Developer · Local MCP server
AgentTrust
Quality verification for AI agents and MCP servers. 6-axis scoring, adversarial probes.
What the MCP Registry states
The entry as published to the official MCP Registry (read 2026-10-04), latest version.
- Registry name
io.github.assister-xyz/agenttrust- Version
- 0.1.2
- Status
- Active
- Category
- developer
- Transport
- stdio (local process)
- Package
- PyPI
- Published
- 2026-03-16
- Updated
- 2026-03-16
- Publisher
- assister-xyz (GitHub)
- Website
- github.com/assister-xyz/quality-oracle
- Repository
- github.com/assister-xyz/quality-oracle
- Source
- Registry API entry
Packages
| Registry | Package | Version | Transport |
|---|---|---|---|
| PyPI | mcp-agenttrust | 0.1.2 | stdio |
How to connect AgentTrust
AgentTrust runs locally from a Python package published to PyPI: mcp-agenttrust version 0.1.2. It speaks MCP over stdio, so the client starts it as a program and talks to it through standard input and output. It needs Python; clients usually start it with uvx (from uv) or after pip install — the usual command is uvx mcp-agenttrust. It reads these environment variables: GROQ_API_KEY (secret), CEREBRAS_API_KEY (secret) and MONGODB_URL (secret); set them in the client's configuration for this server.
In the mcpServers JSON format that many desktop and editor MCP clients read, the entry looks like this (placeholders in angle brackets):
{
"mcpServers": {
"agenttrust": {
"command": "uvx",
"args": [
"mcp-agenttrust"
],
"env": {
"GROQ_API_KEY": "<secret>",
"CEREBRAS_API_KEY": "<secret>",
"MONGODB_URL": "<secret>"
}
}
}
}Derived from the registry entry, not tested here. What the server does, and on what terms, is set by its publisher; check its repository or website before giving it access to your accounts or files. How to add an MCP server to an assistant · Before you connect
More developer servers
| Server | Runs |
|---|---|
| AgentSUMOMCP server for LLM-driven SUMO traffic simulation, scenario design, and result analysis. | Local · stdio |
| AgentswitchboardSearch a curated directory of 300+ verified AI agents, MCP servers, and agentic tools. | Remote · HTTP |
| agentsyncMulti-agent coordination MCP: claim work, survey peers, resolve conflicts via a git branch as CAS. | Local · stdio |
| AgentTasker MCP ServerMinimal stdio MCP server for parallel task execution by AI agents. | Local · stdio |
| AgenttunePersonality tuning files for AI agents: 43 MIT-licensed tunings + 5 inline personality tests. | Remote · HTTP |
| Agentverse MemoryGraph-native persistent memory for AI agents — 33 MCP tools, zero-LLM writes. | Remote · HTTP |
| AgentvetValidate tool-call args before execution. Returns LLM-friendly retry hints. | Local · stdio |
| AgentWatchMulti-agent observability: cascade failure detection, heartbeats, and forensic replay. | Local · stdio |