agentleFS
BerriAIBerriAI/litellm-skills/add-mcp/SKILL.md

add-mcp

Skill84 starsChanged 7 months agoMITView on GitHub

Register a new MCP server on a live LiteLLM proxy. Asks for the server name, transport type, URL, and optional auth, then calls POST /v1/mcp/server.

  • Reads credentials
  • Sends data out

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Ask for these if not already known:

    line 20

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Add MCP Server

Register an MCP (Model Context Protocol) server on a live LiteLLM proxy so it can be used by models and agents.

Setup

Ask for these if not already known:

LITELLM_BASE_URL  — e.g. https://my-proxy.example.com
LITELLM_API_KEY   — proxy admin key

API reference: https://docs.litellm.ai/docs/mcp

Ask the user

  1. Server name (required, e.g. my-github-mcp)
  2. URL (required, e.g. https://mcp.example.com/sse)
  3. Transport — sse (default), http, or stdio
  4. Description (optional)
  5. Auth — does it need a bearer token or API key? (optional)

Run

curl -s -X POST "$BASE/v1/mcp/server" \
  -H "Authorization: Bearer $KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "server_name": "<name>",
    "url": "<url>",
    "transport": "sse",
    "description": "<description_or_omit>",
    "auth_type": "bearer_token",
    "credentials": "<token_if_needed>"
  }'

For unauthenticated servers, omit auth_type and credentials.

List existing MCP servers

curl -s "$BASE/v1/mcp/server" \
  -H "Authorization: Bearer $KEY"

Delete an MCP server

curl -s -X DELETE "$BASE/v1/mcp/server/<server_id>" \
  -H "Authorization: Bearer $KEY"

Output

Show server_id — needed to reference this MCP server in agent configs or to delete it later.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.