[Question]: [Troubleshooting] Cannot install LibreChat with MCP support

[tradanghi1999]

Step:

• Clone the latest code of LibreChat on github
• keep docker-compose.yml as the original
• add docker-compose.override.yml with libechat.yaml bind
• add libechat.yaml with mcp servers stdio
• keep .env as original example (add for OpenAI Rag API)

More Details

-------------------libechat.yaml--------------------

# For more information, see the Configuration Guide:
# https://www.librechat.ai/docs/configuration/librechat_yaml

# Configuration version (required)
version: 1.1.5

# Cache settings: Set to true to enable caching
cache: true

# Custom interface configuration
interface:
  # Privacy policy settings
  privacyPolicy:
    externalUrl: 'https://librechat.ai/privacy-policy'
    openNewTab: true

  # Terms of service
  termsOfService:
    externalUrl: 'https://librechat.ai/tos'
    openNewTab: true
    modalAcceptance: true
    modalTitle: "Terms of Service for LibreChat"
    modalContent: |
      # Terms and Conditions for LibreChat

      *Effective Date: February 18, 2024*

      Welcome to LibreChat, the informational website for the open-source AI chat platform, available at https://librechat.ai. These Terms of Service ("Terms") govern your use of our website and the services we offer. By accessing or using the Website, you agree to be bound by these Terms and our Privacy Policy, accessible at https://librechat.ai//privacy.

      ## 1. Ownership

      Upon purchasing a package from LibreChat, you are granted the right to download and use the code for accessing an admin panel for LibreChat. While you own the downloaded code, you are expressly prohibited from reselling, redistributing, or otherwise transferring the code to third parties without explicit permission from LibreChat.

      ## 2. User Data

      We collect personal data, such as your name, email address, and payment information, as described in our Privacy Policy. This information is collected to provide and improve our services, process transactions, and communicate with you.

      ## 3. Non-Personal Data Collection

      The Website uses cookies to enhance user experience, analyze site usage, and facilitate certain functionalities. By using the Website, you consent to the use of cookies in accordance with our Privacy Policy.

      ## 4. Use of the Website

      You agree to use the Website only for lawful purposes and in a manner that does not infringe the rights of, restrict, or inhibit anyone else's use and enjoyment of the Website. Prohibited behavior includes harassing or causing distress or inconvenience to any person, transmitting obscene or offensive content, or disrupting the normal flow of dialogue within the Website.

      ## 5. Governing Law

      These Terms shall be governed by and construed in accordance with the laws of the United States, without giving effect to any principles of conflicts of law.

      ## 6. Changes to the Terms

      We reserve the right to modify these Terms at any time. We will notify users of any changes by email. Your continued use of the Website after such changes have been notified will constitute your consent to such changes.

      ## 7. Contact Information

      If you have any questions about these Terms, please contact us at [email protected].

      By using the Website, you acknowledge that you have read these Terms of Service and agree to be bound by them.
    
# Example Registration Object Structure (optional)
registration:
  socialLogins: ['github', 'google', 'discord', 'openid', 'facebook']
  # allowedDomains:
  # - "gmail.com"

# speech:
#   tts:
#     openai:
#       url: ''
#       apiKey: '${TTS_API_KEY}'
#       model: ''
#       voices: ['']

#  
#   stt:
#     openai:
#       url: ''
#       apiKey: '${STT_API_KEY}'
#       model: ''

# rateLimits:
#   fileUploads:
#     ipMax: 100
#     ipWindowInMinutes: 60  # Rate limit window for file uploads per IP
#     userMax: 50
#     userWindowInMinutes: 60  # Rate limit window for file uploads per user
#   conversationsImport:
#     ipMax: 100
#     ipWindowInMinutes: 60  # Rate limit window for conversation imports per IP
#     userMax: 50
#     userWindowInMinutes: 60  # Rate limit window for conversation imports per user

# Definition of custom endpoints
endpoints:
  # assistants:
  #   disableBuilder: false # Disable Assistants Builder Interface by setting to `true`
  #   pollIntervalMs: 3000  # Polling interval for checking assistant updates
  #   timeoutMs: 180000  # Timeout for assistant operations
  #   # Should only be one or the other, either `supportedIds` or `excludedIds`
  #   supportedIds: ["asst_supportedAssistantId1", "asst_supportedAssistantId2"]
  #   # excludedIds: ["asst_excludedAssistantId"]
  #   Only show assistants that the user created or that were created externally (e.g. in Assistants playground).
  #   # privateAssistants: false # Does not work with `supportedIds` or `excludedIds`
  #   # (optional) Models that support retrieval, will default to latest known OpenAI models that support the feature
  #   retrievalModels: ["gpt-4-turbo-preview"]
  #   # (optional) Assistant Capabilities available to all users. Omit the ones you wish to exclude. Defaults to list below.
  #   capabilities: ["code_interpreter", "retrieval", "actions", "tools", "image_vision"]
  custom:
    # Groq Example
    - name: 'groq'
      apiKey: '${GROQ_API_KEY}'
      baseURL: 'https://api.groq.com/openai/v1/'
      models:
        default:
          [
            'llama3-70b-8192',
            'llama3-8b-8192',
            'llama2-70b-4096',
            'mixtral-8x7b-32768',
            'gemma-7b-it',
          ]
        fetch: false
      titleConvo: true
      titleModel: 'mixtral-8x7b-32768'
      modelDisplayLabel: 'groq'

