mcp-run-python

Impact

Critical Sandbox Escape & Server Takeover: A critical security vulnerability exists in mcp-run-python due to a lack of isolation between the Python runtime (Pyodide) and the host JavaScript environment.

The runPython and runPythonAsync functions execute Python code using Pyodide without restricting access to the JavaScript bridge. This allows any executed Python code—whether from a user or an AI model—to access the js module in Pyodide. Through this bridge, the Python code can modify the global JavaScript environment, interact with the Node.js process, and alter the behavior of the MCP server.

Specific Attack Vector: MCP Tool Shadowing Because the Python code can modify the JS runtime, an attacker can dynamically overwrite or "shadow" existing MCP tools registered on the server. For example, an attacker could replace a secure file-reading tool with a malicious version that exfiltrates data to an external server, all while the MCP server appears to be functioning normally.

Patches

No Patch Available: The mcp-run-python project is currently archived and maintainers have indicated it is unlikely to receive a fix.

Recommendation: Users are strongly advised to immediately stop using this package. If functionality is required, users must migrate to a maintained alternative that implements proper sandboxing (e.g., running Python in a Docker container or a restricted WASM environment with the JS bridge disabled).

Workarounds

There are no configuration-based workarounds. Securing the environment requires modifying the source code to disable the Pyodide-to-JS bridge or moving the execution environment to a fully isolated sandbox (e.g., a separate container).

Resources

• CVE-2026-25905
• JFrog Security Analysis: MCP Takeover

Impact

Server-Side Request Forgery (SSRF): A security vulnerability exists in the mcp-run-python tool (specifically within the Pydantic-AI integration) due to an overly permissive Deno sandbox configuration.

The tool configures the Deno runtime—which is intended to isolate the execution of untrusted Python code—with network permissions that include access to the host's loopback interface (localhost). Consequently, malicious Python code executed through the tool can bypass network isolation and send HTTP requests to internal services running on the host machine. This allows attackers to interact with local APIs, databases, or cloud metadata services that should not be accessible from the sandbox.

Patches

No Patch Available: The mcp-run-python project is currently archived and maintainers have indicated it is unlikely to receive a fix.

Recommendation: Users are strongly advised to immediately stop using this package. If functionality is required, users must migrate to an alternative execution environment that enforces strict network isolation (e.g., blocking all outbound traffic or explicitly denying access to 127.0.0.1/::1).

Workarounds

There are no configuration-based workarounds provided by the package itself. Remediation requires modifying the source code to restrict the Deno permissions (specifically removing or narrowing the --allow-net flag) or moving the execution to a container with no network access.

Resources

• CVE-2026-25904
• JFrog Security Analysis: Deno SSRF

Impact

Critical Sandbox Escape & Server Takeover: A critical security vulnerability exists in mcp-run-python due to a lack of isolation between the Python runtime (Pyodide) and the host JavaScript environment.

The runPython and runPythonAsync functions execute Python code using Pyodide without restricting access to the JavaScript bridge. This allows any executed Python code—whether from a user or an AI model—to access the js module in Pyodide. Through this bridge, the Python code can modify the global JavaScript environment, interact with the Node.js process, and alter the behavior of the MCP server.

Specific Attack Vector: MCP Tool Shadowing Because the Python code can modify the JS runtime, an attacker can dynamically overwrite or "shadow" existing MCP tools registered on the server. For example, an attacker could replace a secure file-reading tool with a malicious version that exfiltrates data to an external server, all while the MCP server appears to be functioning normally.

Patches

No Patch Available: The mcp-run-python project is currently archived and maintainers have indicated it is unlikely to receive a fix.

Recommendation: Users are strongly advised to immediately stop using this package. If functionality is required, users must migrate to a maintained alternative that implements proper sandboxing (e.g., running Python in a Docker container or a restricted WASM environment with the JS bridge disabled).

Workarounds

There are no configuration-based workarounds. Securing the environment requires modifying the source code to disable the Pyodide-to-JS bridge or moving the execution environment to a fully isolated sandbox (e.g., a separate container).

Resources

• CVE-2026-25905
• JFrog Security Analysis: MCP Takeover

Impact

Server-Side Request Forgery (SSRF): A security vulnerability exists in the mcp-run-python tool (specifically within the Pydantic-AI integration) due to an overly permissive Deno sandbox configuration.

