Code Firewall MCP runs on your own machine — the client starts it, so there is no endpoint to ping. 82 installs a week from pypi. Last commit 19 Jan 2026.
Structural similarity-based code filter. Stops malicious code pattern reaching execution tools.
We read the source, 4 d ago · rules 995398eba69f
A value the model can set ends up inside a file or shell call. That is not a flaw by itself — for a terminal server it is the job — but it is where things go wrong when it is not.
install_proc = subprocess.run(
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
That is not a flaw by itself — but it is where things go wrong when it is not the job. We re-read this code on every release. Watch it and you hear from us the day another one appears.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add code-firewall-mcp -- uvx code-firewall-mcp
{
"mcpServers": {
"code-firewall-mcp": {
"command": "uvx",
"args": [
"code-firewall-mcp"
]
}
}
}
[mcp_servers.code-firewall-mcp]
command = "uvx"
args = ["code-firewall-mcp"]
{
"mcpServers": {
"code-firewall-mcp": {
"command": "uvx",
"args": [
"code-firewall-mcp"
]
}
}
}
{
"servers": {
"code-firewall-mcp": {
"type": "stdio",
"command": "uvx",
"args": [
"code-firewall-mcp"
]
}
}
}
Optional settings from the registry entry, left out of the block above:
FIREWALL_DATA_DIR (Directory for storing ChromaDB data), OLLAMA_URL (URL for Ollama server (default: http://localhost:11434)), EMBEDDING_MODEL (Ollama embedding model (default: nomic-embed-text)), SIMILARITY_THRESHOLD (Block threshold 0-1 (default: 0.85)).
Structural code-quality tools for AI coding agents.
Structural codebase indexer with 17 query tools. 87% token reduction. Zero dependencies.
US law MCP: bills, US Code, Federal Register, executive orders, case law (state+federal), eCFR
Wraps Codex CLI as MCP tools: codex, review, query, search, structured, ping, listSessions.
Code-map tools for AI agents: see a repo's structure first, then edit only what matters.
Wraps Claude Code CLI as MCP tools: query, search, structured, ping, listSessions.
Zero-LLM structural code retrieval for AI coding agents, served over MCP.
Code review as an MCP server — structured reviews with OWASP security scanning.
Answers built from our own checks of this server.