litellm-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| LITELLM_URL | Yes | Base URL of the LiteLLM proxy (no trailing slash) | |
| LITELLM_API_KEY | Yes | Admin bearer key (master or admin virtual key) |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| litellm_versionA | Get the MCP server version and the LiteLLM service readiness.
|
| litellm_adminA | Proxy-global LiteLLM administration (high risk): proxy-global settings, allowed IPs, global spend reset, bulk user update. Call with operation="help" to list all available admin operations. Otherwise pass the operation name and a JSON object with parameters. Example: litellm_admin(operation="AddAllowedIp", params={"ip": "1.2.3.4"}) |
| litellm_deleteB | Delete LiteLLM resources (destructive, irreversible), including cache flushall. Call with operation="help" to list all available delete operations. Otherwise pass the operation name and a JSON object with parameters. Example: litellm_delete(operation="DeleteKeys", params={"keys": ["sk-..."]}) |
| litellm_executeA | Execute reversible actions on LiteLLM resources: block/unblock toggles, key regenerate/reset, connection tests, targeted cache delete. Call with operation="help" to list all available execute operations. Otherwise pass the operation name and a JSON object with parameters. Example: litellm_execute(operation="BlockKey", params={"key": "sk-..."}) |
| litellm_readA | Query LiteLLM proxy data (safe, read-only): lists, infos, spend/usage, health, settings reads, token/cost utils, MCP gateway registry reads. Call with operation="help" to list all available read operations. Otherwise pass the operation name and a JSON object with parameters. Example: litellm_read(operation="ListKeys") |
| litellm_writeA | Create or update LiteLLM resources (non-destructive): keys, teams, users, orgs, customers, budgets, models, credentials, tags, guardrails, fallbacks, MCP servers/toolsets, access groups. Call with operation="help" to list all available write operations. Otherwise pass the operation name and a JSON object with parameters. Example: litellm_write(operation="GenerateKey", params={"team_id": "..."}) |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 6 tools
The tools are separated into clear action categories (read/write/delete/execute/admin/version), which largely avoids confusion. However, litellm_delete and litellm_execute both involve cache deletion, and litellm_admin overlaps with litellm_write for user updates, creating minor boundary ambiguity.
All tools share the consistent 'litellm_' prefix plus a descriptive word, forming a predictable pattern. The pattern is slightly broken by 'litellm_admin' and 'litellm_version', which use nouns rather than verbs, but this is a minor deviation.
Six tools is a well-scoped count for a proxy management server. Each tool represents a broad but coherent category of operations, making the surface area manageable for an agent without being too thin or bloated.
The tool set covers version/health, read-only queries, create/update, delete, reversible actions, and global admin operations. This provides comprehensive lifecycle coverage for LiteLLM resources with no obvious dead ends.