowledge_entityA | Get a single entity by type and ID, with all properties. |
| ingest_text_contentA | BATCH INGESTION — the fast way to populate a knowledge graph. Provide a large block of text (up to 500k chars) and the project code. This tool fetches the graph schema and returns structured extraction instructions. Then call add_knowledge_nodes and add_knowledge_relationships with the extracted data. 3-CALL WORKFLOW:
This replaces per-entity approach. Extract EVERYTHING from the text in one pass, then write it all in two bulk calls. |
| fetch_url_contentA | Scrape a URL and extract clean text content. Returns the text for the LLM to read, extract entities from, and then call add_knowledge_nodes/relationships. Also returns metadata (title, author, date). |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| ingest-content | Ingest text content into a knowledge graph using the 3-call workflow. Extracts entities and relationships from the provided text. |
| explore-graph | Explore a knowledge graph — get statistics, search for concepts, and traverse connections. |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| Getting Started Guide | Documentation: Getting Started |
| Knowledge Graph Guide | Documentation: Knowledge Graph |
TDQS
Scored across 13 tools
Each tool has a clearly distinct purpose with no overlap. For example, add_knowledge_nodes creates entities, add_knowledge_relationships creates connections, fetch_url_content scrapes web content, and traverse_knowledge_graph walks the graph—all serving unique functions. The descriptions explicitly differentiate tools like ingest_text_content (batch processing) versus per-entity methods, preventing confusion.
Tool names follow a highly consistent verb_noun pattern throughout, all using snake_case. Verbs like add, get, list, create, delete, fetch, ingest, search, and traverse are applied predictably to nouns like knowledge_nodes, knowledge_entity, or knowledge_graph. There are no deviations or mixed conventions, making the set easy to navigate.
With 13 tools, the count is well-scoped for managing a knowledge graph system, covering project lifecycle, data ingestion, entity/relationship CRUD, schema inspection, and graph traversal. Each tool earns its place by addressing specific needs like bulk operations, statistics, or search, without being excessive or insufficient for the domain.
The tool surface provides complete coverage for knowledge graph operations, including project management (create/delete/list), schema inspection, entity and relationship CRUD, batch and per-item ingestion, content fetching, statistics, search, and traversal. There are no obvious gaps; agents can perform end-to-end workflows from setup to data exploration without dead ends.