The tool configures the Deno runtime—which is intended to isolate the execution of untrusted Python code—with network permissions that include access to the host's loopback interface (localhost). Consequently, malicious Python code executed through the tool can bypass network isolation and send HTTP requests to internal services running on the host machine. This allows attackers to interact with local APIs, databases, or cloud metadata services that should not be accessible from the sandbox.

Patches

No Patch Available: The mcp-run-python project is currently archived and maintainers have indicated it is unlikely to receive a fix.

Recommendation: Users are strongly advised to immediately stop using this package. If functionality is required, users must migrate to an alternative execution environment that enforces strict network isolation (e.g., blocking all outbound traffic or explicitly denying access to 127.0.0.1/::1).

Workarounds

There are no configuration-based workarounds provided by the package itself. Remediation requires modifying the source code to restrict the Deno permissions (specifically removing or narrowing the --allow-net flag) or moving the execution to a container with no network access.

Resources

• CVE-2026-25904
• JFrog Security Analysis: Deno SSRF

Impact

Critical Sandbox Escape & Server Takeover: A critical security vulnerability exists in mcp-run-python due to a lack of isolation between the Python runtime (Pyodide) and the host JavaScript environment.

The runPython and runPythonAsync functions execute Python code using Pyodide without restricting access to the JavaScript bridge. This allows any executed Python code—whether from a user or an AI model—to access the js module in Pyodide. Through this bridge, the Python code can modify the global JavaScript environment, interact with the Node.js process, and alter the behavior of the MCP server.

Specific Attack Vector: MCP Tool Shadowing Because the Python code can modify the JS runtime, an attacker can dynamically overwrite or "shadow" existing MCP tools registered on the server. For example, an attacker could replace a secure file-reading tool with a malicious version that exfiltrates data to an external server, all while the MCP server appears to be functioning normally.

Patches

No Patch Available: The mcp-run-python project is currently archived and maintainers have indicated it is unlikely to receive a fix.

Recommendation: Users are strongly advised to immediately stop using this package. If functionality is required, users must migrate to a maintained alternative that implements proper sandboxing (e.g., running Python in a Docker container or a restricted WASM environment with the JS bridge disabled).

Workarounds

There are no configuration-based workarounds. Securing the environment requires modifying the source code to disable the Pyodide-to-JS bridge or moving the execution environment to a fully isolated sandbox (e.g., a separate container).

Resources

• CVE-2026-25905
• JFrog Security Analysis: MCP Takeover

Impact

Server-Side Request Forgery (SSRF): A security vulnerability exists in the mcp-run-python tool (specifically within the Pydantic-AI integration) due to an overly permissive Deno sandbox configuration.

The tool configures the Deno runtime—which is intended to isolate the execution of untrusted Python code—with network permissions that include access to the host's loopback interface (localhost). Consequently, malicious Python code executed through the tool can bypass network isolation and send HTTP requests to internal services running on the host machine. This allows attackers to interact with local APIs, databases, or cloud metadata services that should not be accessible from the sandbox.

Patches

No Patch Available: The mcp-run-python project is currently archived and maintainers have indicated it is unlikely to receive a fix.

Recommendation: Users are strongly advised to immediately stop using this package. If functionality is required, users must migrate to an alternative execution environment that enforces strict network isolation (e.g., blocking all outbound traffic or explicitly denying access to 127.0.0.1/::1).

Workarounds

There are no configuration-based workarounds provided by the package itself. Remediation requires modifying the source code to restrict the Deno permissions (specifically removing or narrowing the --allow-net flag) or moving the execution to a container with no network access.

Resources

• CVE-2026-25904
• JFrog Security Analysis: Deno SSRF

Impact

Critical Sandbox Escape & Server Takeover: A critical security vulnerability exists in mcp-run-python due to a lack of isolation between the Python runtime (Pyodide) and the host JavaScript environment.

The runPython and runPythonAsync functions execute Python code using Pyodide without restricting access to the JavaScript bridge. This allows any executed Python code—whether from a user or an AI model—to access the js module in Pyodide. Through this bridge, the Python code can modify the global JavaScript environment, interact with the Node.js process, and alter the behavior of the MCP server.

Specific Attack Vector: MCP Tool Shadowing Because the Python code can modify the JS runtime, an attacker can dynamically overwrite or "shadow" existing MCP tools registered on the server. For example, an attacker could replace a secure file-reading tool with a malicious version that exfiltrates data to an external server, all while the MCP server appears to be functioning normally.

