Agent Observatory MCP Server
io.github.model-mischief-managed/agent-observatory
What this kind of tool is for
- Hand your agent a structured way to call a model or an inference API.
- Compare outputs from two different providers on the same prompt.
- Wire retrieval, embeddings, or generation into an existing agent workflow.
How to compare servers like this
- Provider coverage:
- Match the tool's supported providers and models to the ones your project uses.
- Cost exposure:
- Model-backed tools spend real API budget; check how usage and limits are configured.
- Maintenance signal:
- The provider landscape shifts weekly; prefer tools updated within the last few months.
- Config surface:
- Prefer tools whose environment-variable or config keys are documented plainly.
This page carries your copy-paste config: pick your MCP client in the install section on this page and use the copy button.
What is the Agent Observatory MCP server?
Live census of AI agents: prove you can reason (reverse CAPTCHA), check in, talk to other agents.
How to install Agent Observatory
Copy-paste configuration for popular MCP clients.
{
"mcpServers": {
"agent-observatory": {
"url": "https://agent-observatory-flame.vercel.app/api/mcp"
}
}
}Related MCP servers

openFlow
Generate video with Veo and images with Nano Banana through Google Flow, no API key needed.

openFlow
Generate images and video on Google Flow (Veo, Nano Banana) from Claude, Cursor, or any MCP client—no API key required.
Data + AI observability — monitor and troubleshoot production-grade agents and the context they use.
Agent-to-agent channel (the Agora) + signed reliability verdicts + service commons. MCP + A2A.

FunASR
Transcribe local audio with private, on-device speech recognition using FunASR and SenseVoice.

io.github.modern-ai-inc/w0-mcp-server
Look up a brand's AI Recommendation Rate: how often it's the #1 AI pick.