Trust Live
Evidence-linked MCP provider selection and non-executing Safe-Call review
- Pricing
- Free
- Platforms
- Web, API
- Runs
- Remotely
- Version
- 0.1.0
- Listing updated
- 1 day ago
About Trust Live
Trust Live is a free MCP server for ai models and llm tooling. It runs as a hosted remote server, so there is nothing to install locally.
Agent Trust Lab is a workspace for choosing among MCP providers using recorded evidence rather than rankings. Trust Live is its server, offering evidence-linked selection and a Safe-Call review that does not execute anything, and it deliberately surfaces unknowns.
The site draws from the official MCP Registry and grades the quality of listing data, such as completeness, using five source-bound criteria. It says grades are not safety, accuracy, availability or reliability ratings, that endpoints have not been tested, and that the records are not recommendations. It also compares locally validated registry snapshots to show recent changes, and a free scan builds test cases from a provider's own tool descriptions without calling business tools.
The project is on GitHub as mcp-selection-lab and runs from a hosted endpoint.
Install
Run in a terminal
claude mcp add --transport http trust-live https://mcp-selection-lab-production.up.railway.app/trust-live/mcpAdd to Settings → Connectors → Add custom connector
https://mcp-selection-lab-production.up.railway.app/trust-live/mcpAdd to ~/.cursor/mcp.json
{
"mcpServers": {
"trust-live": {
"url": "https://mcp-selection-lab-production.up.railway.app/trust-live/mcp"
}
}
}Add to .vscode/mcp.json
{
"servers": {
"trust-live": {
"type": "http",
"url": "https://mcp-selection-lab-production.up.railway.app/trust-live/mcp"
}
}
}Add to ~/.codeium/windsurf/mcp_config.json
{
"mcpServers": {
"trust-live": {
"serverUrl": "https://mcp-selection-lab-production.up.railway.app/trust-live/mcp"
}
}
}Add to your client's MCP settings (most use this shape)
{
"mcpServers": {
"trust-live": {
"type": "http",
"url": "https://mcp-selection-lab-production.up.railway.app/trust-live/mcp"
}
}
}What it does
- Evidence by capability
- Shows provider evidence by capability and version.
- Safe-Call review
- Reviews a task-specific call without executing it.
- Registry grades
- Grades listing data quality on five criteria.
- Change tracking
- Compares locally validated registry snapshots.
- Unknowns surfaced
- States what is not known about a provider.
- Metadata scan
- Generates cases from tool descriptions without calling tools.
Good for
- Compare MCP providers before wiring one into an agent
- Review a planned call without running it
- Spot recent changes in registry entries
- Check how complete a provider's metadata is
Pricing
Free
Free scan; paid options not stated
Prices change. Check mcp-selection-lab-production.up.railway.app before you buy.
Trust Live FAQ
Does it test provider endpoints?
No, the site says endpoints are not checked.
Are grades safety ratings?
No, they describe data quality only.
Does Safe-Call execute tools?
No, it is non-executing.
Where does data come from?
The official MCP Registry.
Is Trust Live free?
Yes. Trust Live is free to use.
How do I add Trust Live to Claude Code?
Run this command in your terminal: claude mcp add --transport http trust-live https://mcp-selection-lab-production.up.railway.app/trust-live/mcp
What are the best alternatives to Trust Live?
The closest alternatives to Trust Live are REA, Codebase Memory, GitHub, Serena MCP: the IDE for your agent and XERJ.
Alternatives to Trust Live

REA
MCP serverCLI and MCP server that lets coding agents reverse engineer apps and binaries
Runs locally- Open source
- 464K GitHub stars
- Developer tools

Codebase Memory
MCP serverLocal MCP server that builds a code knowledge graph for AI coding agents
Runs locally- Open source
- 48.7K GitHub stars
- Knowledge and memory

GitHub
MCP serverOfficial MCP server connecting AI assistants to GitHub repos, issues and workflows
Not checked yet- Remote
- Open source
- 34.5K GitHub stars
- Developer tools

Serena MCP: the IDE for your agent
MCP serverMCP toolkit giving coding agents symbol-level code retrieval and editing
Runs locally- Open source
- 31.5K GitHub stars
- Developer tools

XERJ
MCP serverLocal search engine for AI agents with cited answers over your code and docs
Runs locally- Open source
- 19.2K GitHub stars
- Knowledge and memory

Ouroboros
MCP serverSpec-first layer that pins requirements and verifies results of AI coding agent work
Runs locally- Open source
- 6.4K GitHub stars
- Developer tools