cerbere-ag-mcp

Purpose: Protecting MCP-compatible AI agents from prompt injection, PII exposure, and unauthorized tool use.

Inferred · not functionally tested

Audience: AI agent developers

Inferred · not functionally tested

Functions: agents

Inferred · not functionally tested

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

Recorded constraints: pricing: open_source · license: MIT · platforms: CLI · deployment: cli, self_hosted, api_only

Constraint provenance is unknown; confirm requirements with the publisher.

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

cerbere-ag-mcp is an AI & LLM security project. Inferred · not functionally tested: It focuses on protecting MCP-compatible AI agents from prompt injection, PII exposure, and unauthorized tool use. Inferred · not functionally tested: It is built as an open-source project for AI agent developers. Basis unknown · not verified: cerbere-ag-mcp is open source under the MIT license. Basis unknown · not verified: It runs on the command line and API, and it can be self-hosted.

Chrismsmr Celcom builds and maintains cerbere-ag-mcp, and it first shipped in 2026. Development happens publicly on GitHub with 501 commits in the last 90 days. Inferred · not functionally tested: Key capabilities include prompt injection checks, PII redaction, and tool authorization. Inferred · not functionally tested: Catalogued interfaces include an MCP server.

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