cysic-mcp
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@cysic-mcprewrite this email in a friendly tone"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
cysic-mcp
A Model Context Protocol (MCP) server in
TypeScript/Node.js that exposes the Cysic AI model
(minimax-m3) to any MCP client over stdio, with server-side session
memory and a tone-rewriting tool.
Problem
AI assistants and other MCP clients need a uniform way to call an LLM, manage multi-turn conversations across many requests, and rewrite text in different tones — but most existing LLM SDKs are HTTP-first and require per-integration boilerplate. A Cysic AI user has to:
Wire
axios(orfetch) with the rightAuthorization: Bearer …header.Implement retry/backoff for
429/5xx/ network failures.Validate every tool input with
zodso a misbehaving client cannot crash the server.Manage session state for multi-turn chat.
Plug the whole thing into their MCP client.
cysic-mcp collapses all five into a single npm install + one
configuration file.
Related MCP server: MCP SSE Proxy
Solution
cysic-mcp is a single, small Node.js process that speaks the MCP
stdio transport. It registers exactly:
3 tools:
cysic_chat,cysic_session,cysic_humanize2 resources:
cysic://models,cysic://sessions/{id}2 prompts:
code_review,humanize_text
…and nothing more. The HTTP layer is a typed CysicClient wrapper around
axios with explicit timeout + exponential-backoff retries. All tool inputs
are validated by zod. All configuration is environment-driven; the server
fails fast at startup if the required CYSIC_API_KEY is missing.
Feature Checklist
The shipped surface, one item per row:
Tool:
cysic_chat { prompt, system?, temperature? }— single-turn chat with the Cysic AI model.promptis required (min length 1);systemoverrides the default "You are a helpful assistant." preamble;temperatureis optional in[0, 2].Tool:
cysic_session { session_id, message }— multi-turn chat with server-side history. The server keeps the full conversation persession_idin an in-processMap; each call sends the entire history to the model and appends the assistant reply. Sessions are created lazily on first use.Tool:
cysic_humanize { text, tone? }— rewritetextin a requested tone.tonedefaults toneutraland acceptsneutral | friendly | formal | concise | confident. Internally uses a tone-specific system prompt and a low sampling temperature (0.2forconcise,0.4otherwise) to keep rewrites stable.Resource:
cysic://models— static catalog of models served by this MCP server, rendered as a JSONtext/plainpayload (e.g.{ models: [{ id: "minimax-m3", provider: "cysic", default: true }] }).Resource:
cysic://sessions/{id}— read template for a single session's message history. The{id}path segment is thesession_id. Returns the JSON-serialized message array; missing sessions return[].Prompt:
code_review { language?, code }— render a senior-level code-review prompt for a code snippet.languageis optional (e.g."TypeScript");codeis required. The prompt returns two messages the client can render as a chat template.Prompt:
humanize_text { tone?, text }— render a prompt that mirrors thecysic_humanizetool contract so an MCP client can present it as a chat template without invoking the tool.
Distinctive features (innovation callouts):
Server-side session memory —
cysic_sessionkeeps a per-idMap<string, Message[]>so the client does not have to round-trip history. History is in-process; sessions are lost on restart and are not shared across processes (acceptable for a single-instance stdio MCP server).cysic_humanizetone rewriting — five built-in tones (neutral,friendly,formal,concise,confident), each with its own instruction string and temperature. The same tone vocabulary is reused by thehumanize_textprompt so the prompt and the tool stay in lock-step.
Architecture
+----------------------+ stdio JSON-RPC +------------------+
| MCP client (e.g. | <--------------------------> | cysic-mcp |
| Claude Desktop, | | (Node.js) |
| any stdio MCP host) | | |
+----------------------+ | src/server.ts |
| | |
| v |
| src/tools/ |
| src/resources/ |
| src/prompts/ |
| | |
| v |
| CysicClient |
| (axios + retry) |
+--------+---------+
|
v
POST /v1/chat/completions
https://token-ai.cysic.xyzProject layout
src/
server.ts # MCP server bootstrap, transport wiring
config.ts # env loading (loadConfig)
cysicClient.ts # axios wrapper + retry/backoff
state.ts # in-process session Map (sessions)
errors.ts # CysicError + toMcpErrorMessage sanitizer
tones.ts # shared tone vocabulary (used by tool + prompt)
mcpShims.ts # untyped SDK registration shims
tools/
index.ts # registerTools(server, client, state)
cysicChat.ts # cysic_chat tool
cysicSession.ts # cysic_session tool
cysicHumanize.ts # cysic_humanize tool
resources/
index.ts # registerResources(server, state)
models.ts # cysic://models resource
session.ts # cysic://sessions/{id} resource template
prompts/
index.ts # registerPrompts(server)
codeReview.ts # code_review prompt
humanizeText.ts # humanize_text prompt
tests/
cysicClient.test.ts # 8 tests (a-e per AC-3, plus a few extras)
structure.test.ts # 5 tests defending the AC-5 module split
dist/ # tsc output (gitignored)Install
cysic-mcp requires Node.js >= 18.17 (for native fetch /
AbortController; we still use axios per the project rubric for
explicit timeout + retry control).
git clone <this-repo> cysic-mcp
cd cysic-mcp
npm install
npm run buildThe build emits dist/server.js, which is the entry point referenced by
the start script and the cysic-mcp bin.
