Supports AI-assisted scan, fix, and exploit features by calling a configurable OpenAI-compatible LLM endpoint, with base URL, API key, model, and repository root configured via environment variables.
mcp-name: io.github.lambdasec/frame-mcp
An MCP server that exposes the Frame security scanner to any MCP client, so a coding agent can scan code, verify fixes, and reason about vulnerabilities over stdio.
Frame combines taint analysis with separation logic verification to find data-flow vulnerabilities (SQL injection, command injection, path traversal, and more), and checks each reported path with a solver. This package wraps the frame command line program as MCP tools. It launches frame as a subprocess with an explicit argument list, never a shell, and prefers the frame executable installed next to the running Python interpreter.
Run directly with uvx (no separate install step):
uvx frame-mcpclaude mcp add frame -- uvx frame-mcpAdd this stanza to ~/.codex/config.toml:
[mcp_servers.frame]
command = "uvx"
args = ["frame-mcp"]Create .cursor/mcp.json:
{
"mcpServers": {
"frame": {
"command": "uvx",
"args": ["frame-mcp"]
}
}
}Create .vscode/mcp.json:
{
"servers": {
"frame": {
"type": "stdio",
"command": "uvx",
"args": ["frame-mcp"]
}
}
}Add to ~/.codeium/windsurf/mcp_config.json under the mcpServers key:
{
"mcpServers": {
"frame": {
"command": "uvx",
"args": ["frame-mcp"]
}
}
}Add to ~/.gemini/settings.json under the mcpServers key:
{
"mcpServers": {
"frame": {
"command": "uvx",
"args": ["frame-mcp"]
}
}
}Add to Zed settings.json under context_servers:
{
"context_servers": {
"frame": {
"command": {
"path": "uvx",
"args": ["frame-mcp"]
}
}
}
}Related MCP server: scanline
Tool | Purpose | Read only |
| Scan a file or directory for vulnerabilities and return findings as JSON. | yes |
| Scan a path and record the findings as a baseline file. | no |
| Re-scan the files behind earlier findings and report whether each is fixed. | yes |
| Generate and verify fixes for findings. Returns a diff by default. | no |
| Drive an agent to exploit a live, authorized target. | no |
| List the framework packs a scan would load. | yes |
| Validate framework pack files. | yes |
| Check a separation logic entailment | yes |
A security-review prompt chains scan (with the AI layer), verify, and an offer to fix.
The scan tool with ai=true, along with fix and exploit, call an LLM through an OpenAI-compatible endpoint. Configure it with these environment variables in the MCP client that launches the server:
Variable | Purpose |
| Base URL of the LLM endpoint, for example a local server or a hosted API. |
| API key for the endpoint, when it requires one. |
| Model name to request. |
| Repository root for relative path resolution. |
These are inherited from the server process environment and forwarded to each frame subprocess. The plain scan (taint analysis plus verification) needs none of them.
The exploit tool drives an autonomous agent that sends live traffic to a target. Run it only against systems you own or are explicitly authorized to test. Unauthorized testing of systems you do not control may be illegal.
Apache-2.0. See LICENSE.
This server cannot be deployed
MCP server for static security analysis of Android source code
Security scanner for MCP servers. Detect vulnerabilities, prompt injection, and tool poisoning.
ZEN SecDB MCP server for CVE intelligence, CVSS/EPSS scoring, advisories, SSVC, and package audits.