Agent Prompt Injection Firewall Mcp
by CSOAI-ORGcommunityv1.0.11
This MCP server scans prompts and logs for prompt injection and lets users define and list custom firewall rules. It also supports generating signed firewall attestations.
From the registry: The WAF for agents. Pattern-based + heuristic firewall scans prompts, RAG documents, tool argume...
Install & configure
Prerequisites
- requiredInstall the Python packageInstall the MCP server from PyPI so the executable is available on your system.
https://pypi.org/project/agent-prompt-injection-firewall-mcp/'}],$ pip install agent-prompt-injection-firewall-mcp
Install in your client
Paste into the AI you're chatting with — it will figure out the rest
Please install the `agent-prompt-injection-firewall-mcp` MCP server into my current AI client (that's you).
Required prerequisites (do these first if not already done):
- **Install the Python package** — Install the MCP server from PyPI so the executable is available on your system. Run: `pip install agent-prompt-injection-firewall-mcp` (https://pypi.org/project/agent-prompt-injection-firewall-mcp/'}],)
Canonical MCP server config (stdio transport):
- command: `agent-prompt-injection-firewall-mcp`
- args: []
Note: README provides a stdio command for MCP clients via the installed Python package. A Docker run example is shown, but no canonical MCP HTTP/SSE client configuration is documented, so the portable pip-installed stdio path is preferred.
Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.Note: README provides a stdio command for MCP clients via the installed Python package. A Docker run example is shown, but no canonical MCP HTTP/SSE client configuration is documented, so the portable pip-installed stdio path is preferred.
Tools (5)
scan_prompt
Scans a prompt for prompt injection or other malicious content.
define_custom_rule
Creates a custom firewall rule for prompt injection detection.
list_rules
Lists the configured firewall rules.
scan_log
Scans logs for prompt injection or related threats.
sign_firewall_attestation
Generates a signed attestation for firewall scanning results.
Packages
agent-prompt-injection-firewall-mcp
pypiv1.0.11transport: stdio
Remote Endpoints
https://api.meok.ai/v1/a2a/prompt-injection-firewall
type: streamable-http
Details
- Language
- Python
- License
- MIT
- Released
- Jun 13, 2026
- Last commit
- Jun 13, 2026
- Registry name
- io.github.CSOAI-ORG/agent-prompt-injection-firewall-mcp