F
licenseNot graded
qualityA
maintenanceGuardrails service for AI agents that evaluates every tool call for safety and alignment before execution, providing default-deny policy, LLM safety evaluation, and audit trail.
21
-
fusion
by Katawwr
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@fusionrun an eval on my agent and grade it, fail below a B"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Use
pip install "fusion-safety[serve,mcp]"
fusion doctor
fusion run start --prompt agent.txt --target ollama:llama3.2:1b --grader claude-cli
fusion run finalize --min-grade B # report card; exit 1 below the bar
fusion serveAny model or agent can be the target: ollama:<model>, openai-compat:<url>#<model>, claude-cli:<model>, a
hosted API with your own key (openai:, anthropic:, hf:, ...; needs FUSION_ALLOW_API_SPEND=1), or any
program via cmd:<command>.
Runtime guardrail in your agent loop:
from fusion_first.guardrail.guard import Guardrail
from fusion_first.guardrail.policy import GuardConfig
guard = Guardrail(GuardConfig(allowlisted_domains=["your-co.com"], require_authorization=True))
outcome = guard.guard_tool_call(tool_name, tool_args, user_request=user_message,
untrusted_context=True, untrusted_text=tool_results)
if outcome.blocked: ...Claude Code: claude plugin marketplace add "$(fusion plugin-dir)" && claude plugin install fusion@fusion-first.
MCP: { "mcpServers": { "fusion": { "command": "fusion-mcp" } } } exposes the run engine and the guard's
guardrail_snippet / check_tool_call tools.
Related MCP server: sentinel-mcp
License
MIT
This server cannot be deployed
Maintenance
ActivityMaintained
ResponsivenessNo issues
Related MCP Connectors
Runtime permission, approval, and audit layer for AI agent tool execution.
Create and run AI evaluations, record traces, and inspect results with scoped organization access.
Deterministic runtime safety for AI agents: scan PII, gate tool actions, verify LLM output.
Run AI agent evaluations on your own model keys, and publish runs others can review and re-run.
Related MCP Servers
- AlicenseNot gradedqualityBmaintenanceEnables governed tool-calling agents with policy decisions, optional human approval, hash-chained audit logging, and deterministic evaluation.MIT
- AlicenseAqualityBmaintenanceEnables AI agent tool calls to be intercepted and judged before execution, allowing, asking a human, or blocking based on calibrated risk and policy.15MIT
- AlicenseNot gradedqualityBmaintenanceEnables monitoring and interruption of autonomous agent runs by detecting infinite tool loops, livelocks, and planning deadlocks, with safety guardrails for prompt injection, spend limits, and sandboxed command execution.7MIT