bulwark-mcp

Purpose: Protecting AI agent servers from indirect prompt injection attacks via a firewall for MCP servers.

Inferred · not functionally tested

Audience: AI infrastructure engineers and security teams

Inferred · not functionally tested

Functions: monitoring

Inferred · not functionally tested

Interfaces: API: unknown · MCP: indicated (inferred, not tested) · CLI: indicated (inferred, not tested) · Self-hosting: indicated (inferred, not tested)

Recorded constraints: pricing: open_source · license: AGPL-3.0 · platforms: CLI · deployment: cli, self_hosted

Constraint provenance is unknown; confirm requirements with the publisher.

Record sources: pypi.org · github.com. These links do not verify the individual claims.

bulwark-mcp is an AI & LLM security project. Inferred · not functionally tested: It focuses on protecting AI agent servers from indirect prompt injection attacks via a firewall for MCP servers. Inferred · not functionally tested: bulwark-mcp is an open-source project aimed at AI infrastructure engineers and security teams. Basis unknown · not verified: The project is open source (AGPL-3.0). Basis unknown · not verified: It ships for the command line, and it can be self-hosted.

It is developed by churik5, and it first shipped in 2026. Development happens publicly on GitHub with 82 commits in the last 90 days. Inferred · not functionally tested: Among its 5 catalogued features are prompt injection protection, audit logging, and MCP server support. Basis unknown · not verified: Catalogued interfaces include an MCP server.

Summary written by a language model from the project’s public pages.