A Model Context Protocol server for chat completions with any AI model
Multichat MCP server exists for a simple reason — assistants are far more useful when they can act on Multichat directly instead of describing what you should do. A Model Context Protocol server for chat completions with any AI model.
Integrate Claude with Any OpenAI SDK Compatible Chat Completion API - OpenAI, Perplexity, Groq, xAI, PyroPrompts and more.
Installation goes through your MCP client rather than a global install: point it at package on npm and it is fetched when the client starts. The copy-paste blocks for Claude Desktop, Claude Code and Cursor are further down this page.
Once Multichat is connected, these are the calls the assistant has available:
Debugging — Since MCP servers communicate over stdio, debugging can be challenging. We recommend using the [MCPYou will need 7 environment variables: AI_CHAT_KEY, AI_CHAT_NAME, AI_CHAT_MODEL, AI_CHAT_BASE_URL, OPENAI_KEY, PERPLEXITY_KEY, PYROPROMPTS_KEY. The server will not start without them, which is usually why the tools fail to appear on a first run. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.
Among the developer tooling options, the useful question is rarely "what can it do" but "what does it cost you to run" — permissions, credentials, and how much of your context its toolset consumes. Multichat's toolset — Debugging — is a fair guide to whether it matches your workflow. It is maintained by felores; worth a glance at recent repository activity before you build anything load-bearing on it.
SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.
| Tool | What it does |
|---|---|
| Debugging | Since MCP servers communicate over stdio, debugging can be challenging. We recommend using the [MCP Inspector](https://github.com/modelcontextprotocol/inspector), which is available as a package script: |
{
"mcpServers": {
"chat-openai": {
"command": "npx",
"args": [
"@felores/multichat-mcp-server"
],
"env": {
"AI_CHAT_KEY": "OPENAI_KEY",
"AI_CHAT_NAME": "OpenAI",
"AI_CHAT_MODEL": "o1-preview",
"AI_CHAT_BASE_URL": "https://api.openai.com/v1"
}
},
"chat-perplexity": {
"command": "npx",
"args": [
"@felores/multichat-mcp-server"
],
"env": {
"AI_CHAT_KEY": "PERPLEXITY_KEY",
"AI_CHAT_NAME": "Perplexity",
"AI_CHAT_MODEL": "llama-3.1-sonar-small-128k-online",
"AI_CHAT_BASE_URL": "https://api.perplexity.ai"
}
}
}
}Configuration as documented by the project. Restart the client after saving.
| Variable | Description | Required |
|---|---|---|
| AI_CHAT_KEY | Credential the server authenticates with. | Yes |
| AI_CHAT_NAME | Configuration value read at startup. | Optional |
| AI_CHAT_MODEL | Configuration value read at startup. | Optional |
| AI_CHAT_BASE_URL | Endpoint or connection string the server talks to. | Yes |
| OPENAI_KEY | Credential the server authenticates with. | Yes |
| PERPLEXITY_KEY | Credential the server authenticates with. | Yes |
| PYROPROMPTS_KEY | Credential the server authenticates with. | Yes |
Kill hallucinated APIs — version-accurate, up-to-date library documentation injected straight into context.
Microsoft's official browser automation server — drive a real browser through the accessibility tree, no screenshots needed.
GitHub's official server — repos, issues, pull requests, Actions and code security, straight from your assistant.
Issue tracking at the speed of conversation — Linear's official hosted server with OAuth and zero install.
Local repository surgery — status, diffs, commits, branches and history for any repo on disk.
Timezone sanity for AI — current time anywhere and correct conversions, without the model doing date math.