DNS rebinding in AnkiMCP lets web pages reach local MCP tools
Key facts
- Attack vector
- Network
- Privileges required
- None
- User interaction
- Passive
- Attack complexity
- Low
- Attack requirements
- Present
- Impact type
- Security bypass
- Confidentiality · integrity · availability
- High · High · None
- Fix status
- Fixed
Attack profile from CVSS 4.0 · CNA. Fix status from CNA. Impact type from CWE-346.
Summary
AnkiMCP, an Anki addon that implements an MCP server, is affected before version 0.21.0 (anki-mcp-server-addon). The addon disables DNS rebinding protection and origin checks for its default local HTTP listener, which is an origin validation error (CWE-346). An unauthenticated remote attacker needs only a victim who visits a malicious web page while Anki and the listener are running, and can then read the local collection and create or update notes and decks through the MCP tools.
Written with Claude Haiku 5.5 from the sources below · 2026-10-29
Description from the CNA
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.
Why it matters now
SSVC decision points
CISA ADP · SSVC 2.0.3
- Exploitation
- Poc
- Automatable
- No
- Technical impact
- Total
The decision (Track, Attend, Act) also depends on your mission and well-being impact; see CISA's SSVC guide.
Affected products
Remediation
Update the AnkiMCP addon (anki-mcp-server-addon) to version 0.21.0, which fixes the issue.
Written with Claude Haiku 5.5 from the sources below · 2026-10-29
- Fix · CNA anki-mcp-server-addon (ankimcp) Fixed in 0.21.0
Timeline
- 2026-10-28 Threatist record created from CVE-2026-61546
- 2026-10-29 CISA SSVC decision points changed
- 2026-10-29 Priority changed: MEDIUM → HIGH
References
Other 4
- https://github.com/ankimcp/anki-mcp-server-addon/security/advisories/GHSA-j9xx-59ph-wmr6
- 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/tree/v0.21.0
Sources
This product uses the NVD API but is not endorsed or certified by the NVD. Sources and licences