The safeguards map / 3.3 Gateways
LiteLLM
Drafted with AI
Drafted with AI from the cited sources under the direction of UnGovr staff. UnGovr holds editorial responsibility for this page. How this site is made
An open-source large language model (LLM) proxy and Model Context Protocol (MCP) gateway that routes model, tool and agent calls with tool allow and deny lists, guardrails and tracing.
Where it sits
3.3 Gateways (primary): Sits on the path between applications and their models, MCP servers and agents, and lets the operator allow or block specific tools and runs guardrails on inputs and outputs.
LiteLLM namespaces multiple MCP servers by prefixing each tool name with its MCP server name
captured
Route, control, and observe LLM traffic
captured
Register and invoke A2A agents
captured
Use disallowed_tools to block specific tools. All other tools will be available.
captured
Run before LLM call, on input
captured
Facts
- Concern
- security
- Names the law
- no
- Subject
- agentAI system
- Used by
- those who run it
- Runs
- at runtime
- Policy comes from
- owner-entered settings
- Traffic it sees
- model callstool calls (MCP)agent to agent (A2A)
- Can the agent bypass it
- depends
Handoffs
produces Runtime records: OpenTelemetry (OTLP exporters)
Every quote is verbatim from a stored capture of the page linked under it. Placement is our reading of the product's own documentation; no publisher has reviewed or endorsed it. Rows CC BY 4.0. Names, marks and logos belong to their owners; logos identify each product and are not part of the dataset.