    # Mistral AI Example
    - name: 'Mistral' # Unique name for the endpoint
      # For `apiKey` and `baseURL`, you can use environment variables that you define.
      # recommended environment variables:
      apiKey: '${MISTRAL_API_KEY}'
      baseURL: 'https://api.mistral.ai/v1'

      # Models configuration
      models:
        # List of default models to use. At least one value is required.
        default: ['mistral-tiny', 'mistral-small', 'mistral-medium']
        # Fetch option: Set to true to fetch models from API.
        fetch: true # Defaults to false.

      # Optional configurations

      # Title Conversation setting
      titleConvo: true # Set to true to enable title conversation

      # Title Method: Choose between "completion" or "functions".
      # titleMethod: "completion"  # Defaults to "completion" if omitted.

      # Title Model: Specify the model to use for titles.
      titleModel: 'mistral-tiny' # Defaults to "gpt-3.5-turbo" if omitted.

      # Summarize setting: Set to true to enable summarization.
      # summarize: false

      # Summary Model: Specify the model to use if summarization is enabled.
      # summaryModel: "mistral-tiny"  # Defaults to "gpt-3.5-turbo" if omitted.

      # Force Prompt setting: If true, sends a `prompt` parameter instead of `messages`.
      # forcePrompt: false

      # The label displayed for the AI model in messages.
      modelDisplayLabel: 'Mistral' # Default is "AI" when not set.

      # Add additional parameters to the request. Default params will be overwritten.
      # addParams:
      # safe_prompt: true # This field is specific to Mistral AI: https://docs.mistral.ai/api/

      # Drop Default params parameters from the request. See default params in guide linked below.
      # NOTE: For Mistral, it is necessary to drop the following parameters or you will encounter a 422 Error:
      dropParams: ['stop', 'user', 'frequency_penalty', 'presence_penalty']

    # OpenRouter Example
    - name: 'OpenRouter'
      # For `apiKey` and `baseURL`, you can use environment variables that you define.
      # recommended environment variables:
      # Known issue: you should not use `OPENROUTER_API_KEY` as it will then override the `openAI` endpoint to use OpenRouter as well.
      apiKey: '${OPENROUTER_KEY}'
      baseURL: 'https://openrouter.ai/api/v1'
      models:
        default: ['meta-llama/llama-3-70b-instruct']
        fetch: true
      titleConvo: true
      titleModel: 'meta-llama/llama-3-70b-instruct'
      # Recommended: Drop the stop parameter from the request as Openrouter models use a variety of stop tokens.
      dropParams: ['stop']
      modelDisplayLabel: 'OpenRouter'
      
    # Portkey AI Example
    - name: "Portkey"
      apiKey: "dummy"  
      baseURL: 'https://api.portkey.ai/v1'
      headers:
          x-portkey-api-key: '${PORTKEY_API_KEY}'
          x-portkey-virtual-key: '${PORTKEY_OPENAI_VIRTUAL_KEY}'
      models:
          default: ['gpt-4o-mini', 'gpt-4o', 'chatgpt-4o-latest']
          fetch: true
      titleConvo: true
      titleModel: 'current_model'
      summarize: false
      summaryModel: 'current_model'
      forcePrompt: false
      modelDisplayLabel: 'Portkey'
      iconURL: https://images.crunchbase.com/image/upload/c_pad,f_auto,q_auto:eco,dpr_1/rjqy7ghvjoiu4cd1xjbf
    
    - name: "xai"
      apiKey: "${XAI_API_KEY}"
      baseURL: "https://api.x.ai/v1"
      models:
        default: ["grok-beta"]
        fetch: false
      titleConvo: true
      titleMethod: "completion"
      titleModel: "grok-beta"
      summarize: false
      summaryModel: "grok-beta"
      forcePrompt: false
      modelDisplayLabel: "Grok"    
      iconURL: https://registry.npmmirror.com/@lobehub/icons-static-png/1.10.0/files/dark/xai.png
# fileConfig:
#   endpoints:
#     assistants:
#       fileLimit: 5
#       fileSizeLimit: 10  # Maximum size for an individual file in MB
#       totalSizeLimit: 50  # Maximum total size for all files in a single request in MB
#       supportedMimeTypes:
#         - "image/.*"
#         - "application/pdf"
#     openAI:
#       disabled: true  # Disables file uploading to the OpenAI endpoint
#     default:
#       totalSizeLimit: 20
#     YourCustomEndpointName:
#       fileLimit: 2
#       fileSizeLimit: 5
#   serverFileSizeLimit: 100  # Global server file size limit in MB
#   avatarSizeLimit: 2  # Limit for user avatar image size in MB
# See the Custom Configuration Guide for more information on Assistants Config:
# https://www.librechat.ai/docs/configuration/librechat_yaml/object_structure/assistants_endpoint

