Search / io.github.BerriAI/litellm-mcp
LiteLLM Multi-Model API
L0· runs locallyAccess 100+ LLMs with one API: GPT-4, Claude, Gemini, Mistral, and more.
v1.0.2 · active · repository · descriptor JSON · versions
Search / io.github.BerriAI/litellm-mcp
L0· runs locallyAccess 100+ LLMs with one API: GPT-4, Claude, Gemini, Mistral, and more.
v1.0.2 · active · repository · descriptor JSON · versions
{
"mcpServers": {
"litellm-mcp": {
"command": "python",
"args": [
"litellm-mcp"
],
"env": {
"OPENAI_API_KEY": "${OPENAI_API_KEY}",
"ANTHROPIC_API_KEY": "${ANTHROPIC_API_KEY}",
"LITELLM_API_KEY": "${LITELLM_API_KEY}"
}
}
}
}claude mcp add litellm-mcp -e "OPENAI_API_KEY=${OPENAI_API_KEY}" -e "ANTHROPIC_API_KEY=${ANTHROPIC_API_KEY}" -e "LITELLM_API_KEY=${LITELLM_API_KEY}" -- python litellm-mcp[mcp_servers.litellm-mcp]
command = "python"
args = ["litellm-mcp"]
env = { "OPENAI_API_KEY" = "${OPENAI_API_KEY}", "ANTHROPIC_API_KEY" = "${ANTHROPIC_API_KEY}", "LITELLM_API_KEY" = "${LITELLM_API_KEY}" }
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"litellm-mcp": {
"type": "local",
"command": [
"python",
"litellm-mcp"
],
"enabled": true,
"environment": {
"OPENAI_API_KEY": "{env:OPENAI_API_KEY}",
"ANTHROPIC_API_KEY": "{env:ANTHROPIC_API_KEY}",
"LITELLM_API_KEY": "{env:LITELLM_API_KEY}"
}
}
}
}{
"mcpServers": {
"litellm-mcp": {
"command": "python",
"args": [
"litellm-mcp"
],
"env": {
"OPENAI_API_KEY": "${OPENAI_API_KEY}",
"ANTHROPIC_API_KEY": "${ANTHROPIC_API_KEY}",
"LITELLM_API_KEY": "${LITELLM_API_KEY}"
}
}
},
"deeplink": "cursor://anysphere.cursor-deeplink/mcp/install?name=litellm-mcp&config=eyJjb21tYW5kIjoicHl0aG9uIiwiYXJncyI6WyJsaXRlbGxtLW1jcCJdLCJlbnYiOnsiT1BFTkFJX0FQSV9LRVkiOiIke09QRU5BSV9BUElfS0VZfSIsIkFOVEhST1BJQ19BUElfS0VZIjoiJHtBTlRIUk9QSUNfQVBJX0tFWX0iLCJMSVRFTExNX0FQSV9LRVkiOiIke0xJVEVMTE1fQVBJX0tFWX0ifX0%3D"
}{
"servers": {
"litellm-mcp": {
"type": "stdio",
"command": "python",
"args": [
"litellm-mcp"
],
"env": {
"OPENAI_API_KEY": "${OPENAI_API_KEY}",
"ANTHROPIC_API_KEY": "${ANTHROPIC_API_KEY}",
"LITELLM_API_KEY": "${LITELLM_API_KEY}"
}
}
}
}{
"mcpServers": {
"litellm-mcp": {
"command": "python",
"args": [
"litellm-mcp"
],
"env": {
"OPENAI_API_KEY": "${OPENAI_API_KEY}",
"ANTHROPIC_API_KEY": "${ANTHROPIC_API_KEY}",
"LITELLM_API_KEY": "${LITELLM_API_KEY}"
}
}
}
}extensions:
"litellm-mcp":
enabled: true
name: "litellm-mcp"
type: stdio
cmd: "python"
args:
- "litellm-mcp"
envs:
"OPENAI_API_KEY": "${OPENAI_API_KEY}"
"ANTHROPIC_API_KEY": "${ANTHROPIC_API_KEY}"
"LITELLM_API_KEY": "${LITELLM_API_KEY}"
timeout: 300
Placeholders to fill from your own secret store: ${OPENAI_API_KEY}, ${ANTHROPIC_API_KEY}, ${LITELLM_API_KEY}. The registry never accepts secret values.
