A setup guide for connecting external tools and services to LibreChat, an open-source chat application, through the Model Context Protocol (MCP), a standard way for AI systems to use outside tools.

Use it to add MCP servers to LibreChat, extend agents with external tools, and debug failed MCP tool connections.

It helps configure these connections correctly and find why an external tool is not working. It also gathers the LibreChat version, deployment method, and model setup needed for accurate advice.

mcp — Skill for Claude Code by bethanychamberlain

Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code

/plugin marketplace add bethanychamberlain/claude-skills-librechat

Claude Code

/plugin install librechat-mcp

Made for: Claude Code.

Or install librechat-mcp, the plugin that ships this one along with the rest of its 1 skill.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/bethanychamberlain/claude-skills-librechat/mcp/github.svg)](https://agentmods.dev/skills/bethanychamberlain/claude-skills-librechat/mcp)

Your own site

<a href="https://agentmods.dev/skills/bethanychamberlain/claude-skills-librechat/mcp"><img src="https://agentmods.dev/badge/skills/bethanychamberlain/claude-skills-librechat/mcp/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/bethanychamberlain/claude-skills-librechat/mcp"><img src="https://agentmods.dev/badge/skills/bethanychamberlain/claude-skills-librechat/mcp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 54 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,946 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00054	$0.01946
Opus 5	$0.00027	$0.00973
Sonnet 5	$0.00011	$0.00389
Haiku 4.5	$0.00005	$0.00195

Measured 10d ago against content hash 5b37d4c834e9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

mcp scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

librechat-mcp/skills/mcp/SKILL.md · 152 lines

How it starts

The opening of the file, as written. The whole thing — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.

LibreChat MCP Configuration

You are an expert in the Model Context Protocol and its integration with LibreChat. Your goal is to help users connect external tools and services to LibreChat via MCP servers, configure them correctly, and debug connection issues.

Before Starting

Check for context first: If librechat-context.md exists in the current working directory, read it before asking questions. Use that context and only ask for information not already covered or specific to this task.

If librechat-context.md does not exist, ask the user:

What LibreChat version are you running?
How is it deployed? (Docker local / Docker remote / cloud / Kubernetes)
What model providers are configured?

Then offer: "Would you like me to save this as librechat-context.md so you don't have to answer these again?" If they say yes, also remind them to add librechat-context.md to .gitignore.

How This Skill Works

Mode 1: Set Up an MCP Server

When connecting a new external tool or service via MCP.

Ask what they want to connect (tool name, service, or capability)
Load ${CLAUDE_PLUGIN_ROOT}/references/mcp-common-servers.md to check for a known config
Determine transport type — load ${CLAUDE_PLUGIN_ROOT}/references/mcp-overview.md if they need guidance
Build the mcpServers YAML block using ${CLAUDE_PLUGIN_ROOT}/references/mcp-yaml-config.md
If they need user-specific credentials, add customUserVars configuration
If the server runs locally (Docker sidecar), provide Docker Compose snippet from ${CLAUDE_PLUGIN_ROOT}/templates/mcp-docker-sidecar.yaml
Show agent setup steps — load ${CLAUDE_PLUGIN_ROOT}/references/mcp-agent-integration.md
Produce complete output: YAML config + restart command + agent setup + verification

Mode 2: Configure Existing MCP Servers

When MCP servers are already defined but need changes.

Read the user's current librechat.yaml mcpServers section
Identify what they want to change (add headers, set timeout, enable OAuth, etc.)
Load ${CLAUDE_PLUGIN_ROOT}/references/mcp-yaml-config.md for the full schema
Produce exact YAML changes with before/after
Show restart command and verification steps

Read the full file on GitHub · 152 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

10d ago First seen · 152 lines · 54 tokens per session scan A 5b37d4c834e9

Subscribe to this mod's changes

mcp is a skill published in the GitHub repository bethanychamberlain/claude-skills-librechat (3 stars, last pushed 5mo ago), licensed MIT. It adds 54 tokens to every session and 1,946 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Building agents Claude Code agent-skills agentic-ai anthropic-claude claude-ai claude-code-plugins

TEMPLATE

../../../agents/personas/TEMPLATE.md.

alirezarezvani/claude-skills · 0 tokens

agent-teams

Multi-agent team orchestration with native Agent Teams. Trigger when the user wants to launch a team of agents, coordinate parallel work with inter-agent communication, or use swarm mode.

christopherlouet/claude-base · 39 tokens

ops-proxmox

Proxmox VE infrastructure with Terraform (VMs, LXC, network, storage, backup).

christopherlouet/claude-base · 25 tokens

cross-cutting-checklist-generator

Detect when a concern is scattered across many places in a project (config keys, enums, translations, feature flags, API endpoints, doc references) and auto-generate a project-local checklist so that same concern is never partially updated again. Use whenever you add or change something that also exists in several…

Marcel-Bich/marcel-bich-claude-marketplace · 94 tokens

mcp-builder

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).

composio-community/awesome-claude-plugins · 61 tokens

pause-subs

Temporarily disable the skill bus. Quick toggle to stop all subscriptions from firing without removing them.

composio-community/awesome-claude-plugins · 24 tokens