# Example MCP Servers Object Structure
mcpServers:
  everything:
    # type: sse # type can optionally be omitted
    url: http://localhost:3001/sse
  puppeteer:
    type: stdio
    command: npx
    args:
      - -y
      - "@modelcontextprotocol/server-puppeteer"
  # filesystem:
  #   # type: stdio
  #   command: npx
  #   args:
  #     - -y
  #     - "@modelcontextprotocol/server-filesystem"
  #     - /home/user/LibreChat/
  #   iconPath: /home/user/LibreChat/client/public/assets/logo.svg
  # mcp-obsidian:
  #   command: npx
  #   args:
  #     - -y
  #     - "mcp-obsidian"
  #     - /path/to/obsidian/vault
  

  ---------------------------docker-compose.override.yml--------------------------------
  
  # Please consult our docs for more info: https://www.librechat.ai/docs/configuration/docker_override

# TO USE THIS FILE, FIRST UNCOMMENT THE LINE ('services:')

# THEN UNCOMMENT ONLY THE SECTION OR SECTIONS CONTAINING THE CHANGES YOU WANT TO APPLY
# SAVE THIS FILE AS 'docker-compose.override.yaml'
# AND USE THE 'docker compose build' & 'docker compose up -d' COMMANDS AS YOU WOULD NORMALLY DO

# WARNING: YOU CAN ONLY SPECIFY EVERY SERVICE NAME ONCE (api, mongodb, meilisearch, ...)
# IF YOU WANT TO OVERRIDE MULTIPLE SETTINGS IN ONE SERVICE YOU WILL HAVE TO EDIT ACCORDINGLY

# EXAMPLE: if you want to use the config file and the latest numbered release docker image the result will be:
version: "3.9"
services:
  api:
    #image: ghcr.io/danny-avila/librechat-dev:latest
    volumes:
    - type: bind
      source: ./librechat.yaml
      target: /app/librechat.yaml
    image: ghcr.io/danny-avila/librechat-dev:latest

Screenshots

2024-12-20 03:24:28 2024-12-19 20:24:28 info: Custom config file loaded:
2024-12-20 03:24:28 2024-12-19 20:24:28 info: {
2024-12-20 03:24:28 "version": "1.1.5",
2024-12-20 03:24:28 "cache": true,
2024-12-20 03:24:28 "interface": {
2024-12-20 03:24:28 "privacyPolicy": {
2024-12-20 03:24:28 "externalUrl": "https://librechat.ai/privacy-policy",
2024-12-20 03:24:28 "openNewTab": true
2024-12-20 03:24:28 },
2024-12-20 03:24:28 "termsOfService": {
....

Code of Conduct

• I agree to follow this project's Code of Conduct

[danny-avila]

SSE Servers need to be running beforehand from an independent process. They cannot be spawned by LibreChat (only URLs are provided).

[kjbrum]

So LibreChat assumes you have MCP servers set up on a server and running? That definitely isn't clear from the documentation.

It would be really helpful to better address this in the documentation to help people less familiar get them set up (like myself!).

Would it be possible to "piggyback" off the LibreChat infra if we're already using Docker? 🤔

[danny-avila]

This only applies to MCP servers with SSE transports. This is true for any application that supports MCP servers with SSE Transports:

https://modelcontextprotocol.io/docs/concepts/transports#server-sent-events-sse

Most MCP servers utilize stdio transport, but the one erroring in OP's logs does not.

If using MCP servers with stdio transports, LibreChat will attempt to spawn the process using the specified command.

Would it be possible to "piggyback" off the LibreChat infra if we're already using Docker?

Yes, however, python dependencies are not included in LibreChat's MCP infra, so uvx commands will fail unless you are using your own infra directly (using LC outside of Docker)

To facilitate using MCP servers with any transport, and make it directly compatible with LC running on docker, the following projects can be leveraged:

• https://github.com/acehoss/mcp-gateway
• https://github.com/supercorp-ai/supergateway

[Passerby1011]

I thought that "everything" was the famous file search software?
Is that it?

[danny-avila]

No “everything” is an example MCP server, it doesn’t do anything

[madrover]

For reference, I've been able to use mcp-gateway on my Docker Compose based LibreChat deployment and connect to remote MCP servers following acehoss/mcp-gateway#1
For some reason I was not able to connect with supergateway on the remote host.