Is Graphlit MCP server safe?

No malicious indicators - review capabilities before installing

Notable — review in context (capabilities are not malware):

Dangerous MCP tool capability
Node.js filesystem read
Node.js network egress

graphlit-mcp-server is an AI npm_package analyzed by SkillTotal's deterministic static scanner. The scan found no malicious indicators, though 4 risky constructs are reported for review. 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

npm_package · https://github.com/graphlit/graphlit-mcp-server

LOW

/ 100 risk score

Snapshot · scanned Sep 24, 2026 · graphlit-mcp-server@1.0.1 · engine 0.53.0 / ruleset 60

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.

Capabilities — what this component can do (not a risk score):

filesystem readmcp tools detectednetwork egress

Behavioral traits

How this component maps to the CSA agentic threat model. Descriptive — it never affects the risk score.

Tool surface

Tool Usage

Execution authority

Tool Access Control / Direct Tool Access

Filesystem reach

Tool Execution Context

Network egress

Interaction & Communication / Direct Communication

Findings (4)

HIGHDangerous MCP tool capabilityST-MCP-DANGEROUS-TOOL

An MCP tool exposes a powerful capability (files, shell, network, browser, or credentials).

src/tools.ts:4523-4524

server.tool(
    "screenshotPage",

src/tools.ts:4816-4817

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.

MEDIUMNode.js filesystem readST-FS-NODE-READ

The component reads files from disk.

src/tools.ts:4487-4487

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.

MEDIUMNode.js network egressST-NET-NODE

The component makes outbound network requests.

src/tools.ts:683-683

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.

LOWMCP tool surface detectedST-MCP-DETECTED

An MCP tool surface (manifest or tool definitions) was found.

src/index.ts:53-53

export const server = new McpServer(

src/tools.ts:43-44

server.tool(
    "configureProject",

src/tools.ts:302-303

server.tool(
    "queryProjectUsage",

src/tools.ts:418-419

server.tool(
    "askGraphlit",

src/tools.ts:458-459

server.tool(
    "promptConversation",

src/tools.ts:515-516

server.tool(
    "retrieveSources",

src/tools.ts:637-638

server.tool(
    "retrieveImages",

src/tools.ts:750-751

server.tool(
    "extractText",

src/tools.ts:816-817

server.tool(
    "createCollection",

src/tools.ts:864-865

server.tool(
    "addContentsToCollection",

src/tools.ts:907-908

server.tool(
    "removeContentsFromCollection",

src/tools.ts:954-955

server.tool(
    "deleteContent",

src/tools.ts:991-992

server.tool(
    "deleteConversation",

src/tools.ts:1028-1029

server.tool(
    "deleteCollection",

src/tools.ts:1066-1067

server.tool(
    "deleteFeed",

src/tools.ts:1104-1105

server.tool(
    "deleteFeeds",

src/tools.ts:1158-1159

server.tool(
    "deleteCollections",

src/tools.ts:1206-1207

server.tool(
    "deleteConversations",

src/tools.ts:1253-1254

server.tool(
    "deleteContents",

src/tools.ts:1315-1316

server.tool(
    "queryContents",

src/tools.ts:1424-1425

server.tool(
    "queryCollections",

src/tools.ts:1483-1484

server.tool(
    "queryFeeds",

src/tools.ts:1542-1543

server.tool(
    "queryConversations",

src/tools.ts:1610-1611

server.tool(
    "isContentDone",

src/tools.ts:1651-1652

server.tool(
    "isFeedDone",

Why it matters: Just context — review which tools it offers and their permissions.

Fix: Review the declared MCP tools and their permissions.

Check your own component

Run the same evidence-backed scan on any MCP server, agent skill, or package.

Scan your own component

How we determine this: deterministic static analysis (regex + AST), evidence-anchored, no code execution. Methodology →