Categories › Productivity & Office › Notes, docs & knowledge bases
CompanyGraph: Written once, read by both
Remote server: your requests and data go to mcp.companygraph.io. Claude Code: claude mcp add --transport http companygraph https://mcp.companygraph.io/mcp · Claude app: Settings → Connectors → Add custom connector.
The tools this server listed when we connected to it, in its own words.
list_types — Every type the model's schemas declare. Use first, to learn which types exist before listing or describing one. No input. Returns `types`, edescribe_schema — One type's schema: its sections as written and its declared relations as data. Use to learn what an entity of the type may hold; for the whodescribe_relations — What the schemas declare between types: references with form and cardinality, ownership, enums, joins, list kinds. Use for a diagram or audilist_rules — The vocabulary's conventions the model is held to, R0 onwards, from its core's CONVENTIONS.md. Use to resolve a number a schema or refusal cdescribe_rule — One convention of the vocabulary as written, not a company's own rule (an entity of type `rule`: list_entities, get_entity). Input: `rule`, list_checks — The checks the model's own gate runs, from the checker release this server was built with. Use to see which rules a script enforces and whicdescribe_errors — What a refused call looks like. A tool's output schema covers its answers only, so use this once, to branch on refusals or validate them. Nolist_entities — Entities with their frontmatter's short facts, in address order or newest first. Use to browse, or for what runs on a date, came last or hasget_entity — One entity as structured data: fields, sections, tables, references both ways. Use to reason over one; for its page as written use fetch. Inlist_references — The model's edges, filtered and paged. Use to inspect one entity's relations or one kind of reference without taking whole entities. Optionafind_evidence — Every edge into one skill, grouped by the type of the page that drew it. Use to check a claimed skill against its evidence. Input: `skill`, search — Find entities by words, substring or exact name. `match: "words"` needs every query word's stem in name, tagline, fields, sections or cells;fetch — One entity's page as written. Use to quote or display the source; for structured fields and references use get_entity. Input: `id` or addresdiagram — A picture of the model as Mermaid; edge data: list_references. Input: `shape`; `id`, `domain`, `type` or `unit` narrow it. aggregate, flow, Not tested by KitScout yet. When our harness runs it, pros, cons and the tasks we tried appear here, with the date and evidence.