Configure
Copy the example env file and fill in your real Cysic API key:
cp .env.example .env
# then edit .env and set CYSIC_API_KEY=...The full set of environment variables:
Variable | Required | Default | Description |
| yes | — | Bearer token for the Cysic AI endpoint. Never echoed in logs. |
| no |
| Base URL for the Cysic AI OpenAI-compatible API. |
| no |
| Default model used by the tools when no per-call override is given. |
| no |
| Per-request HTTP timeout in milliseconds. |
| no |
| Retries on |
If CYSIC_API_KEY is missing or empty, the server fails fast at
startup with a clear error message that names the variable (but does
not echo the value).
Run
Production (after npm run build):
npm start
# equivalent to: node dist/server.jsDevelopment (live TypeScript via tsx):
npm run dev
# equivalent to: tsx src/server.tsThe server uses the MCP stdio transport. There is no HTTP port to
scrape; stdout is reserved for the MCP JSON-RPC stream. All fatal
startup errors are written to stderr so they do not corrupt the MCP
channel.
MCP Client Registration
Point your MCP client at the compiled entry point. The exact JSON shape depends on the client; the two common forms are below.
Claude Desktop (claude_desktop_config.json)
Add this entry under mcpServers:
{
"mcpServers": {
"cysic": {
"command": "node",
"args": ["/absolute/path/to/cysic-mcp/dist/server.js"],
"env": {
"CYSIC_API_KEY": "sk-your-real-key-here"
}
}
}
}If you prefer the .env file approach, omit the env block and let the
server read it from disk:
{
"mcpServers": {
"cysic": {
"command": "node",
"args": ["/absolute/path/to/cysic-mcp/dist/server.js"]
}
}
}Generic stdio MCP config
Any MCP host that speaks stdio can launch the server as a child process. The minimum invocation is:
{
"command": "node",
"args": ["dist/server.js"],
"cwd": "/absolute/path/to/cysic-mcp",
"env": {
"CYSIC_API_KEY": "sk-your-real-key-here",
"CYSIC_BASE_URL": "https://token-ai.cysic.xyz/v1",
"CYSIC_MODEL": "minimax-m3"
}
}For a development-mode build, swap node + dist/server.js for
npx tsx src/server.ts and the host will run the TypeScript source
directly.
Example Tool Calls
The examples below are copy-pasteable. The exact wire format depends on
your MCP client; the JSON argument shape is what the server validates
with zod.
cysic_chat — single-turn chat
{
"name": "cysic_chat",
"arguments": {
"prompt": "What is the capital of France?",
"system": "You are a concise geography tutor.",
"temperature": 0.2
}
}Returns:
{
"content": [{ "type": "text", "text": "Paris." }],
"isError": false
}cysic_session — multi-turn chat with server-side history
Turn 1:
{
"name": "cysic_session",
"arguments": {
"session_id": "user-42",
"message": "Hi, my name is Alice."
}
}Turn 2 (the server sends the full [user, assistant, user] history to
the model):
{
"name": "cysic_session",
"arguments": {
"session_id": "user-42",
"message": "What's my name?"
}
}The full history can be inspected at runtime by reading the
cysic://sessions/user-42 resource.
cysic_humanize — tone rewriting
{
"name": "cysic_humanize",
"arguments": {
"text": "We're gonna ship the thing on Friday. Probably.",
"tone": "formal"
}
}tone defaults to neutral; the full set of accepted values is
neutral | friendly | formal | concise | confident.
cysic://models — model catalog
{ "uri": "cysic://models" }Returns a JSON payload listing the Cysic AI models served by this
server (currently { id: "minimax-m3", provider: "cysic", default: true }).
cysic://sessions/{id} — per-session history
{ "uri": "cysic://sessions/user-42" }Returns the JSON-serialized message array for user-42. Missing
sessions return [].
code_review prompt
{
"name": "code_review",
"arguments": {
"language": "TypeScript",
"code": "const x: number = 1; console.log(x);"
}
}Renders two messages the client can show as a chat template: a "you are a senior TypeScript engineer…" brief and a fenced code block to review.
humanize_text prompt
{
"name": "humanize_text",
"arguments": {
"tone": "confident",
"text": "I think maybe we could try to ship this?"
}
}Renders two messages that mirror the cysic_humanize tool contract
(the tone instruction as the first message, the text to rewrite as the
second). Because the MCP PromptMessage.role enum is restricted to
"user" | "assistant", both messages are emitted with role: "user";
the "system" intent from the plan is preserved by the
two-message shape, not by a literal role: "system".
Testing
Unit tests use vitest and stub the HTTP layer
with nock so no real network is ever
made.
npm testThe current suite covers:
tests/cysicClient.test.ts— 8 tests across the AC-3 cases (a) 200 returns first choice, (b) 429 retried then succeeds, (c) 500 retried then fails with noapiKeyin the message, (d) 400 fails fast withcode: BAD_REQUESTand is not retried, (e) request body includesmodelandmessages, plus extras for temperature pass-through, per-call model override, and empty-messages rejection.tests/structure.test.ts— 5 tests importing every per-featureregisterXfunction and theCysicError/toMcpErrorMessage/TONE_VALUES/temperatureForTone/TONE_INSTRUCTIONSexports from the compileddist/tree, to defend the AC-5 module split.
License
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Latest Blog Posts
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/nguyennpduoc/mcp-tool'
If you have feedback or need assistance with the MCP directory API, please join our Discord server