نسخههای متأثر
بازهها نیاز به بررسی دارند.
- نسخههای متأثر
- < 0.30.1
- نسخهٔ اصلاحشده
- 0.30.1
- نسخههای متأثر
- <0.30.1
- نسخهٔ اصلاحشده
- 0.30.1
بهرهبرداری
شرح آسیبپذیری
Summary
A containerized MCP server running with the default network permission profile (insecure_allow_all: true) can reach host-local services via host.docker.internal. This includes the ToolHive API itself, other ToolHive-managed MCP server proxies, and any other service listening on the host's localhost. Combined with the unauthenticated ToolHive API and MCP proxy endpoints, this enables a compromised or malicious MCP server to perform lateral movement without any container escape.
Severity
High — This bypasses the container isolation model that is ToolHive's core security value proposition.
Reproduction
All tests performed from inside the filesystem MCP container (docker.io/mcp/filesystem:latest), started with default settings via thv run filesystem -- /tmp.
1. Container can reach the ToolHive control plane MCP endpoint
$ docker exec <container_id> wget -qO- \
--header="Content-Type: application/json" \
--header="Accept: application/json" \
--post-data='{"jsonrpc":"2.0","method":"initialize","params":{"protocolVersion":"2025-03-26","capabilities":{},"clientInfo":{"name":"evil-mcp","version":"1.0"}},"id":1}' \
http://host.docker.internal:50444/mcp
Result: Full MCP handshake succeeds:
{"jsonrpc":"2.0","id":1,"result":{"protocolVersion":"2025-03-26","capabilities":{"logging":{},"tools":{}},"serverInfo":{"name":"toolhive-mcp","version":"v0.9.3"}}}
2. Container can connect to another MCP server's proxy and call its tools
$ docker exec <container_id> wget -qO- \
--header="Content-Type: application/json" \
--header="Accept: application/json" \
--post-data='{"jsonrpc":"2.0","method":"tools/list","params":{},"id":2}' \
http://host.docker.internal:64965/mcp
Result: Returns the full tool list of the target MCP server (read_file, write_file, edit_file, move_file, etc.), and tools can be called:
{"jsonrpc":"2.0","id":3,"result":{"content":[{"text":"Allowed directories:\n/tmp","type":"text"}]}}
3. Container can reach other host services
# Kubernetes API
$ docker exec <container_id> wget -qO- --no-check-certificate https://host.docker.internal:6443/version
{"major":"1","minor":"34","gitVersion":"v1.34.1"...}
# Ollama LLM API
$ docker exec <container_id> wget -qO- http://host.docker.internal:11434/api/tags
{"models":[{"name":"kimi-k2:1t-cloud"...}]}
Attack Scenarios
Scenario 1: Malicious MCP server pivots to privileged native MCP tools
Many users run native (non-containerized) MCP servers like Desktop Commander, terminal servers, or custom tools that have execute_command, write_file, or shell capabilities with full host access. These typically listen on localhost ports. A malicious containerized MCP server can:
Port-scan
host.docker.internalto discover listening servicesAttempt MCP handshakes on discovered ports
Call privileged tools (e.g.,
execute_command("rm -rf /")orwrite_file("/etc/crontab", "..."))
This achieves full host compromise without any container escape vulnerability.
Scenario 2: Compromised MCP server manipulates ToolHive itself
Via the unauthenticated ToolHive MCP endpoint on port 50444, a compromised container could potentially:
List and stop other running MCP servers (denial of service)
Start new MCP servers with attacker-controlled images
Modify configurations
Scenario 3: Data exfiltration via cross-MCP-server access
A low-privilege MCP server (e.g., sequentialthinking with no file mounts) could reach the filesystem server's proxy and call read_file to access files it was never authorized to see.
Scenario 4: LLM model theft / abuse
As demonstrated, the container can reach Ollama's API and could enumerate models, run inference, or exfiltrate model weights from self-hosted LLMs.
Root Causes
insecure_allow_all: trueas default — permits outbound connections to any destination includinghost.docker.internalNo authentication on ToolHive API / MCP proxies — any client that can reach the port can interact fully
Docker's
host.docker.internalDNS — resolves to the host machine, bypassing localhost-only binding assumptions
Suggested Mitigations
Short-term
Block
host.docker.internaland172.17.0.1(Docker gateway) in container networking by default, even wheninsecure_allow_allis enabled. These should require explicit opt-in.Add authentication to MCP proxy endpoints — even a shared secret or token per session would prevent cross-container lateral movement.
Medium-term
Network policy per container — ToolHive already has the
permission_profileinfrastructure. Add support for explicit allow-lists rather than just the binary none/all choice.Isolate container networks — run each MCP server in its own Docker network with no access to the Docker bridge gateway.
Long-term
Mutual TLS or token-based auth between ToolHive proxy and containers, so even if network access exists, unauthorized MCP calls are rejected.
Audit logging — log all MCP tool calls with source identification so lateral movement attempts are visible.
Environment
ToolHive v0.9.3 (macOS desktop app, Docker runtime)
Docker Desktop for Mac (host.docker.internal enabled by default)
Tested with
docker.io/mcp/filesystem:latest
پیوندها
- https://github.com/advisories/GHSA-qg2g-g9w3-m5h8
- https://github.com/stacklok/toolhive
- https://github.com/stacklok/toolhive-studio/commit/968182d7f3ee1e55123369e66ad88f82128119b0
- https://github.com/stacklok/toolhive-studio/pull/2469
- https://github.com/stacklok/toolhive-studio/releases/tag/v0.38.0
- https://github.com/stacklok/toolhive/commit/d8f40cb1599b8bf66657f2dfff15bfbfc236e712
- https://github.com/stacklok/toolhive/pull/5583
- https://github.com/stacklok/toolhive/releases/tag/v0.30.1
- https://github.com/stacklok/toolhive/security/advisories/GHSA-qg2g-g9w3-m5h8
گزارشدهندگان
- xxradar
- ChrisJBurns
- JAORMX
- jhrozek
- kantord
- eleftherias

