Is Anki MCP Server safe?
- Node.js shell/command execution
- Dangerous MCP tool capability
- Node.js filesystem read
What to do: Nothing here argues against installing it. Grant the capabilities it lists only if you expect the tool to need them.
Anki MCP Server is an MCP server analyzed by SkillTotal's deterministic static scanner. The scan found no malicious indicators. It can: delegated authentication, filesystem read, filesystem write, install time execution, mcp tools detected, network egress and shell execution — capabilities are what the code can do, not a verdict on intent. Risk score 0/100 (low).
@ankimcp/
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 Anki 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 (8)
An MCP tool exposes a powerful capability (files, shell, network, browser, or credentials).
(0, mcp_nest_1.Tool)({
name: "guiDeckBrowser",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 can run operating-system commands or spawn processes.
const child_process_1 = require("child_process");this.process = (0, child_process_1.spawn)("ngrok", ["http", "--host-header=rewrite", port.toString()], {const check = (0, child_process_1.spawn)(command, ["ngrok"], {const child_process_1 = require("child_process");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.
return JSON.parse((0, fs_1.readFileSync)((0, path_1.join)(__dirname, "../../package.json"), "utf-8"));
const markdown = fs.readFileSync(markdownPath, "utf-8");
const content = await (0, promises_1.readFile)(CredentialsService.CREDENTIALS_FILE, {return JSON.parse((0, fs_1.readFileSync)((0, path_1.join)(__dirname, "../package.json"), "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 (0, promises_1.writeFile)(CredentialsService.CREDENTIALS_FILE, content, {await (0, promises_1.unlink)(CredentialsService.CREDENTIALS_FILE);
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.
package.json has a 'prepare' script (runs on git/local installs and before publishing).
"prepare": "husky"
Why it matters: Usually a build step, but confirm it doesn't fetch or run remote code.
Fix: Usually a legitimate build step; confirm it only builds and does not fetch or execute remote code.
The component makes outbound network requests.
const dns = __importStar(require("node:dns"));resolved = await dns.promises.lookup(hostnameForLookup, { all: true });const http_1 = __importDefault(require("http"));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 OAuth 2.0 / OpenID Connect delegated-authentication flow was detected (authorization-code / refresh-token / token-exchange grant, an OIDC authorize/discovery endpoint or id_token, or a delegation library). Tools authenticate with the end user's delegated, scoped credentials rather than a long-lived embedded service credential.
grant_type: "refresh_token",
Fix: Delegated auth is a lower-blast-radius execution context than an embedded static credential. Confirm the requested scopes are minimal and that tokens are never logged or forwarded off-host.
An MCP tool surface (manifest or tool definitions) was found.
(0, mcp_nest_1.Tool)({(0, mcp_nest_1.Tool)({(0, mcp_nest_1.Tool)({(0, mcp_nest_1.Tool)({(0, mcp_nest_1.Tool)({(0, mcp_nest_1.Tool)({(0, mcp_nest_1.Tool)({(0, mcp_nest_1.Tool)({(0, mcp_nest_1.Tool)({(0, mcp_nest_1.Tool)({(0, mcp_nest_1.Tool)({(0, mcp_nest_1.Tool)({(0, mcp_nest_1.Tool)({(0, mcp_nest_1.Tool)({(0, mcp_nest_1.Tool)({(0, mcp_nest_1.Tool)({(0, mcp_nest_1.Tool)({(0, mcp_nest_1.Tool)({(0, mcp_nest_1.Tool)({(0, mcp_nest_1.Tool)({(0, mcp_nest_1.Tool)({(0, mcp_nest_1.Tool)({(0, mcp_nest_1.Tool)({(0, mcp_nest_1.Tool)({(0, mcp_nest_1.Tool)({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 Anki MCP Server.
Maintain Anki 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 →