Girder runs on your own machine — the client starts it, so there is no endpoint to ping. 144 installs a week from npm. Last commit 7 Oct 2026.
Saves AI coding-agent context by giving exact code instead of whole files, from a local graph.
We read the source, 2 d ago · rules 995398eba69f
What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.
postinstall: node install.js
const child = spawn(binary, process.argv.slice(2), {
const archive = path.join(scratch, asset);
result = subprocess.run(
Found in continuous integration, deployment or infrastructure files, or in a neighbouring package of the same monorepo. None of this is installed when you add the server: it describes how the project is built and released. We list it because a leaked key in a build pipeline is still a real problem, but it is not something this server does on your machine.
exec(compile(source, str(path), "exec"), namespace)
return dict(
os.environ, HOME=str(home), XDG_CACHE_HOME=str(home / ".cache"),
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add girder -- npx -y girder-mcp
{
"mcpServers": {
"girder": {
"command": "npx",
"args": [
"-y",
"girder-mcp"
]
}
}
}
[mcp_servers.girder]
command = "npx"
args = ["-y", "girder-mcp"]
{
"mcpServers": {
"girder": {
"command": "npx",
"args": [
"-y",
"girder-mcp"
]
}
}
}
{
"servers": {
"girder": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"girder-mcp"
]
}
}
}
Local Tree-sitter code graph: surgical edit context for AI agents instead of full-file reads.
Ranked local code-graph context for AI coding agents. Intercepts reads + greps. Apache-2.0.
Index your codebase. AI searches instead of re-reading files. 94% token savings.
Deterministic code map for AI coding agents: a tree-sitter call graph with exact file:line over MCP.
Cross-repository semantic code intelligence for AI coding agents, from a local code graph.
Save tokens while coding — your AI agent gets structured code context, not file dumps.
Local-first memory for AI coding agents. Memory + CodeGraph + Wiki in one SQLite file.
Give your coding agent the right code: graph + hybrid search, packed into a token budget. Local.
Answers built from our own checks of this server.