What your agent can do with Graphify

When your coding agent connects to the hosted MCP server, it gets a set of Graphify tools. This page maps each job you might want done to the tool that does it, with a prompt you can paste. You don’t have to name tools in your prompts. Naming them makes it easier to check that the agent used the graph.

​

At a glance

​

Find code

graphify_find matches symbol names, so use a fragment, not a question. graphify_rank_files takes a plain-language question and returns files, not code. search and fetch work as a pair: search returns results with ids, and fetch reads the code behind one id.

​

Understand how something works

query_graph answers a question with the relevant definitions in full. graphify_node returns one symbol’s code plus its immediate neighbors. graphify_expand turns ids from another tool’s results into full code, and graphify_render_subgraph returns a small graph you can draw.

​

Follow calls and dependencies

graphify_callers and graphify_callees list direct calls. graphify_trace returns directed call paths between two symbols, and shortest_path returns the most confident connection between them. graphify_references finds uses that aren’t calls, such as reads and mentions. graphify_imports_exports and graphify_file_neighbors work at the file level.

​

Change code safely

graphify_impact lists the code directly connected to a symbol. It’s a first pass, not every indirect dependency. impact_and_risk ranks the riskiest files by combining that with linked test coverage. graphify_tests_for lists tests linked through the graph. All three read the graph. They don’t run tests or prove that a change is safe.

​

Use what your team remembers

memories_about returns what’s remembered about one file or symbol. recall searches memory with a question. remember saves one fact. Have your agent ask you before it saves anything. Saved facts wait for review before they’re published. See Memory.

​

Search your documents

If your workspace has Google Drive folders connected, they show up in list_repositories next to your code, and the same tools search them. See Connect Google Drive.

​

Pick the repository and workspace

Most tools take a repository_id, either an id or a name like acme/web-app. graph_stats shows whether a repository is indexed and when. set_workspace switches the workspace for the current session. Your agent can also start a task handed off from a repository page with run_repository_starter_task.

​

What the tools don’t do

• They don’t edit your code or run your tests. Your agent does that with its own tools.
• They answer from the last index of your default branch. Code that isn’t merged or indexed yet isn’t in the results.
• There’s no tool to read pull request reviews. Your agent reads reviews on GitHub. See Know when a review is ready.

​

Related