CVE-2026-61546
AnkiMCP is an Anki addon that implements an MCP server, enabling AI assistants to interact with the…
- Risk score
- 58/100
- CVSS
- 8.8 v4.0
- Published
- 28 Oct 2026
Open in the live forecast Today's forecast
What to know
- What it is
- AnkiMCP is an Anki addon that implements an MCP server, enabling AI assistants to interact with the Anki flashcard application. Prior to version 0.21.0, anki_mcp_server/mcp_server.py globally disables FastMCP DNS-rebinding protection through TransportSecuritySettings with enable_dns_rebinding_protection=False, includi…
- Affected
- See advisory
- Fix
- Upgrade the product to 0.21.0 or later.
- Exploitation
- No known exploitation
Why it is Yellow
- CVSS 8.8 high
- Remotely exploitable without logging in
References
- https://github.com/ankimcp/anki-mcp-server-addon/commit/6dcb6939b0ecc0801f45cf0d241dc946aad1654f
- https://github.com/ankimcp/anki-mcp-server-addon/commit/d5306ff42d68f1e3b82a96878eb059437e820316
- https://github.com/ankimcp/anki-mcp-server-addon/security/advisories/GHSA-j9xx-59ph-wmr6
- https://github.com/ankimcp/anki-mcp-server-addon/tree/v0.21.0
Original description
AnkiMCP is an Anki addon that implements an MCP server, enabling AI assistants to interact with the Anki flashcard application. Prior to version 0.21.0, `anki_mcp_server/mcp_server.py` globally disables FastMCP DNS-rebinding protection through `TransportSecuritySettings` with `enable_dns_rebinding_protection=False`, including for the default local Streamable HTTP listener. The defaults in `anki_mcp_server/config.py` enable `http_enabled` on `127.0.0.1:3141`, with an empty `http_path` selecting the root endpoint. No bearer token, API key, session secret, strict `Host` allowlist or strict `Origin` allowlist is enforced before `initialize`, `tools/list` and `tools/call` reach MCP dispatch. A victim who visits a malicious web page while Anki and the listener are running can have browser requests rebound to loopback, allowing the attacker to `initialize` MCP, enumerate tools, read the local collection, and perform enabled non-destructive note/deck creation or updates. The attacker needs neither LAN position nor a local process. Available operations depend on enabled tool filters; destructive tools are hidden unless `enabled_destructive_tools` is opted into, limiting deletion-level impact but not the exposed read/write operations. The reported harness confirms real MCP tool dispatch with substituted Anki bridge responses rather than demonstrating destructive changes to a real collection. Disabling protection for tunnels/proxies also disables it for the normal loopback configuration. This issue is fixed in version 0.21.0.
Last activity 28 Oct 2026. Patch Forecast updates every hour.