Patches

No Patch Available: The mcp-run-python project is currently archived and maintainers have indicated it is unlikely to receive a fix.

Recommendation: Users are strongly advised to immediately stop using this package. If functionality is required, users must migrate to a maintained alternative that implements proper sandboxing (e.g., running Python in a Docker container or a restricted WASM environment with the JS bridge disabled).

Workarounds

There are no configuration-based workarounds. Securing the environment requires modifying the source code to disable the Pyodide-to-JS bridge or moving the execution environment to a fully isolated sandbox (e.g., a separate container).

Resources

• CVE-2026-25905
• JFrog Security Analysis: MCP Takeover

Impact

Server-Side Request Forgery (SSRF): A security vulnerability exists in the mcp-run-python tool (specifically within the Pydantic-AI integration) due to an overly permissive Deno sandbox configuration.

The tool configures the Deno runtime—which is intended to isolate the execution of untrusted Python code—with network permissions that include access to the host's loopback interface (localhost). Consequently, malicious Python code executed through the tool can bypass network isolation and send HTTP requests to internal services running on the host machine. This allows attackers to interact with local APIs, databases, or cloud metadata services that should not be accessible from the sandbox.

Patches

No Patch Available: The mcp-run-python project is currently archived and maintainers have indicated it is unlikely to receive a fix.

Recommendation: Users are strongly advised to immediately stop using this package. If functionality is required, users must migrate to an alternative execution environment that enforces strict network isolation (e.g., blocking all outbound traffic or explicitly denying access to 127.0.0.1/::1).

Workarounds

There are no configuration-based workarounds provided by the package itself. Remediation requires modifying the source code to restrict the Deno permissions (specifically removing or narrowing the --allow-net flag) or moving the execution to a container with no network access.

Resources

• CVE-2026-25904
• JFrog Security Analysis: Deno SSRF

Impact

Critical Sandbox Escape & Server Takeover: A critical security vulnerability exists in mcp-run-python due to a lack of isolation between the Python runtime (Pyodide) and the host JavaScript environment.

The runPython and runPythonAsync functions execute Python code using Pyodide without restricting access to the JavaScript bridge. This allows any executed Python code—whether from a user or an AI model—to access the js module in Pyodide. Through this bridge, the Python code can modify the global JavaScript environment, interact with the Node.js process, and alter the behavior of the MCP server.

Specific Attack Vector: MCP Tool Shadowing Because the Python code can modify the JS runtime, an attacker can dynamically overwrite or "shadow" existing MCP tools registered on the server. For example, an attacker could replace a secure file-reading tool with a malicious version that exfiltrates data to an external server, all while the MCP server appears to be functioning normally.

Patches

No Patch Available: The mcp-run-python project is currently archived and maintainers have indicated it is unlikely to receive a fix.

Recommendation: Users are strongly advised to immediately stop using this package. If functionality is required, users must migrate to a maintained alternative that implements proper sandboxing (e.g., running Python in a Docker container or a restricted WASM environment with the JS bridge disabled).

Workarounds

There are no configuration-based workarounds. Securing the environment requires modifying the source code to disable the Pyodide-to-JS bridge or moving the execution environment to a fully isolated sandbox (e.g., a separate container).

Resources

• CVE-2026-25905
• JFrog Security Analysis: MCP Takeover

Impact

Server-Side Request Forgery (SSRF): A security vulnerability exists in the mcp-run-python tool (specifically within the Pydantic-AI integration) due to an overly permissive Deno sandbox configuration.

The tool configures the Deno runtime—which is intended to isolate the execution of untrusted Python code—with network permissions that include access to the host's loopback interface (localhost). Consequently, malicious Python code executed through the tool can bypass network isolation and send HTTP requests to internal services running on the host machine. This allows attackers to interact with local APIs, databases, or cloud metadata services that should not be accessible from the sandbox.

Patches

No Patch Available: The mcp-run-python project is currently archived and maintainers have indicated it is unlikely to receive a fix.

Recommendation: Users are strongly advised to immediately stop using this package. If functionality is required, users must migrate to an alternative execution environment that enforces strict network isolation (e.g., blocking all outbound traffic or explicitly denying access to 127.0.0.1/::1).

Workarounds

There are no configuration-based workarounds provided by the package itself. Remediation requires modifying the source code to restrict the Deno permissions (specifically removing or narrowing the --allow-net flag) or moving the execution to a container with no network access.

Resources

• CVE-2026-25904
• JFrog Security Analysis: Deno SSRF