Watchlist tracking
Reviewed for relevance and future tracking value.
MCP100 Assessment
Watchlist / Tracking
Why we’re tracking it
Track client transport, server configuration, and desktop support
Reviewed · Documentation review; complete setup workflow not independently tested
Best fit
Exploring and operating MCP servers from a desktop client
What we know
Desktop MCP client/host supporting tools, prompts, resources, sampling, elicitation, registry discovery and remote MCP connectivity.
Maintenance / activity evidence
- Observed (UTC)Bump Node targets, fix path imports, tweak window height
Tracking evidence observed Oct 5, 2026. These dated signals do not establish current maintenance. Reviewed enrichment confidence: high.
Verification gaps / watch-outs
- Exact OS uninstall and provider credential-revocation procedures are not independently confirmed.
- Invokes configured MCP capabilities. Writes: Depends on downstream tools.
- Provider API keys plus downstream server auth.
- Sensitive access: Prompts, Files, Credentials, Remote server data
- TUUI is a host; effective risk is inherited from configured models and MCP servers.
Full authority, access and evidence limits are available in Review context and Access & risk.
Popularity
1,155 repository stars
Stars observed Oct 6, 2026.
No canonical package metric applied.
No canonical package metric applied.
No canonical package metric applied.
All limitations / Review context
Which MCP transports and client features does the current TUUI release provide?
The bounded assessment reviewed the official README, repository notices, security policy path, and security page for known material public-tracking blockers. No such blocker was identified. This is a public-tracking assessment, not an installation safety certification.
- TUUI is a host; effective risk is inherited from configured models and MCP servers.
- Invokes configured MCP capabilities.
- Provider API keys plus downstream server auth.
- Data flows to configured LLM and MCP servers.
- Reviewed write actions: Depends on downstream tools
- Sensitive access: Prompts, Files, Credentials, Remote server data
- Installation, client compatibility and comprehensive security have not been independently audited. Authentication and access depend on the configured services.
- Exact OS uninstall and provider credential-revocation procedures are not independently confirmed.
- No independent runtime, installation, or comprehensive security audit was performed.
- No installation, runtime, client matrix, or complete tool-contract audit was performed in this review.
- Release installer details
- Pricing
- Requires an LLM backend with tool calling.
- Remote auth depends on each server.
Original activity observations
- 2026-05-14T09:02:22Z: Bump Node targets, fix path imports, tweak window height
Technical identity
github.com/ai-ql/tuui- Exact implementation source
- https://github.com/ai-ql/tuui ↗
- Reviewed resource type
- Host
- Repository identity
- AI-QL/tuui
Evidence & Sources
- Evidence basis
- Publisher documentation
- Setup runtime verification
- Not independently runtime-tested by MCP100 for this setup workflow.
Reviewed · Latest source observation
- GitHub repository ↗
ai-ql/tuui
Recorded repository material and project history.
Includes references whose attribution is not established.
Setup · Watchlist
Host / Desktop app setup
Publisher instructions.
Source evidence observed .
Additional setup details required — see the specific gaps below.
Download / install
Publisher instructionsInstall TUUI as a desktop MCP client from its official releases, then manage other MCP server entries in TUUI. No `claude mcp add tuui` exists for this product.
Configure application / integrations
Publisher instructionsOpen TUUI and configure a model provider with a valid tool/function-calling model. Use the publisher llm.json Qwen template as a format example, replacing apiKey and selected endpoint/model privately; importing/storing settings is separate from adding an MCP server. Do not copy the demo Qwen endpoint/key as working credentials. The README documents `llm.json` and `mcp.json` schemas, and storing imported configurations in localStorage. No verified universal in-app button path is asserted.
Advanced configuration · tuui llm json example
{ "name": "Qwen", "apiKey": "REPLACE_WITH_PROVIDER_KEY", "url": "https://dashscope.aliyuncs.com/compatible-mode", "path": "/v1/chat/completions", "model": "qwen-turbo", "modelList": [ "qwen-turbo", "qwen-plus", "qwen-max" ], "maxTokensValue": "", "mcp": true }Advanced configuration · tuui mcp json example
{ "mcpServers": { "cloudflare": { "command": "npx", "args": [ "-y", "mcp-remote", "https://YOURDOMAIN.com/sse" ] } } }Check connection
Suggested checkOpen TUUI, add a known MCP server under its MCP connection settings and inspect the server tool list in TUUI. This verifies TUUI client integration; TUUI itself is not a server to register in Claude.
Disconnect / uninstall / revoke
Publisher instructionsTo disconnect an MCP integration, delete that server within TUUI settings/mcp.json. To remove TUUI, use the operating system application uninstall control. These are distinct actions.
What it does
Desktop MCP client/host supporting tools, prompts, resources, sampling, elicitation, registry discovery and remote MCP connectivity.
- Capability
- Productivity & Collaboration
- Resource type
- Host
- Industry
- Software & Technology
- Best fit
- Exploring and operating MCP servers from a desktop client
Representative uses
- Discover MCP servers
- Connect NPX/UVX/Docker servers
- Use tools/prompts/resources
- Connect remote SSE servers
- Trace tool calls
Limitations
- Requires an LLM backend with tool calling.
- Remote auth depends on each server.
Reviewed access
Access & risk
Review the exact access boundary before connecting this MCP to accounts, credentials, or sensitive data.
- Authentication
- Provider API keys plus downstream server auth.
- Permissions
- Invokes configured MCP capabilities.
- Data handling
- Data flows to configured LLM and MCP servers.
- Cost
- unknown
- Risk and cautions
- TUUI is a host; effective risk is inherited from configured models and MCP servers.
Access scope and cautions
- Write actions
- Depends on downstream tools
- Sensitive access
- Prompts Files Credentials Remote server data
- Risk level
- moderate
FAQ
Based on reviewed evidence as of 2026-10-06. Watchlist tracking is not a recommendation or a security certification.
Which tasks are documented for this implementation?
What authentication is documented?
Can it modify data or perform write operations?
What data-handling boundary should I consider?
What limitations and risks should I check before use?
Is this an official MCP?
AI-QL is listed as Community implementation in MCP100’s current evidence.