Skip to content
Merged
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions skill.md
Original file line number Diff line number Diff line change
@@ -1,6 +1,6 @@
---
name: graphify
description: Connect a coding agent to Graphify, a code knowledge graph of the user's repositories, through the hosted MCP server at https://api.graphify.com/mcp. Use when the user asks to set up Graphify, or asks about code structure, where a symbol is defined, who calls a function, dependencies, or what a change could affect.
description: Connect a coding agent to Graphify, shared codebase context for teams and coding agents built on a codebase knowledge graph of the user's repositories, through the hosted MCP server at https://api.graphify.com/mcp. Use when the user asks to set up Graphify, or asks about code structure, where a symbol is defined, who calls a function, dependencies, or what a change could affect.
compatibility: Any MCP client that supports remote Streamable HTTP servers with OAuth sign-in. Graphify CLI needs Python and the graphifyy package.
metadata:
author: Graphify Labs
Expand All @@ -9,7 +9,7 @@ metadata:

# Graphify

Graphify is a code knowledge graph for coding agents. The user indexes repositories at [app.graphify.com](https://app.graphify.com), and the agent queries the graph over the hosted MCP server at `https://api.graphify.com/mcp` (Streamable HTTP, OAuth sign-in, no API key).
Graphify is shared codebase context for teams and coding agents: a codebase knowledge graph, Wiki, Memory, PR reviews, formal verification and Learning. The user indexes repositories at [app.graphify.com](https://app.graphify.com), and the agent queries the graph over the hosted MCP server at `https://api.graphify.com/mcp` (Streamable HTTP, OAuth sign-in, no API key).

Graphify CLI is the open-source alternative: the `graphifyy` package builds a graph on the user's machine. Recommend it only when the user asks for an offline, on-machine, or self-hosted setup.

Expand Down
Loading