Is Hypertool MCP server safe?
- Node.js shell/command execution
- Node.js filesystem read
- Node.js filesystem write/delete
@toolprint/hypertool-mcp 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, filesystem write, mcp tools detected and shell execution — capabilities are what the code can do, not a verdict on intent. Risk score 0/100 (low).
@toolprint/hypertool-mcp 0.0.45
Automated static-analysis result. It can contain false positives and false negatives, and is not a claim about the intent of Hypertool 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)
The component can run operating-system commands or spawn processes.
import { execSync } from "child_process";execSync("pbcopy", { input: text });execSync("clip", { input: text });execSync("xclip -selection clipboard", { input: text });execSync("xsel --clipboard --input", { input: text });import { execSync } from "child_process";execSync("pbcopy", { input: text });execSync("clip", { input: text });execSync("xclip -selection clipboard", { input: text });execSync("xsel --clipboard --input", { input: text });import { spawnSync } from "child_process";spawnSync("pbcopy", { input: rawCommand });Why it matters: Powerful and often legitimate — confirm the commands aren't built from untrusted input.
Fix: Confirm the command and its arguments are fully controlled and not derived from untrusted input; prefer execFile with an argument array.
The component reads files from disk.
const configContent = await fs.readFile(mcpConfigPath, "utf-8");
const configContent = await fs.readFile(envCheck.configPath, "utf-8");
const content = await fs.readFile(configPath, "utf-8");
const content = await fs.readFile(claudeConfigPath, "utf-8");
const content = await fs.readFile(cursorConfigPath, "utf-8");
const content = await fs.readFile(claudeCodePath, "utf-8");
const content = await fs.readFile(app.configPath, "utf-8");
const content = await fs.readFile(configPath, "utf-8");
const content = await fs.readFile(mainConfigPath, "utf-8");
const content = await fs.readFile(app.configPath, "utf-8");
const content = await fs.readFile(configPath, "utf-8");
const content = await fs.readFile(mainConfigPath, "utf-8");
const content = await fs.readFile(mainConfigPath, "utf-8");
const content = await this.fs.readFile(this.registryPath, "utf-8");
const content = await this.fs.readFile(srcPath);
const content = await this.fs.readFile(projectConfigPath, "utf-8");
const content = await this.fs.readFile(configPath, "utf-8");
const yamlContent = await this.fs.readFile(metadataPath, "utf-8");
const yamlContent = await this.fs.readFile(metadataPath, "utf-8");
const yamlContent = await this.fs.readFile(metadataPath, "utf-8");
const yamlContent = await this.fs.readFile(metadataPath, "utf-8");
const metadataContent = await this.fs.readFile(metadataPath, "utf-8");
const content = await this.fs.readFile(backupFile, "utf-8");
const content = await this.fs.readFile(path, "utf-8");
const serversContent = await this.fs.readFile(serversPath, "utf-8");
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 writes or deletes files on disk.
await fs.writeFile(envCheck.configPath, JSON.stringify(config, null, 2));
await fs.writeFile(globalConfigPath, JSON.stringify(exampleConfig, null, 2), "utf-8");
await fs.writeFile(mainConfigPath, JSON.stringify(mainConfig, null, 2), "utf-8");
await fs.writeFile(configPath, JSON.stringify(config, null, 2));
await fs.writeFile(configPath, JSON.stringify(appConfig, null, 2));
await fs.writeFile(mainConfigPath, JSON.stringify(mainConfig, null, 2));
await fs.writeFile(mainConfigPath, JSON.stringify(mainConfig, null, 2), "utf-8");
await this.fs.writeFile(this.registryPath, JSON.stringify(this.registry, null, 2), "utf-8");
await this.fs.writeFile(destPath, content);
await this.fs.writeFile(metadataPath, yaml.stringify(metadata), "utf-8");
await this.fs.rm(tempDir, { recursive: true, force: true });await this.fs.writeFile(metadataFilePath, yaml.stringify(metadata), "utf-8");
await this.fs.writeFile(join(appDir, basename(projectConfigPath)), content, "utf-8");
await this.fs.writeFile(join(appDir, filename), content, "utf-8");
await this.fs.rm(tempDir, { recursive: true, force: true });await this.fs.rm(backupPath, { recursive: true, force: true });await this.fs.unlink(backupPath);
await this.fs.unlink(metadataPath);
await this.fs.writeFile(targetPath, content, "utf-8");
await this.fs.writeFile(serversPath, JSON.stringify(servers, null, 2), "utf-8");
await this.fs.writeFile(groupsPath, JSON.stringify(groups, null, 2), "utf-8");
await this.fs.writeFile(sourcesPath, JSON.stringify(sources, null, 2), "utf-8");
await fs.writeFile(options.output, jsonOutput, "utf-8");
await fs.writeFile(filename, content, "utf-8");
await this.fs.writeFile(configPath, JSON.stringify(config, null, 2), "utf-8");
Why it matters: Usually legitimate, but worth confirming the paths can't be controlled by untrusted input.
Fix: Confirm which files are written/deleted and that paths cannot be influenced by untrusted input.
An MCP tool surface (manifest or tool definitions) was found.
this.server = new Server({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 componentHow we determine this: deterministic static analysis (regex + AST), evidence-anchored, no code execution. Methodology →