Is Graphlit MCP server safe?
- Dangerous MCP tool capability
- Node.js filesystem read
- Node.js network egress
What to do: Nothing here argues against installing it. Grant the capabilities it lists only if you expect the tool to need them.
Graphlit MCP server is an MCP server analyzed by SkillTotal's deterministic static scanner. The scan found no malicious indicators. It can: filesystem read, mcp tools detected and network egress — capabilities are what the code can do, not a verdict on intent. Risk score 0/100 (low).
graphlit-mcp-server 1.0.1
Get notified when this component changes
Change alerts aren't live yet. Leave your email and we'll let you know when they launch. We use it only for this and delete it on request.
Automated static-analysis result. It can contain false positives and false negatives, and is not a claim about the intent of Graphlit MCP server's authors. Report a false positive.
Behavioral traits
How this component maps to the CSA agentic threat model. Descriptive — it never affects the risk score.
Findings (4)
An MCP tool exposes a powerful capability (files, shell, network, browser, or credentials).
server.tool(
"screenshotPage",server.tool(
"sendWebHookNotification",Why it matters: Wired into an agent, these grant it real access to your machine — confirm each is required.
Fix: Confirm each powerful tool is required and constrained; broad MCP tools (shell/filesystem/network) grant an agent significant host access.
The component reads files from disk.
const fileData = fs.readFileSync(filePath);
Why it matters: Usually legitimate, but worth confirming it can't be steered into reading sensitive files.
Fix: Confirm which files are read and that paths cannot be influenced by untrusted input to reach sensitive locations.
The component makes outbound network requests.
const fetchResponse = await fetch(url);
Why it matters: Usually legitimate, but confirm the destinations are expected and no sensitive data leaves.
Fix: Confirm the destination hosts are expected and that no sensitive data is sent off-host.
An MCP tool surface (manifest or tool definitions) was found.
export const server = new McpServer(
const transport = new StdioServerTransport();
server.tool(
"configureProject",server.tool(
"queryProjectUsage",server.tool(
"askGraphlit",server.tool(
"promptConversation",server.tool(
"retrieveSources",server.tool(
"retrieveImages",server.tool(
"extractText",server.tool(
"createCollection",server.tool(
"addContentsToCollection",server.tool(
"removeContentsFromCollection",server.tool(
"deleteContent",server.tool(
"deleteConversation",server.tool(
"deleteCollection",server.tool(
"deleteFeed",server.tool(
"deleteFeeds",server.tool(
"deleteCollections",server.tool(
"deleteConversations",server.tool(
"deleteContents",server.tool(
"queryContents",server.tool(
"queryCollections",server.tool(
"queryFeeds",server.tool(
"queryConversations",server.tool(
"isContentDone",Why it matters: Just context — review which tools it offers and their permissions.
Fix: Review the declared MCP tools and their permissions.
How attackers abuse these capabilities
Interactive labs on the attack class behind the rules above. They show the technique, not anything found in Graphlit MCP server.
Maintain Graphlit MCP server?
The free Claude Code plugin scans each npm, PyPI or MCP package with this report's open-source engine before the install command runs. It runs on your machine and needs no account.
Check your own component
Run the same evidence-backed scan on any MCP server, agent skill, or package.
Scan your own componentHow we determine this: deterministic static analysis (regex + AST), evidence-anchored, no code execution. Methodology →