This is a local package: the command runs on your machine.
Not scored: fewer than three checks apply, usually because no remote answered a credential-free probe or the server is a local package.
protocol.modern, protocol.stateless, protocol.transport, protocol.list_ttlno remote answered a protocol handshake (not probed yet, unreachable, or local-only)auth.prm, auth.as_metadata, auth.cimdno remote uses OAuthauth.secret_in_urlno templated URLtools.descriptions, tools.description_length, tools.schemas, tools.annotations, tools.directory_hints, tools.token_cost, tools.api_dumptool list unknown (behind auth, not probed, or empty)stability.changes, stability.rug_pulltool list unknowndeps.known_vulns2 advisories to act on (malicious, or rated high or critical with a fix available): GHSA-2g87-pp6c-29x5 in [email protected] (indirect, fixed in 3.14.4), GHSA-5wr8-gcqf-gqf3 in [email protected] (indirect, fixed in 3.14.4); 1 more of lower severity or without a fixdeps.mcp_sdk_versionmcp 2.2.0, no known advisorydeps.resolvable[email protected] resolved: 73 packagesNo tool definition changes recorded. A server's first observation is its baseline; later probes record what changes.
Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed. How it is computed.
+repository +namespace-matches-repo ~liveness-unmeasured -stale-254d
Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed. How it is computed.
[email protected] PyPI72 dependencies, resolved · MCP SDK mcp 2.2.0 · advisories checked 2026-10-19
| advisory | severity | package | fixed in |
|---|---|---|---|
| GHSA-2g87-pp6c-29x5aiohttp: Multiple instances of excessive or unbounded memory/CPU use | high | [email protected]indirect | fixed in 3.14.4 |
| GHSA-5wr8-gcqf-gqf3aiohttp server lacks an initial request/header timeout | high | [email protected]indirect | fixed in 3.14.4 |
| GHSA-494j-54xm-rwp3AIOHTTP: Secure attribute not enforced for shared cookie | low | [email protected]indirect | fixed in 3.14.4 |
Dependency graphs from deps.dev; advisories from OSV.dev, including the GitHub Advisory Database and the PyPI Advisory Database; all CC BY 4.0. The graph is what a clean install of this version resolves today; nothing was installed or run. How it is checked.
| package | registry | version | runtime | secrets |
|---|---|---|---|---|
litellm-mcp | pypi | 1.0.2 | python | OPENAI_API_KEY, ANTHROPIC_API_KEY, LITELLM_API_KEY |
No tools observed. Local packages are never executed by the registry.
Schemas: list_tools.
{
"name": "io.github.BerriAI/litellm-mcp",
"title": "LiteLLM Multi-Model API",
"$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
"version": "1.0.2",
"packages": [
{
"version": "1.0.2",
"transport": {
"type": "stdio"
},
"identifier": "litellm-mcp",
"runtimeHint": "python",
"registryType": "pypi",
"environmentVariables": [
{
"name": "OPENAI_API_KEY",
"isSecret": true,
"description": "OpenAI API key for GPT models"
},
{
"name": "ANTHROPIC_API_KEY",
"isSecret": true,
"description": "Anthropic API key for Claude models"
},
{
"name": "LITELLM_API_BASE",
"description": "LiteLLM Proxy base URL (optional)"
},
{
"name": "LITELLM_API_KEY",
"isSecret": true,
"description": "LiteLLM Proxy API key (optional)"
}
]
}
],
"repository": {
"url": "https://github.com/BerriAI/litellm-agent-mcp",
"source": "github"
},
"description": "Access 100+ LLMs with one API: GPT-4, Claude, Gemini, Mistral, and more."
}