litellm_key_list

【内网/内部 API Key】查询公司内网 virtual key 列表(含 key_alias、脱敏 key_name、lookup_token)。适用于:管理员查全部 key、员工查自己的 key。关键词:api key列表、密钥列表、内部key

Server Litellm Admin junwayne66/litellm-admin-mcp
Category Read
Risk class Low
Parameters 00 required

What litellm_key_list does on Litellm Admin

AI agents call litellm_key_list to retrieve information from Litellm Admin without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

Why litellm_key_list needs a policy

This tool retrieves and lists virtual API keys and authentication credentials without modifying or deleting them. The operation is fundamentally a read/query action. However, severity is high rather than low because the data returned includes sensitive authentication material (API keys, lookup tokens) that could enable unauthorized access if an agent misuses this tool to exfiltrate credentials or expose them in logs.

From the tool's definition Tool description states '查询公司内网 virtual key 列表' (query company internal virtual key list), with the term '查询' (query/retrieve) indicating a read operation that retrieves API keys and related metadata (key_alias, key_name, lookup_token).

Questions about litellm_key_list

What does the litellm_key_list tool do? +

【内网/内部 API Key】查询公司内网 virtual key 列表(含 key_alias、脱敏 key_name、lookup_token)。适用于:管理员查全部 key、员工查自己的 key。关键词:api key列表、密钥列表、内部key. It is categorised as a Read tool in the Litellm Admin MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on litellm_key_list? +

Register the Litellm Admin MCP server in PolicyLayer and add a rule for litellm_key_list: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Litellm Admin. Nothing to install.

What risk level is litellm_key_list? +

litellm_key_list is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit litellm_key_list? +

Yes. Add a rate_limit block to the litellm_key_list rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.

How do I block litellm_key_list completely? +

Set action: deny in the PolicyLayer policy for litellm_key_list. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.

What MCP server provides litellm_key_list? +

litellm_key_list is provided by the Litellm Admin MCP server (junwayne66/litellm-admin-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

// LOOK UP ANOTHER SERVER

Every MCP server has a record like this.

Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.

Teams ship this data inside their own products. See what a licence covers →

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.